{"family":"agents","name":"Agent Frameworks & Harnesses","count":235,"license":"CC-BY-4.0","systems":[{"id":"11x-ai--11x-ai","name":"11x.ai","url":"https://www.11x.ai/","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"AI sales agents (Alice, Mike, Jordan)","license":"","latest_release":"","deployment":"Managed-only — hosted SaaS AI sales agents","pricing":"Per-seat / per-agent enterprise tiers","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2022 by Hasan Sukkar; AI sales agents Alice (outbound SDR), Mike (voice SDR), Jordan (RevOps). $50M Series B Oct-2024 (Benchmark + Andreessen Horowitz; $350M val). Among the most-discussed AI-employee startups of 2024.","cited_cells":21,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/11x-ai--11x-ai"},{"id":"6sense--6sense-com","name":"6sense","url":"https://6sense.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"ABM intent + AI agent platform","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — 6sense MCP Server (listed as New); intelligence can be activated via APIs and MCP","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2013; ABM/intent platform with Revenue AI agents. $200M Series E Jan-2022 ($5.2B val; Blue Owl). 6sense Revenue AI agents launched 2024 — autonomous account research + email drafting.","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/6sense--6sense-com"},{"id":"adept-act--adept-ai","name":"Adept ACT","url":"https://www.adept.ai/","section":"Multi-agent orchestration platforms","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Computer-use / workflow-automation agent (Adept now part of Amazon AGI 2024)","license":"","latest_release":"","deployment":"","pricing":"Pre-acq: enterprise pilot only","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"single-vendor (Adept-proprietary ACT models historically)","github":"","description":"Founded 2022 by David Luan and fellow ex-OpenAI / Google researchers. Built ACT-1 / ACT-2 multimodal action transformers for computer-use. In June 2024 Amazon hired Luan and co-founders (Odena, Nye, Elsen, Szot) into Amazon AGI and licensed Adept's technology (acqui-hire, not a full acquisition); Adept continues with former head of engineering Zach Brock as CEO, refocused on agentic AI solutions. Important historical entry — ACT models inspired Anthropic Computer Use + OpenAI Operator.","cited_cells":19,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/adept-act--adept-ai"},{"id":"agency-swarm--gh-vrsen-agency-swarm","name":"Agency Swarm","url":"https://github.com/VRSEN/agency-swarm","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"OpenAI-Assistants-based multi-agent","license":"MIT","latest_release":"v1.11.0 (2026-08-03)","deployment":"Self-hosted only — library","pricing":"free (OSS)","mcp_support":"yes — official MCP client support (MCP servers incl. per-user OAuth via MCPServerOAuth, v1.11.0)","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"VRSEN/agency-swarm — ~4.6k stars, last commit 2026-08","description":"Multi-agent orchestration framework — 'agencies' of agents with defined communication flows; v1.x is rebuilt on the OpenAI Agents SDK (originally built on the Assistants API).","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/agency-swarm--gh-vrsen-agency-swarm"},{"id":"agent-qa--vostride-com","name":"Agent QA","url":"https://vostride.com/docs/agent-qa","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-22","type":"Harness","license":"Other (specify in notes)","latest_release":"last commit 2026-08-03","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/vostride/agent-qa (897★)","description":"Agent-driven runtime for testing web, Android, and iOS user flows from YAML, with a local dashboard, CLI/MCP control, and recorded evidence. Traction: Submitted via intake issue #182","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/agent-qa--vostride-com"},{"id":"agent2agent-protocol-a2a--google-github-io","name":"Agent2Agent Protocol (A2A)","url":"https://a2a-protocol.org/","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Open agent-to-agent protocol","license":"Apache-2.0","latest_release":"v1.0.1 (2026-05-28)","deployment":"Self-hosted only — open protocol spec + SDKs","pricing":"free (OSS)","mcp_support":"searched not found","a2a_support":"yes — this is the A2A protocol specification itself","backend_storage":"","llm_lock":"searched not found","github":"a2aproject/A2A — ~25.5k stars, last commit 2026-05","description":"Google-led open protocol for agent-to-agent collaboration (announced 2025-04-09) — agent cards, RPCs, server-sent events. Launched with 50+ technology partners including Atlassian, MongoDB, Salesforce, ServiceNow.","cited_cells":19,"third_party_cells":7,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/agent2agent-protocol-a2a--google-github-io"},{"id":"agntcy-internet-of-agents--agntcy-org","name":"AGNTCY (Internet of Agents)","url":"https://agntcy.org/","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Cisco-LangChain agent-mesh protocols","license":"Apache-2.0","latest_release":"searched not found","deployment":"Self-hosted only — open-source components (OASF, SLIM, Directory, Identity)","pricing":"free (OSS)","mcp_support":"yes — official (AGNTCY Identity onboards/verifies MCP servers)","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"agntcy (org, ~51 repos) — top: agntcy/oasf ~339 stars, agntcy/slim ~226 stars, last commit 2026-10","description":"Cisco + LangChain-led 'Internet of Agents' collective — open standards for discovery, messaging, observability of agent networks.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/agntcy-internet-of-agents--agntcy-org"},{"id":"aider-harness--aider-chat","name":"Aider (harness)","url":"https://aider.chat","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-31","type":"Terminal-native AI pair programmer (OSS, Python)","license":"Apache-2.0","latest_release":"v0.86.2 (2026-02-12)","deployment":"Self-hosted only — local CLI (pip install aider-chat); BYO LLM provider","pricing":"Free (OSS); usage via LLM provider","mcp_support":"no — no MCP client/server in Aider README or docs","a2a_support":"searched not found","backend_storage":"local repo + CONVENTIONS.md","llm_lock":"","github":"Aider-AI/aider — ~49.7k stars, last commit 2026-02 (last push 2026-02-25 per ecosyste.ms)","description":"OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in \"Coding-agent memory\"; this row characterises the harness itself.","cited_cells":50,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/aider-harness--aider-chat"},{"id":"alphasense--alpha-sense-com","name":"AlphaSense","url":"https://www.alpha-sense.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Financial-research search platform + Genesis AI agent","license":"","latest_release":"","deployment":"Managed-only — SaaS; enterprise deployment to AWS/GCP also offered","pricing":"","mcp_support":"yes — MCP tools exposed through the AlphaSense Agent API (alongside GenSearch, ThinkLonger, DeepResearch)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2010; AI-driven market intelligence — semantic search over earnings calls, broker research, regulatory filings. $4B val Jun-2024 ($650M growth round; BDT + MSP). **Acquired Tegus Jun-2024 for $930M** (expert-call transcripts). Genesis = autonomous research agent launched 2024.","cited_cells":22,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/alphasense--alpha-sense-com"},{"id":"amazon-q-developer--aws-amazon-com","name":"Amazon Q Developer","url":"https://aws.amazon.com/q/developer/","section":"Agent IDEs & coding harnesses","tier":1,"status":"deprecated","last_verified_at":"2026-10-31","type":"AWS-hosted developer AI agent + IDE plugins","license":"","latest_release":"","deployment":"Managed-only — AWS-hosted service via IDE plugins, AWS Console and CLI","pricing":"Free tier (50 agentic requests/mo); Pro $19/user/mo — new subscriptions closed from 2026-05-15","mcp_support":"yes — MCP support in Q Developer agentic coding (carried over to successor Kiro per AWS)","a2a_support":"searched not found","backend_storage":"AWS-hosted","llm_lock":"","github":"","description":"Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows. End of support for the Amazon Q Developer IDE plugins is set for 2027-04-30 per an AWS notice, which points users to Kiro as the successor.","cited_cells":58,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/amazon-q-developer--aws-amazon-com"},{"id":"anchor-anchor-browser--anchorbrowser-io","name":"Anchor (Anchor Browser)","url":"https://anchorbrowser.io/","section":"AI sandbox & runtime environments","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Cloud-hosted browser for AI agents (anti-detect, persistent state)","license":"","latest_release":"","deployment":"Managed-only — cloud-hosted Chromium browsers","pricing":"Free ($5 credits/mo, 5 concurrent browsers); Starter $50/mo; Growth $2,000/mo; Enterprise custom","mcp_support":"yes — official MCP server (hosted at api.anchorbrowser.io/v1/mcp + open-source version)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Anchor Browser provides cloud-hosted Chromium instances optimised for AI agent use — anti-detect, persistent sessions, residential proxies, CAPTCHA handling. Founded 2023, YC W24. $2.6M seed disclosed. Distinct from Browserless by adding persistent-state + anti-detect optimised for AI-agent web workflows.","cited_cells":29,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/anchor-anchor-browser--anchorbrowser-io"},{"id":"anthropic-computer-use--docs-anthropic-com","name":"Anthropic Computer Use","url":"https://docs.anthropic.com/en/docs/agents-and-tools/computer-use","section":"Computer-use & desktop agents","tier":1,"status":"active","last_verified_at":"2026-10-31","type":"Claude desktop-control capability (Anthropic API)","license":"proprietary (Claude API feature)","latest_release":"computer_toolset_20260801 (2026-08) — current tool version, no beta header required","deployment":"Managed-only — Claude API tool (also Bedrock, Vertex, Foundry); actions execute in a caller-provided desktop environment","pricing":"Standard Claude API token pricing; ~4.5k input-token toolset overhead plus screenshots billed as image input; no per-action fee","mcp_support":"no — computer use is a client-executed API tool, not an MCP server or client","a2a_support":"searched not found","backend_storage":"stateless API","llm_lock":"","github":"","description":"Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.","cited_cells":62,"third_party_cells":11,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/anthropic-computer-use--docs-anthropic-com"},{"id":"anvilogic-forge--anvilogic-com","name":"Anvilogic Forge","url":"https://www.anvilogic.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Detection-engineering platform with AI Forge","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — platform exposes an Anvilogic MCP and connects to third-party MCP servers (per platform architecture diagram)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2019 by ex-Yahoo CISO Karthik Kannan; AI-driven detection-engineering platform. $45M Series C Jul-2024 (Evolution + G Squared; ~$200M val). Forge is the AI agent that auto-generates SIEM detections.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/anvilogic-forge--anvilogic-com"},{"id":"apex-security--apex-security","name":"Apex Security","url":"https://www.apex.security/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Generative-AI security platform (red-team + DLP + runtime)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2023 by Tomer Avni + Matan Getz (ex-Microsoft); generative-AI security platform spanning red-teaming, DLP, and runtime. $7M seed Apr-2024 (Sequoia + Index Ventures).","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/apex-security--apex-security"},{"id":"apollo-io--apollo-io","name":"Apollo.io","url":"https://www.apollo.io/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"GTM platform with AI agents (Apollo AI)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — hosted remote MCP server at https://mcp.apollo.io/mcp (Streamable HTTP, OAuth 2.0 or master API key)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2015 (rebranded from ZenProspect); GTM platform — prospecting database + outreach + AI. $100M Series D Aug-2023 ($1.6B val; Bain Capital Ventures + Sequoia). $200M+ ARR; Apollo AI launched 2024.","cited_cells":21,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/apollo-io--apollo-io"},{"id":"arcade-dev--arcade-dev","name":"Arcade.dev","url":"https://www.arcade.dev/","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"OAuth + tools for agents","license":"MIT (arcade-mcp framework); proprietary (Arcade Cloud / Engine)","latest_release":"v1.16.3 (2026-10-14) — arcade-mcp","deployment":"Both (self-hosted + managed cloud) — Arcade Cloud; VPC or air-gapped deployment on Enterprise","pricing":"Free ($0: 2,000 auth events + 2,000 tool calls/mo); Team from $25/mo + usage; Enterprise custom","mcp_support":"yes — official MCP server framework (arcade-mcp) + MCP gateway","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"ArcadeAI/arcade-mcp — ~1.1k stars, last commit 2026-10","description":"Authorization + tool platform for AI agents — managed OAuth so agents act on user accounts, an MCP server framework (arcade-mcp) and MCP gateway with thousands of pre-built tools.","cited_cells":21,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/arcade-dev--arcade-dev"},{"id":"auditboard--auditboard-com","name":"AuditBoard (now Optro)","url":"https://optro.ai/","section":"Use-case-specific agent harnesses","tier":2,"status":"acquired","last_verified_at":"2026-10-28","type":"Enterprise GRC platform with AI features","license":"","latest_release":"","deployment":"SaaS + private cloud","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2014; enterprise audit + GRC platform — 60%+ of Fortune 500 customers. **Acquired by Hg for $3B Jun-2024** (private-equity take-private). AI features added 2024 — auto-population of audit workpapers, AI-assisted issue classification.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/auditboard--auditboard-com"},{"id":"auth0-for-ai-agents--auth0-com","name":"Auth0 for AI Agents","url":"https://auth0.com/ai/docs/overview","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Auth0's identity layer for AI agents, covering user authentication, calling first- and third-party APIs on a user's behalf through delegated authorization, asynchronous human-in-the-loop approval (CIBA), fine-grained authorization for RAG, and auth for MCP.","cited_cells":11,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/auth0-for-ai-agents--auth0-com"},{"id":"autogen-ag2--gh-ag2ai-ag2","name":"AutoGen / AG2","url":"https://github.com/ag2ai/ag2","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-31","type":"Multi-agent conversation framework","license":"Apache-2.0","latest_release":"v1.2.1 (2026-10-21)","deployment":"Self-hosted only — library","pricing":"free (OSS)","mcp_support":"yes — official MCP client support (autogen.mcp.create_toolkit)","a2a_support":"yes — native A2A server + client since AG2 v0.10 (2025-10)","backend_storage":"","llm_lock":"searched not found","github":"ag2ai/ag2 — ~4.9k stars, last commit 2026-10","description":"Originally Microsoft Research's multi-agent framework — fork branded AG2 (2024-10) led by community. Memory is one optional component (AutoGen Memory cross-listed).","cited_cells":44,"third_party_cells":9,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/autogen-ag2--gh-ag2ai-ag2"},{"id":"autogpt--gh-significant-gravitas-autogpt","name":"AutoGPT","url":"https://github.com/Significant-Gravitas/AutoGPT","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-31","type":"Autonomous task agent (origin)","license":"MIT (classic/ + other files); Polyform Shield 1.0.0 (autogpt_platform/)","latest_release":"autogpt-platform-beta-v0.9.0 (2026-10-23)","deployment":"Both (self-hosted + managed cloud) — hosted AutoGPT Platform; self-host via Docker / Compose","pricing":"free self-host; hosted AutoGPT Platform paid with trial","mcp_support":"yes — official MCP integrations in AutoGPT Platform (MCP server auth, MCP 2026-07-28 spec support)","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"Significant-Gravitas/AutoGPT — ~187.7k stars, last commit 2026-10","description":"The first viral autonomous agent demo (March 2023) — GPT-4 + memory + tool use + self-direction. Significant Gravitas raised $12M to commercialise the AutoGPT Platform.","cited_cells":24,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/autogpt--gh-significant-gravitas-autogpt"},{"id":"babyagi--gh-yoheinakajima-babyagi","name":"BabyAGI","url":"https://github.com/yoheinakajima/babyagi","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Task-loop agent (origin)","license":"MIT","latest_release":"no GitHub releases","deployment":"Self-hosted only — library","pricing":"free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"yoheinakajima/babyagi — ~22.3k stars, last commit unknown (not archived)","description":"Yohei Nakajima's iconic spring-2023 task-list agent loop (original now in babyagi_archive); the repo now hosts an experimental self-building 'functionz' function framework.","cited_cells":21,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/babyagi--gh-yoheinakajima-babyagi"},{"id":"bedrock-agentcore-aws--aws-amazon-com","name":"Bedrock AgentCore (AWS)","url":"https://aws.amazon.com/bedrock/agentcore/","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"AWS-managed runtime + memory + tools for agents","license":"","latest_release":"","deployment":"Managed-only — AWS-hosted (Runtime, Gateway, Memory, Identity, Browser, Code Interpreter, Observability)","pricing":"Pay-per-use, no seat fee: Runtime from $0.0895/vCPU-hr + $0.00945/GB-hr; Gateway $0.005/1k calls; new AWS customers get up to $200 Free Tier credits","mcp_support":"yes — Gateway exposes APIs/Lambdas as MCP servers; Runtime hosts MCP-compatible tools; Agent Registry publishes MCP servers","a2a_support":"searched not found","backend_storage":"AWS-managed (DynamoDB, S3, OpenSearch under the hood)","llm_lock":"","github":"aws/bedrock-agentcore-sdk-python — ~750 stars (Apache-2.0 SDK; service itself closed source), last commit n/a","description":"AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).","cited_cells":37,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/bedrock-agentcore-aws--aws-amazon-com"},{"id":"beeai-framework--gh-i-am-bee-beeai-framework","name":"BeeAI Framework","url":"https://github.com/i-am-bee/beeai-framework","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Framework","license":"Apache-2.0","latest_release":"last commit 2026-10-23","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/i-am-bee/beeai-framework (3443★)","description":"Framework for production-ready AI agents in Python and TypeScript (Linux Foundation / IBM BeeAI).","cited_cells":16,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/beeai-framework--gh-i-am-bee-beeai-framework"},{"id":"bland-ai--bland-ai","name":"Bland AI","url":"https://www.bland.ai/","section":"Voice agent platforms","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Developer platform for AI phone agents (vertically integrated)","license":"","latest_release":"","deployment":"Both (self-hosted + managed cloud) — managed cloud by default; on-prem/VPC deployment on Enterprise only","pricing":"Start: $0 platform fee + $0.14/connected min; Build: $299/mo + $0.12/min; Enterprise custom","mcp_support":"yes — remote MCP server at api.bland.ai/v1/mcp for MCP clients (Claude, Claude Code, ChatGPT, VS Code, Windsurf, Gemini CLI)","a2a_support":"searched not found","backend_storage":"Call + pathway state in Bland-managed DB","llm_lock":"","github":"","description":"Voice-AI platform with custom STT + LLM + TTS stack ('the whole pipeline'). Raised $40M Series A Apr-2024 (Lightspeed + Anthology). Distinguished by 'pathway' graphs (deterministic call flows) and aggressive outbound-calling positioning.","cited_cells":46,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/bland-ai--bland-ai"},{"id":"bolt-new-stackblitz-harness--bolt-new","name":"Bolt.new (StackBlitz) — harness","url":"https://bolt.new","section":"Agent IDEs & coding harnesses","tier":1,"status":"inactive","last_verified_at":"2026-10-28","type":"Browser-only AI app builder (StackBlitz WebContainer)","license":"","latest_release":"","deployment":"Managed-only — browser-based (StackBlitz WebContainers); apps hosted on Bolt","pricing":"Free (1M tokens/mo, 300K/day cap); Pro $25/mo (10M tokens); Teams $30/member/mo; Enterprise custom","mcp_support":"yes — client: connect MCP servers so Bolt can use external apps/data in chat","a2a_support":"searched not found","backend_storage":"browser (WebContainer) + cloud session","llm_lock":"","github":"stackblitz/bolt.new — ~16.6k stars, last commit 2024-12 (open-source repo, not archived)","description":"Cross-listing of Bolt.new at the harness layer. StackBlitz's WebContainer technology runs full Node.js in-browser; Bolt prompts the user for an app spec, then writes/edits/runs/deploys it entirely in-browser. The Coding-agent-memory row remains canonical for the memory framing.","cited_cells":57,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/bolt-new-stackblitz-harness--bolt-new"},{"id":"browser-use--browser-use-com","name":"Browser Use","url":"https://browser-use.com/","section":"Computer-use & desktop agents","tier":1,"status":"active","last_verified_at":"2026-10-31","type":"OSS browser-agent library + Cloud (browser-use)","license":"MIT","latest_release":"v0.13.11 (2026; release date not confirmed)","deployment":"Both (self-hosted + managed cloud) — OSS Python library + Browser Use Cloud; on-prem via sales","pricing":"OSS library free; Cloud pay-as-you-go: $1 free credit, $5 min top-up, browsers $0.02/hr, agents = model price +20%; on-prem via sales","mcp_support":"yes — first-party hosted MCP server (api.browser-use.com/v3/mcp) plus local stdio browser-harness-mcp","a2a_support":"searched not found","backend_storage":"Local Playwright state; Cloud uses managed Postgres","llm_lock":"","github":"browser-use/browser-use — ~119k stars, last commit 2026-09+ (release 0.13.10 on 2026-09-04)","description":"Python library that turns any LLM into a browser agent — extracts DOM into a structured representation the LLM can act on (rather than pure screenshot). Browser Use Inc. raised $17M seed Q1 2025 (Felicis); cloud product at cloud.browser-use.com. Project is one of the most-starred browser-agent OSS repos.","cited_cells":67,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/browser-use--browser-use-com"},{"id":"browserless-io--browserless-io","name":"Browserless.io","url":"https://www.browserless.io/","section":"AI sandbox & runtime environments","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Headless browser-as-a-service (Chromium / Playwright API for AI agents)","license":"SSPL-1.0 + Browserless Commercial License (dual; commercial use needs commercial licence)","latest_release":"","deployment":"Both (self-hosted + managed cloud) — Browserless cloud or self-hosted Docker image","pricing":"Hobby ($50/mo) + Startup ($200/mo) + Business + Enterprise (quote); per-session pricing model","mcp_support":"yes — official Browserless MCP server (premium feature)","a2a_support":"","backend_storage":"","llm_lock":"","github":"browserless/browserless — ~13.8k stars, last commit not retrieved (not archived)","description":"Browserless is a headless-browser-as-a-service — managed Chromium / Playwright / Puppeteer endpoints for web scraping, screenshots, PDF generation, web automation. Increasingly used as substrate for browser-agent products. Founded 2017 by Joel Griffith. Bootstrapped + small seed. Distinct from Playwright OSS — Browserless ships managed Chromium farms with anti-bot circumvention.","cited_cells":28,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/browserless-io--browserless-io"},{"id":"burr-dagworks--gh-dagworks-inc-burr","name":"Burr (DAGWorks)","url":"https://github.com/apache/burr","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"State-machine agent framework","license":"Apache-2.0","latest_release":"v0.43.0 (2026-08-25) — apache-burr","deployment":"Self-hosted only — library + self-hosted tracking UI","pricing":"free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"","llm_lock":"multi-vendor (BYO)","github":"apache/burr (formerly DAGWorks-Inc/burr) — ~2.6k stars, last commit 2026-08","description":"State-machine framework for agents — state + actions + transitions; lightweight alternative to LangGraph. Created by DAGWorks and donated to the Apache Software Foundation, where it is now Apache Burr (incubating).","cited_cells":34,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/burr-dagworks--gh-dagworks-inc-burr"},{"id":"bytebot--bytebot-ai","name":"Bytebot","url":"https://bytebot.ai/","section":"Computer-use & desktop agents","tier":3,"status":"archived","last_verified_at":"2026-10-29","type":"OSS desktop-control agent runtime (containerised Linux desktop)","license":"Apache-2.0","latest_release":"none — no GitHub releases published; repo archived 2026-03-07","deployment":"Self-hosted only — Docker (Linux desktop container); repo archived","pricing":"Free (Apache-2.0 OSS; repo archived, no paid tier listed)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Container ephemeral disk; user provides durable storage","llm_lock":"","github":"bytebot-ai/bytebot — ~11.1k stars, archived 2026-03-07","description":"Open-source desktop-agent runtime that runs an LLM-controlled Linux desktop inside Docker — uses xdotool / X11 capture for control. Pitched as the 'self-hosted Operator' alternative; agent sees a real desktop screen, not just a browser.","cited_cells":39,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/bytebot--bytebot-ai"},{"id":"callrail-conversation-intelligence--callrail-com","name":"CallRail Conversation Intelligence","url":"https://www.callrail.com/conversation-intelligence","section":"Voice agent platforms","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Conversation intelligence / call analytics platform","license":"","latest_release":"","deployment":"Managed-only — CallRail-hosted SaaS","pricing":"No free tier; plans from $50/mo (Lead Tracking); Premium Conversation Intelligence included in Lead Conversion ($150/mo) and Lead Conversion Complete ($195/mo)","mcp_support":"no — not mentioned on product page","a2a_support":"searched not found","backend_storage":"CallRail-managed cloud (call recording + AI metadata)","llm_lock":"","github":"","description":"CallRail's AI-driven conversation intelligence layer atop their call-tracking product. Marketing-vertical voice analytics — auto-tagging, sentiment, lead scoring. CallRail is profitable / private (Sageview-backed); not a voice-agent runtime but the BI / analytics adjacent layer.","cited_cells":42,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/callrail-conversation-intelligence--callrail-com"},{"id":"calypso-ai--calypsoai-com","name":"Calypso AI (now F5 AI Guardrails)","url":"https://www.f5.com/products/ai-guardrails","section":"Use-case-specific agent harnesses","tier":2,"status":"acquired","last_verified_at":"2026-10-28","type":"Enterprise LLM/agent security & content scanner","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Dublin / NYC founded 2018; GenAI security and content scanning. $23M Series A-1 Aug-2024 (Paladin Capital + Lockheed Martin Ventures). Pivoted from defence ML to enterprise GenAI guardrails 2023-24.","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/calypso-ai--calypsoai-com"},{"id":"camel--gh-camel-ai-camel","name":"CAMEL","url":"https://github.com/camel-ai/camel","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-31","type":"Framework","license":"Apache-2.0","latest_release":"last commit 2026-10-19","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/camel-ai/camel (17973★)","description":"Open-source multi-agent framework for role-playing agent societies, data generation and agent scaling research.","cited_cells":18,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/camel--gh-camel-ai-camel"},{"id":"cartesia-sonic--cartesia-ai","name":"Cartesia Sonic","url":"https://cartesia.ai/sonic","section":"Voice agent platforms","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Real-time TTS + voice-agent platform (Cartesia)","license":"","latest_release":"Sonic-3.6 (current model; release date not stated)","deployment":"Both (self-hosted + managed cloud) — managed API; on-prem (incl. air-gapped), customer VPC and OEM under enterprise contract","pricing":"Free (20K credits/mo); Pro $5/mo; Startup $49/mo; Scale $299/mo; Enterprise custom; managed voice agents $0.06/min","mcp_support":"yes — official Cartesia MCP server (cartesia-ai/cartesia-mcp)","a2a_support":"searched not found","backend_storage":"Stateless API; caller manages state","llm_lock":"","github":"github.com/cartesia-ai (SDKs)","description":"Cartesia's Sonic TTS — state-space-model-based voice generation, lowest published TTS latency (~40ms). Cartesia raised $64M Series A Q1 2025 (Index + Lightspeed); founded by Mamba authors. Agent platform layer ('Cartesia Line') wraps Sonic with telephony + LLM.","cited_cells":46,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cartesia-sonic--cartesia-ai"},{"id":"causaly--causaly-com-2","name":"Causaly","url":"https://www.causaly.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Biomedical knowledge-graph + AI research agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — Causaly scientific capabilities (literature, knowledge graph, workflows) callable via MCP, A2A and APIs","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Cross-listing: Causaly already exists in Scientific / research AI memory. This row adds the use-case agent harness framing: London-based biomedical-research AI for drug-discovery teams. $60M Series B 2023 (Index + ICONIQ). 25M+ scientific articles indexed; causal-graph-grounded.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/causaly--causaly-com-2"},{"id":"charm-crush--gh-charmbracelet-crush","name":"Charm Crush","url":"https://github.com/charmbracelet/crush","section":"Agent IDEs & coding harnesses","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Terminal-native AI coding agent (Charm; TUI)","license":"FSL-1.1-MIT (source-available; converts to MIT after 2 years)","latest_release":"v0.92.0 (2026-08-31)","deployment":"Self-hosted only — local terminal TUI/CLI (Go)","pricing":"Free (OSS)","mcp_support":"yes — MCP client (http, stdio and sse servers)","a2a_support":"searched not found","backend_storage":"local config","llm_lock":"","github":"charmbracelet/crush — ~27.9k stars, last commit 2026-09","description":"Charm Bracelet's terminal-native AI coding assistant — built in Go atop the Bubble Tea TUI framework. Multi-model via Glamour/Mods integration. Open-sourced 2025; positioned as a TUI-native alternative to web/Electron harnesses for developers who live in the terminal.","cited_cells":46,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/charm-crush--gh-charmbracelet-crush"},{"id":"chatgpt-codex-cloud-agent--chatgpt-com","name":"ChatGPT — Codex (cloud agent)","url":"https://chatgpt.com/codex","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"OpenAI's ChatGPT-integrated cloud coding agent","license":"","latest_release":"","deployment":"Managed-only — OpenAI-hosted sandboxed cloud environments, via ChatGPT web/app (chatgpt.com/codex), IDE extension and CLI","pricing":"Included in ChatGPT plans (Free/Go limited, Plus $20/mo, Pro $100–200/mo, Business $25/user/mo); usage metered in credits per model tokens","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"cloud sandbox per task","llm_lock":"","github":"","description":"OpenAI's cloud-hosted, asynchronous coding agent surfaced inside ChatGPT — distinct from Codex CLI (terminal) and from the deprecated 2021 Codex API. Released 2025-05. Reads + writes from sandboxed cloud environments; integrates with GitHub. Cross-listing — the coding-agent-memory row remains canonical for memory framing.","cited_cells":57,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/chatgpt-codex-cloud-agent--chatgpt-com"},{"id":"claude-agent-sdk--gh-anthropics-claude-agent-sdk-python","name":"Claude Agent SDK","url":"https://github.com/anthropics/claude-agent-sdk-python","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Framework","license":"MIT","latest_release":"last commit 2026-10-24","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/anthropics/claude-agent-sdk-python (8347★)","description":"Anthropic's SDK for building agents on the Claude Code agent loop (tools, sub-agents, MCP); published to PyPI as claude-agent-sdk.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/claude-agent-sdk--gh-anthropics-claude-agent-sdk-python"},{"id":"claude-code-anthropic--anthropic-com","name":"Claude Code (Anthropic)","url":"https://www.anthropic.com/claude-code","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"Terminal-native agentic coding harness","license":"proprietary — © Anthropic PBC, use subject to Anthropic Commercial Terms (repo public, not OSS)","latest_release":"v2.1.310 (2026-10-23)","deployment":"Both (self-hosted + managed cloud) — local CLI/IDE/desktop client plus cloud sessions on web; models via Anthropic API (or Bedrock/Vertex)","pricing":"No free tier; included in Pro ($20/mo, $17 annual), Max (from $100/mo), Team ($25/seat/mo, $20 annual), Enterprise; or API pay-per-token via Console","mcp_support":"yes — MCP client (claude mcp add; stdio and HTTP servers)","a2a_support":"searched not found","backend_storage":"local CLAUDE.md + ~/.claude state + git","llm_lock":"","github":"anthropics/claude-code — ~153k stars, last commit 2026-10","description":"Anthropic's agentic coding tool: Claude as a coding agent in the terminal, IDEs (VS Code, JetBrains), desktop app, web/mobile, GitHub and Slack. Context via CLAUDE.md, skills, hooks, subagents and MCP servers.","cited_cells":67,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/claude-code-anthropic--anthropic-com"},{"id":"claude-for-chrome--anthropic-com","name":"Claude for Chrome","url":"https://claude.com/resources/articles/claude-for-chrome","section":"Computer-use & desktop agents","tier":1,"status":"active","last_verified_at":"2026-10-29","type":"Consumer browser-agent extension (Chrome) — Anthropic","license":"","latest_release":"","deployment":"Managed-only — Chrome extension in the user's browser; model runs in Anthropic cloud","pricing":"Not on Free; included in Pro ($20/mo, $17 annual), Max (from $100/mo), Team and Enterprise","mcp_support":"Claude supports MCP servers (caller-side)","a2a_support":"searched not found","backend_storage":"Anthropic-managed session state; local extension storage","llm_lock":"","github":"","description":"Anthropic's Chrome extension (Claude in Chrome) letting Claude act inside the user's own browser. Research preview Aug 2025; beta for all Max users Nov 2025; on all paid plans since Dec 2025. Distinct from the Computer Use API.","cited_cells":58,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/claude-for-chrome--anthropic-com"},{"id":"clay--clay-com","name":"Clay","url":"https://www.clay.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"GTM data orchestration + AI agents","license":"","latest_release":"","deployment":"","pricing":"Free (500 actions/mo); Launch from $167/mo; Growth from $446/mo (monthly billing; annual saves 10%)","mcp_support":"yes — Clay MCP brings Clay search, enrichment and Functions into Claude, ChatGPT and Codex","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2017; GTM data orchestration — combine 100+ data sources, enrich, AI-draft outbound. $46M Series B Jan-2024 (Sequoia + Boldstart + Box Group); reported $40M+ ARR mid-2024; viral with growth marketers. Considered a cultural touchstone of the 2024 AI-GTM wave.","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/clay--clay-com"},{"id":"cleric--cleric-io","name":"Cleric","url":"https://cleric.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Autonomous AI SRE agent for cloud-native incidents","license":"","latest_release":"","deployment":"","pricing":"Team $700/month (1,400 credits); Pro $1,500/month (3,000 credits); ~$1 to verify a change, $5 to triage an alert; free trial with 1,000 credits","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2023; autonomous AI SRE that investigates Kubernetes + cloud-native alerts end-to-end. $10M seed Apr-2024 (Greylock + Innovation Endeavors). Direct competitor to Resolve.ai in the AI-SRE wave.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cleric--cleric-io"},{"id":"cline-framework--cline-bot","name":"Cline (framework)","url":"https://cline.bot/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Autonomous VS Code coding agent","license":"Apache-2.0","latest_release":"searched not found","deployment":"Self-hosted only — local IDE extension / CLI / SDK with bring-your-own model keys","pricing":"searched not found","mcp_support":"yes — official MCP client (connects MCP servers; managed via `cline mcp`)","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"cline/cline — ~67.6k stars, last commit not retrieved (not archived)","description":"Open-source autonomous coding agent shipped as a VS Code/JetBrains extension, CLI (headless for CI) and Node SDK (@cline/sdk) — file edits, terminal, browser, MCP tools.","cited_cells":36,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cline-framework--cline-bot"},{"id":"cline-harness--cline-bot","name":"Cline (harness)","url":"https://cline.bot","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"VS Code agentic coding extension (OSS, formerly Claude Dev)","license":"Apache-2.0","latest_release":"v4.1.17 (2026-09-02)","deployment":"Self-hosted only — local VS Code extension, JetBrains plugin and CLI; BYO model keys","pricing":"Free (OSS) + paid Pro","mcp_support":"yes — MCP client in extension and CLI (cline mcp to manage servers)","a2a_support":"searched not found","backend_storage":"local workspace + .clinerules","llm_lock":"","github":"cline/cline — ~67.6k stars, last commit 2026-09","description":"OSS VS Code extension that runs as a fully agentic coding assistant — plan/act modes, file ops, shell exec, browser-use, MCP. Originally \"Claude Dev\" (2024); rebranded Cline 2024-Q4. Multi-model: Anthropic, OpenAI, OpenRouter, Bedrock, Vertex. Memory layer = .clinerules and Memory Bank pattern (distinct rows in catalog).","cited_cells":48,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cline-harness--cline-bot"},{"id":"cloudflare-mcp-server-portals--developers-cloudflare-com","name":"Cloudflare MCP server portals","url":"https://developers.cloudflare.com/cloudflare-one/access-controls/ai-controls/mcp-portals/","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Cloudflare One feature that puts multiple MCP servers behind a single HTTP endpoint secured by Cloudflare Access, with customized tools and per-user policies for MCP clients.","cited_cells":9,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cloudflare-mcp-server-portals--developers-cloudflare-com"},{"id":"cloudflare-workflows--developers-cloudflare-com","name":"Cloudflare Workflows","url":"https://developers.cloudflare.com/workflows/","section":"Durable execution & workflow engines","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Durable execution engine on Cloudflare Workers that runs multi-step workflows with automatic retries, sleeping and waiting for events. The docs include a guide to building a durable AI agent.","cited_cells":11,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cloudflare-workflows--developers-cloudflare-com"},{"id":"coalfire-ai-operations--coalfire-com","name":"Coalfire AI Operations","url":"https://coalfire.com/services/advisory/ai-security-and-trust-engineering","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Cyber-services firm with AI-assisted compliance/pentest","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Coalfire is the largest specialist-cybersecurity-services firm in the FedRAMP/PCI/HITRUST space. Apax Partners acquired majority stake 2020. Launched AI-augmented assessment services 2024 — pentest + audit workpaper automation. On 2026-05-05 Coalfire launched Audit AI in its Compliance Essentials platform, letting customers' AI agents work on live compliance data via MCP and open APIs; AI agent services for security operations (LegionAI) now sit under Coalfire AI Security and Trust Engineering.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/coalfire-ai-operations--coalfire-com"},{"id":"coder-com--coder-com","name":"Coder.com","url":"https://coder.com/","section":"AI sandbox & runtime environments","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Self-hosted enterprise CDE + AI-agent workspace platform","license":"AGPL-3.0 (Community); proprietary Premium / AI Premium licence for some features","latest_release":"v2.38.0 (2026-10-06)","deployment":"Self-hosted only — on your own infrastructure (K8s / VMs / Docker), air-gap capable","pricing":"Community free (OSS); Premium billed per user/year (quote); AI Premium custom","mcp_support":"yes — Coder Agents use MCP servers (private-network MCP allowlisting in v2.38.0)","a2a_support":"","backend_storage":"","llm_lock":"","github":"coder/coder — ~14.1k stars, last commit 2026-10","description":"Coder.com (formerly Coder Technologies) provides enterprise self-hosted cloud development environments — VS Code Server + dev workspaces on K8s / VMs. $30M Series B 2021 (Redpoint + Founders Fund + Coatue). Founded 2017 by Kyle Carberry + Ammar Bandukwala. 2024 launched 'Coder AI' for agent-execution inside workspaces. Self-hostable AGPL OSS + commercial enterprise.","cited_cells":34,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/coder-com--coder-com"},{"id":"codesandbox-ai--codesandbox-io","name":"CodeSandbox AI","url":"https://codesandbox.io/ai","section":"AI sandbox & runtime environments","tier":2,"status":"acquired","last_verified_at":"2026-10-26","type":"Browser-based dev sandbox with AI-agent features (acquired by Together AI 2024)","license":"","latest_release":"","deployment":"Managed-only — SaaS; SDK also offered as Together Code Sandbox","pricing":"Free + Pro ($12/mo) + Team + Enterprise; commercial CodeSandbox SDK for agent integration","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"CodeSandbox is the long-running browser-based dev sandbox (founded 2017 by Ives van Hoorne + Bas Buursma in Amsterdam). **Acquired by Together AI Oct-2024** to anchor Together's agent-execution stack alongside its GPU inference cloud. AI features include AI-assisted coding, agent-execution sandboxes, and instant-preview for AI-generated apps.","cited_cells":24,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/codesandbox-ai--codesandbox-io"},{"id":"cognition-devin-v2-spec-mode--cognition-ai","name":"Cognition Devin v2 / Spec Mode","url":"https://cognition.com/","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-29","type":"Devin successor — autonomous coding agent + spec-mode (cross-listing)","license":"","latest_release":"Devin release notes update (2026-10-26)","deployment":"Managed-only — Cognition cloud agents plus Devin Desktop and CLI; enterprise plan offers a dedicated deployment option","pricing":"Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo plus $40/mo per full seat; Enterprise custom","mcp_support":"yes — MCP marketplace plus custom MCP servers (STDIO and remote) configurable in Devin; Devin also ships its own Devin MCP server","a2a_support":"searched not found","backend_storage":"cloud session state + Knowledge","llm_lock":"","github":"","description":"Cross-listing of Cognition's Devin product framed at the harness level rather than the memory layer. Devin 2.0 (Mar 2025) added cheaper concurrent sessions; Spec Mode (Aug 2025, post-Windsurf-IP acquisition) integrates Windsurf-style spec authoring. The Coding-agent-memory row remains canonical for the memory framing.","cited_cells":63,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cognition-devin-v2-spec-mode--cognition-ai"},{"id":"common-room--commonroom-io","name":"Common Room","url":"https://www.commonroom.io/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Community intelligence + AI signal-based sales agent","license":"","latest_release":"","deployment":"","pricing":"Essential $2,500/mo billed annually (5 seats); Advanced and Enterprise custom","mcp_support":"yes — Common Room MCP Server for MCP-compatible assistants plus a CLI for headless access","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2020; community intelligence platform that ingests GitHub, Slack, Discord, X, LinkedIn signals + maps them to people/companies; AI agent surfaces sales-ready signals. $32M Series B Mar-2024 (Greylock + Index + Madrona).","cited_cells":21,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/common-room--commonroom-io"},{"id":"composer--composer-trade","name":"Composer (now Composer by SoFi)","url":"https://www.composer.trade/","section":"Use-case-specific agent harnesses","tier":3,"status":"renamed","last_verified_at":"2026-10-28","type":"AI-driven retail algorithmic-trading platform","license":"","latest_release":"","deployment":"","pricing":"Starter $0; Advanced $10/mo; Pro $32/mo billed yearly ($384/yr); Business custom; zero commissions","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2020 (YC W21); AI-driven retail algorithmic-trading — composable strategies + LLM strategy builder. $14M Series A May-2022 (Greycroft + Y Combinator). Composer GPT + strategy-builder AI launched 2023.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/composer--composer-trade"},{"id":"composio--composio-dev","name":"Composio","url":"https://composio.dev/","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Tool/auth platform for agents","license":"MIT (SDKs)","latest_release":"v0.30.0 (2026-10-22) — composio Python SDK (2.0.0b0 pre-release 2026-08-31)","deployment":"Managed-only — hosted API + MCP endpoints (Helm charts published for Kubernetes deploys)","pricing":"searched not found","mcp_support":"yes — official hosted MCP endpoint per session (session.mcp.url) + Rube MCP server","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"ComposioHQ/composio — ~30k stars, last commit 2026-10","description":"Authentication and tool-execution platform for AI agents — 100+ apps with OAuth handled, function-call schemas, observability.","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/composio--composio-dev"},{"id":"continue-dev-harness--continue-dev","name":"Continue.dev","url":"https://continue.dev","section":"Agent IDEs & coding harnesses","tier":2,"status":"deprecated","last_verified_at":"2026-10-29","type":"OSS agentic IDE plugin (VS Code + JetBrains)","license":"Apache-2.0","latest_release":"v2.0.0-vscode (2026-06-19) — final release","deployment":"Self-hosted only — VS Code/JetBrains extensions and CLI (discontinued after Cursor acquisition; OSS code remains forkable)","pricing":"Discontinued — recurring billing turned off after Cursor acquisition; OSS code free (Apache-2.0)","mcp_support":"native — Continue MCP client","a2a_support":"searched not found","backend_storage":"local + Continue Hub (optional)","llm_lock":"","github":"continuedev/continue — ~35.7k stars, last commit 2026-06 (read-only, no longer maintained)","description":"OSS in-IDE coding-assistant plugin — supports VS Code and JetBrains. Customisable: any model, any context provider, any slash-command. \"Agent mode\" added 2024 for multi-step plan + execute. Memory layer = .continue/rules; separate Memory MCP. Built by Nate Sesti and Ty Dunn. Acquired by Cursor (2026, per continue.dev; no date given); the continuedev/continue repo is read-only and no longer maintained after a final 2.0.0 release.","cited_cells":64,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/continue-dev-harness--continue-dev"},{"id":"crewai--crewai-com","name":"CrewAI","url":"https://www.crewai.com/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Multi-agent orchestration","license":"MIT","latest_release":"v1.15.30 (2026-10-24)","deployment":"Both (self-hosted + managed cloud) — OSS library; CrewAI AMP on CrewAI cloud, your VPC or own infra","pricing":"free (OSS); AMP Basic free (50 workflow executions/mo); Enterprise custom","mcp_support":"yes — official MCP support in CrewAI agents","a2a_support":"yes — native A2A support in CrewAI agents","backend_storage":"","llm_lock":"searched not found","github":"crewAIInc/crewAI — ~58.6k stars, last commit 2026-10","description":"Multi-agent framework — Crews (sequential) + Flows (event-driven). Open-source core + CrewAI Enterprise. Memory available via Mem0 / Letta adapters (CrewAI Memory cross-listed).","cited_cells":44,"third_party_cells":9,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/crewai--crewai-com"},{"id":"crewai-enterprise--crewai-com","name":"CrewAI Enterprise (now CrewAI AMP)","url":"https://crewai.com/agent-management-platform","section":"Multi-agent orchestration platforms","tier":2,"status":"renamed","last_verified_at":"2026-10-29","type":"Commercial multi-agent orchestration platform (vs OSS CrewAI)","license":"proprietary (CrewAI AMP); MIT OSS core","latest_release":"","deployment":"Both (self-hosted + managed cloud) — CrewAI cloud, dedicated VPC or your own infrastructure (Enterprise)","pricing":"Basic free (50 workflow executions/mo, 2 automations); Enterprise custom — no public self-serve paid tier","mcp_support":"yes — official MCP support in CrewAI agents","a2a_support":"planned (Google A2A roadmap)","backend_storage":"","llm_lock":"multi-vendor (BYO OpenAI / Anthropic / Gemini / Bedrock / Ollama)","github":"crewAIInc/crewAI (OSS core) — ~58.6k stars","description":"Commercial Enterprise tier of the CrewAI OSS multi-agent framework. Adds managed cloud runtime, RBAC, audit logging, SLA support, on-prem option. OSS CrewAI is in the Framework-embedded memory section already; this row covers the commercial cloud platform separately. $18M Series A Oct-2024 (Insight Partners). 30k+ companies have deployed CrewAI agents in prod (vendor-stated).","cited_cells":31,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/crewai-enterprise--crewai-com"},{"id":"crogl--crogl-com","name":"Crogl","url":"https://crogl.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Autonomous SOC investigation copilot","license":"","latest_release":"","deployment":"","pricing":"Free single-user workstation install ($0, 30-day full-feature trial); Enterprise custom","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"$25M Series A Jan-2025 (Menlo Ventures + Tola Capital + Pelion); founded by Monzy Merza (ex-Splunk CSO). 'Knowledge engine' that does autonomous investigation across SIEM data. Pitched as the AI analyst pair for security teams.","cited_cells":16,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/crogl--crogl-com"},{"id":"cursor-ide--cursor-com","name":"Cursor (IDE)","url":"https://cursor.com","section":"Agent IDEs & coding harnesses","tier":1,"status":"acquired","last_verified_at":"2026-10-27","type":"Agentic IDE; Agent Mode + Background Agents (VS Code fork)","license":"","latest_release":"Agent SDK (2026-10-20)","deployment":"Managed-only — desktop app backed by vendor cloud; Agent SDK agents can also run as a Node process on own infrastructure","pricing":"Free $0; Plus $8/mo (Grok models only); Premium $30/mo; Super $100/mo; Ultra $200/mo; Teams from $30/user/mo; Enterprise custom; third-party models billed separately by usage","mcp_support":"yes — install and manage MCP servers in Cursor (editor and CLI)","a2a_support":"searched not found","backend_storage":"local workspace + cloud session state for Background Agents","llm_lock":"","github":"","description":"AI-first IDE that forked VS Code; Composer (multi-file edit) and Agent Mode (long-running coding agent) are its flagship surfaces. Memory layer = .cursorrules / Rules; recall via repo-aware Context Engine. Anysphere (parent) raised $900M Series C at $9.9B in May 2025; acquired by SpaceX (announced 2026-08-14, terms undisclosed), product continues under the Cursor brand.","cited_cells":45,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/cursor-ide--cursor-com"},{"id":"dapr-agents--docs-dapr-io","name":"Dapr Agents","url":"https://docs.dapr.io/developing-ai/dapr-agents/","section":"Durable execution & workflow engines","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Framework","license":"Apache-2.0","latest_release":"last commit 2026-10-27","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/dapr/dapr-agents (768★)","description":"Python framework, GA at v1.0, for building LLM agents that run durable tasks and collaborate through Dapr Workflows, using Dapr's state management, messaging and observability.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dapr-agents--docs-dapr-io"},{"id":"datadog-bits-ai--datadoghq-com","name":"Datadog Bits AI","url":"https://www.datadoghq.com/product/ai/bits-ai-agents/","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"Observability AI agent / SRE copilot","license":"","latest_release":"","deployment":"Managed-only — part of Datadog SaaS","pricing":"","mcp_support":"yes — Datadog remote MCP Server (under active development) gives AI clients access to Datadog data","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Datadog's AI-assistant for observability — incident summarisation, root-cause hypotheses, runbook automation. Bits AI launched Aug-2023, GA 2024 across the Datadog suite. Datadog parent: $2.7B+ revenue 2024; NASDAQ:DDOG.","cited_cells":43,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/datadog-bits-ai--datadoghq-com"},{"id":"daytona--daytona-io","name":"Daytona","url":"https://www.daytona.io/","section":"AI sandbox & runtime environments","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Self-hostable development environment manager (cloud dev envs, AI sandbox tier)","license":"Apache-2.0 (SDKs in daytona/clients; CLI under AGPL-3.0); core platform closed-source since June 2026 (archived daytonaio/daytona repo remains AGPL-3.0 at v0.190.0)","latest_release":"v0.226.1 (2026-10-23)","deployment":"Managed-only — Daytona cloud (pay-as-you-go); enterprise tier offers BYOC; archived OSS repo (v0.190.0) still forkable but unmaintained","pricing":"Pay-as-you-go per-second billing (vCPU $0.0504/h, memory $0.0162/GiB-h, storage $0.000108/GiB-h, first 5 GiB free); $200 free compute; startup credits up to $50k; preemptible GPUs from $0.57/h; Enterprise custom (SSO, audit logs, BYOC)","mcp_support":"yes — Daytona MCP server (shipped with the CLI/MCP tools in daytona/clients) for agent sandbox control","a2a_support":"","backend_storage":"","llm_lock":"","github":"daytona/clients — ~15 stars (SDKs, API clients, CLI); the former daytonaio/daytona monorepo (~71k stars, last commit 2026-07) stopped development when core moved to a private codebase in 2026-06","description":"Daytona is secure, elastic sandbox infrastructure for running AI-generated code and agent workflows (isolated sandboxes with snapshots, volumes, computer use, MCP server). Pivoted from an open-source cloud development environment; as of June 2026 core development moved to a private codebase and the daytonaio/daytona repo was archived (2026-10-03). SDKs, API clients and CLI/MCP tools are published in the open daytona/clients repo. Founded by the ex-Codeanywhere team (Ivan Burazin).","cited_cells":32,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/daytona--daytona-io"},{"id":"dbos--dbos-dev","name":"DBOS","url":"https://www.dbos.dev/","section":"Durable execution & workflow engines","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Framework","license":"MIT","latest_release":"last commit 2026-10-27","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/dbos-inc/dbos-transact-py (1654★)","description":"Postgres-backed durable workflow library that makes AI agents and applications resilient to failures, with durable queues, cron and human-in-the-loop. It integrates with Pydantic AI, LlamaIndex, the OpenAI Agents SDK and the Vercel AI SDK.","cited_cells":15,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dbos--dbos-dev"},{"id":"demandbase--demandbase-com","name":"Demandbase","url":"https://www.demandbase.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"ABM platform with AI agents","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2006; ABM platform with intent + AI. $175M growth round Apr-2021 ($1B val; Vista Equity). Demandbase One Smarter GTM AI launched 2024 — buyer-stage scoring + auto-personalised outbound.","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/demandbase--demandbase-com"},{"id":"descope-agentic-identity-hub--descope-com","name":"Descope Agentic Identity Hub","url":"https://www.descope.com/use-cases/ai","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Identity provider for AI agents and MCP servers that adds auth, consent, SSO, access control and policy to AI systems. It also manages purpose-built agent credentials for downstream connections and keeps a directory of an organization's agents.","cited_cells":10,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/descope-agentic-identity-hub--descope-com"},{"id":"dify--gh-langgenius-dify","name":"Dify","url":"https://github.com/langgenius/dify","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Product","license":"Dify Open Source License (Apache-2.0 based, with additional conditions)","latest_release":"last commit 2026-10-26","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/langgenius/dify (159560★)","description":"Open-source platform to build agentic workflows and RAG pipelines in a visual, collaborative workspace; self-hosted or Dify Cloud.","cited_cells":19,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dify--gh-langgenius-dify"},{"id":"docker-mcp-catalog-toolkit-gateway--docs-docker-com","name":"Docker MCP Catalog, Toolkit & Gateway","url":"https://docs.docker.com/ai/mcp-catalog-and-toolkit/","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary; mcp-gateway MIT","latest_release":"last commit 2026-10-26","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/docker/mcp-gateway (1616★)","description":"Docker's catalog of containerized MCP servers with a Desktop toolkit and an open-source MCP Gateway (docker mcp CLI plugin). An enterprise gateway authenticates users, scopes servers and tools, applies per-call policy and supplies credentials.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/docker-mcp-catalog-toolkit-gateway--docs-docker-com"},{"id":"docusign-iam--docusign-com","name":"DocuSign IAM","url":"https://www.docusign.com/products/platform","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Intelligent Agreement Management — DocuSign's CLM-AI agent","license":"","latest_release":"","deployment":"Managed-only — Docusign cloud","pricing":"","mcp_support":"yes — Docusign MCP Connectors bring agreement drafting, clause extraction and signing into AI assistants","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"DocuSign's IAM platform (launched 2024) adds AI extraction, clause analysis, and workflow automation atop the eSignature core. Acquired Lexion Jun-2024 ($165M) to consolidate the AI-CLM stack. DocuSign parent: $2.8B+ revenue.","cited_cells":22,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/docusign-iam--docusign-com"},{"id":"draftwise--draftwise-com","name":"DraftWise","url":"https://www.draftwise.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"AI contract drafting + benchmark agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2021 by James Ding (ex-Allen & Overy); drafting + benchmarking AI agent that lets transactional lawyers see historical deals. $20M Series A Apr-2024 (Index Ventures + Y Combinator); ex-A&O / Linklaters customers.","cited_cells":18,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/draftwise--draftwise-com"},{"id":"drata--drata-com","name":"Drata","url":"https://drata.com/","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"Compliance automation platform with AI Trust Hub agent","license":"","latest_release":"","deployment":"SaaS","pricing":"Quote-based; Compliance tiers Foundation, Advanced and Enterprise (no list prices published)","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2020; compliance automation (SOC 2, HIPAA, GDPR, ISO 27001) with hundreds of pre-built control libraries. $200M Series C Mar-2024 ($2B val; ICONIQ + GGV + Cowboy). Trust Hub launched 2024; AI Trust Hub auto-fills security questionnaires.","cited_cells":21,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/drata--drata-com"},{"id":"dropzone-ai--dropzone-ai","name":"Dropzone AI","url":"https://www.dropzone.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Autonomous SOC analyst agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Autonomous SOC analyst agent — investigates Tier-1 SIEM/EDR alerts end-to-end. $16.85M Series A Aug-2024 (Theory Ventures + Decibel). Founded by Edward Wu (ex-ExtraHop). Targets the 60%-of-alerts-go-uninvestigated problem.","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dropzone-ai--dropzone-ai"},{"id":"dspy--gh-stanfordnlp-dspy","name":"DSPy","url":"https://github.com/stanfordnlp/dspy","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Framework","license":"MIT","latest_release":"last commit 2026-10-25","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/stanfordnlp/dspy (38791★)","description":"Stanford's framework for programming, not prompting, language models: declarative modules and optimizers for prompts and weights.","cited_cells":15,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dspy--gh-stanfordnlp-dspy"},{"id":"dx-engineering-intelligence--getdx-com","name":"DX Engineering Intelligence","url":"https://getdx.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Engineering intelligence + AI insights platform","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2020 by Abi Noda; engineering-productivity intelligence (DORA + SPACE metrics) with AI-driven analysis. $14M Series A Apr-2024 (Notable Capital). Differentiates with research-rigour metrics; 'Stripe metrics for engineering teams.'","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dx-engineering-intelligence--getdx-com"},{"id":"dynatrace-davis-copilot--dynatrace-com","name":"Dynatrace Davis CoPilot (now Dynatrace Assist)","url":"https://www.dynatrace.com/news/blog/dynatrace-assist-ask-analyze-and-act-with-dynatrace-intelligence/","section":"Use-case-specific agent harnesses","tier":1,"status":"renamed","last_verified_at":"2026-10-28","type":"GenAI assistant for the Davis AI observability engine","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — Dynatrace MCP Server; Assist uses the same tools hosted on it","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Dynatrace launched Davis CoPilot Sep-2023 — GenAI conversational interface on top of the (deterministic) Davis AI engine, the largest causal-AI observability deployment. Dynatrace parent: NYSE:DT, $1.4B+ revenue.","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/dynatrace-davis-copilot--dynatrace-com"},{"id":"e2b--e2b-dev","name":"e2b","url":"https://e2b.dev/","section":"AI sandbox & runtime environments","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Code-execution sandbox infrastructure for AI agents (firecracker microVMs)","license":"Apache-2.0","latest_release":"v2.61.0 (2026-10-26)","deployment":"Both (self-hosted + managed cloud) — E2B Cloud; open-source Apache-2.0 runtime (e2b-dev/infra) can be self-hosted; enterprise BYOC","pricing":"Hobby $0 (one-time $100 credit, 20 concurrent sandboxes); Pro $150/mo + usage (100 concurrent; Pro+ $650, Pro++ $1,150); Enterprise custom ($3,000/mo minimum, BYOC); per-second usage vCPU $0.000014/s, RAM $0.0000045/GiB-s","mcp_support":"native (MCP server for sandbox tools)","a2a_support":"","backend_storage":"","llm_lock":"","github":"e2b-dev/E2B — ~15k stars, last commit 2026-10","description":"e2b provides secure, ephemeral sandboxes (Firecracker microVMs) for AI agent code execution. Each sandbox spins up in <200ms with full Linux environment, Python/Node/etc preinstalled. Substrate for code-agent products including Anthropic Claude Code (artifacts run on e2b), Perplexity, You.com Search, Cognition Devin (partially), and Hugging Face Spaces. Apache 2.0 OSS + managed cloud. $13M Seed + Series A 2024 (Sunflower Capital + a16z).","cited_cells":33,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/e2b--e2b-dev"},{"id":"elevenlabs-conversational-ai--elevenlabs-io","name":"ElevenLabs Conversational AI (now ElevenAgents)","url":"https://elevenlabs.io/conversational-ai","section":"Voice agent platforms","tier":1,"status":"renamed","last_verified_at":"2026-10-29","type":"Voice-agent platform from a TTS-first vendor (ElevenLabs)","license":"","latest_release":"","deployment":"Cloud-managed","pricing":"Per-minute usage (Conv AI tier); free + Pro + Enterprise","mcp_support":"yes — hosted ElevenLabs MCP server (recommended); local elevenlabs-mcp server deprecated/archived 2026-08-20","a2a_support":"searched not found","backend_storage":"Conversation state in ElevenLabs cloud","llm_lock":"","github":"github.com/elevenlabs (SDKs only)","description":"ElevenLabs launched Conversational AI Nov-2024 — STT + LLM + their own market-leading TTS in one pipeline. Combines vendor's voice cloning + multilingual TTS strengths with hosted call orchestration. ElevenLabs raised $180M Series C Jan-2025 at $3.3B val. As of 2026-10 ElevenLabs markets the platform as ElevenAgents.","cited_cells":62,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/elevenlabs-conversational-ai--elevenlabs-io"},{"id":"eliza-ai16z--gh-elizaos-eliza","name":"Eliza (ai16z)","url":"https://github.com/elizaOS/eliza","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"Web3-flavoured agent framework","license":"MIT","latest_release":"v1.7.2 (2026-01-19)","deployment":"Both (self-hosted + managed cloud) — open-source runtime runs locally; hosted Eliza Cloud (cloud.eliza.app)","pricing":"searched not found","mcp_support":"yes — MCP client via the @elizaos/plugin-mcp plugin","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"elizaOS/eliza — ~20k stars, last commit 2026-10","description":"ai16z's TypeScript agent framework popularised in the crypto/Web3 agent space — multi-platform (Discord, X, Telegram). Brand evolved into elizaOS.","cited_cells":21,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/eliza-ai16z--gh-elizaos-eliza"},{"id":"endor-labs--endorlabs-com","name":"Endor Labs","url":"https://www.endorlabs.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"AI-powered SCA + reachability analysis","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — local stdio MCP server launched via npx or endorctl (Cursor, Claude Code, Codex, VS Code, etc.)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2021 by Dimitri Stiliadis + Varun Badhwar (ex-Palo Alto Networks Prisma Cloud); reachability-aware SCA with AI for triage. $70M Series A Oct-2023 ($200M val; Lightspeed + Coatue + Dell Tech Capital); $93M total raised.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/endor-labs--endorlabs-com"},{"id":"garak--gh-nvidia-garak","name":"Garak","url":"https://github.com/NVIDIA/garak","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"OSS LLM vulnerability scanner (NVIDIA-stewarded)","license":"Apache-2.0","latest_release":"v0.17.1 (2026-10-16)","deployment":"Self-hosted only — pip-installed Python CLI","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"NVIDIA/garak — ~9.7k stars, last commit 2026-10","description":"OSS (Apache 2.0) LLM vulnerability scanner — 'nmap for LLMs.' Originally Leon Derczynski (Univ Sheffield / ITU Copenhagen); NVIDIA now stewards the project. Tests for jailbreaks, prompt injection, hallucination, data leakage. Apache-2.0.","cited_cells":24,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/garak--gh-nvidia-garak"},{"id":"genie-ai--genieai-co","name":"Genie AI","url":"https://www.genieai.co/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Self-service AI legal agent (template + redline)","license":"","latest_release":"","deployment":"","pricing":"Free $0; Pro $59/mo billed annually or $75/mo monthly (1 user); Business $259/mo annually or $320/mo (5 users); Enterprise quote","mcp_support":"yes — MCP connectors to email, CRM, storage and eSign tools; API and MCP integrations on Enterprise","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"London-based legal AI for businesses — contract drafting, review and AI legal agents (first agents Jan-2024). $17.8M Series A Jun-2023 led by GV and Khosla Ventures; rebranded as 'The Global Legal Brain' Jan-2026. Distinct from Hugo (research) and not to be confused with Google's Genie.","cited_cells":21,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/genie-ai--genieai-co"},{"id":"genkit--gh-firebase-genkit","name":"Genkit","url":"https://github.com/firebase/genkit","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Framework","license":"Apache-2.0","latest_release":"last commit 2026-10-23","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/firebase/genkit (6549★)","description":"Google Firebase's open-source framework for building AI-powered applications, with libraries for Node.js and Go (Go in alpha).","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/genkit--gh-firebase-genkit"},{"id":"ghost-beacon--gh-moecanales-agent-oracle-beacon","name":"Ghost Beacon","url":"https://github.com/moecanales/agent-oracle-beacon","section":"MCP gateways & registries","tier":4,"status":"active","last_verified_at":"2026-10-31","type":"MCP tool server (GitHub-Issue rollover, board-game rules, transcript scan, A2A checks)","license":"MIT","latest_release":"v5.0 per README (2026-10-28); no GitHub releases published","deployment":"Self-hosted — runs locally over stdio via npx; static JSON shards served from GitHub Pages","pricing":"Free — MIT, no hosted plan","mcp_support":"yes — ships an MCP server (mcp-server.js) with 9 tools; install with npx -y github:moecanales/agent-oracle-beacon","a2a_support":"A2A discovery and DNS/TLS check tooling only; no verified A2A agent card of its own","backend_storage":"searched not found","llm_lock":"searched not found","github":"moecanales/agent-oracle-beacon — 0 stars, 1 fork, first commit 2026-10-22, last commit 2026-10-31","description":"Zero-dependency Node.js MCP server (npx -y github:moecanales/agent-oracle-beacon) exposing nine tools: GitHub-Issue context rollover and comment-mutex extraction (GBR-2500), board-game rules lookup over bundled CC0 datasets, an agent transcript scanner, and A2A discovery with DNS/TLS checks. Submitted by its author (issue #194); GBR-2500 (issue #299) is one of its tools in the same repository, not a separate system.","cited_cells":28,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/ghost-beacon--gh-moecanales-agent-oracle-beacon"},{"id":"github-copilot-agent-mode--gh-features-copilot","name":"GitHub Copilot (Agent Mode)","url":"https://github.com/features/copilot","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"IDE Copilot extension — chat, completions, Agent Mode","license":"","latest_release":"","deployment":"Managed-only — GitHub-hosted service via IDE extensions, Copilot CLI and github.com cloud agent","pricing":"Free $0 (2,000 completions/mo); Pro $10/mo; Pro+ $39/mo; Max $100/mo; Business $19/user/mo; Enterprise $39/user/mo","mcp_support":"yes — client: custom MCP servers in agent mode/cloud agent; admins can allow-list MCP servers","a2a_support":"searched not found","backend_storage":"session in IDE + GitHub-hosted","llm_lock":"","github":"","description":"The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.","cited_cells":38,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/github-copilot-agent-mode--gh-features-copilot"},{"id":"github-copilot-autofix--github-blog","name":"GitHub Copilot Autofix","url":"https://github.blog/2024-03-20-found-means-fixed-introducing-code-scanning-autofix-powered-by-github-copilot-and-codeql/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Automated code-vuln-fix agent (CodeQL + Copilot)","license":"","latest_release":"","deployment":"GitHub SaaS","pricing":"Included in GitHub Code Security at $30 per active committer/month (Team and Enterprise); free on public repositories","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"GitHub's CodeQL-powered auto-fix for code-scanning alerts; combines static analysis with Copilot model suggestions to generate patches for vulnerabilities. Launched Mar-2024 (public beta), GA Aug-2024 for GitHub Advanced Security customers.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/github-copilot-autofix--github-blog"},{"id":"github-copilot-workspace--githubnext-com","name":"GitHub Copilot Workspace","url":"https://githubnext.com/projects/copilot-workspace","section":"Agent IDEs & coding harnesses","tier":1,"status":"archived","last_verified_at":"2026-10-26","type":"Agentic IDE — GitHub-hosted plan/code/test workspace","license":"","latest_release":"","deployment":"Managed-only — GitHub-hosted (technical preview ended; discontinued)","pricing":"Discontinued — successor features (Copilot cloud agent) in Copilot Pro $10/mo, Business $19/user/mo, Enterprise $39/user/mo","mcp_support":"MCP support added 2025 (Copilot Agent Mode)","a2a_support":"searched not found","backend_storage":"GitHub-hosted session state per workspace","llm_lock":"","github":"githubnext/copilot-workspace-user-manual — archived 2025-09-02 (product closed source)","description":"GitHub's hosted agentic workspace — given an issue, generates a spec, plan, and PR. Preview launched April 2024; rebranded \"GitHub Copilot Coding Agent\" + \"Copilot Agent Mode\" in 2025 with broader GA. Backed by Microsoft Azure OpenAI + Anthropic Claude (added 2024). Companion to in-editor Copilot.","cited_cells":59,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/github-copilot-workspace--githubnext-com"},{"id":"gitpod-ai-features--gitpod-io","name":"Gitpod AI features (now Ona)","url":"https://ona.com/","section":"AI sandbox & runtime environments","tier":2,"status":"dead","last_verified_at":"2026-10-29","type":"Cloud development environment with AI-agent integrations (Gitpod Flex)","license":"AGPL-3.0 (Gitpod Self-Hosted)","latest_release":"","deployment":"Managed cloud + self-hostable (AGPL OSS) + on-prem (enterprise)","pricing":"Free OSS tier + Personal Pro ($9/mo) + Team + Enterprise","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"gitpod-io/gitpod — ~14k stars, last commit 2026-10","description":"Gitpod was the original cloud development environment (CDE) — founded by Sven Efftinge + Johannes Landgraf (TypeFox / Eclipse Theia / Open VSX); $25M Series A 2022 led by General Catalyst. Renamed Ona on 2025-09-02 and repositioned as background AI software-engineering agents in cloud environments (Ona cloud or customer VPC). Acquired by OpenAI (2026-08-10; announced 2026-06-11; team joined the Codex team); Ona Cloud is being wound down on 2026-10-31.","cited_cells":27,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/gitpod-ai-features--gitpod-io"},{"id":"glama-mcp--glama-ai","name":"Glama MCP","url":"https://glama.ai/mcp/servers","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Searchable directory of more than 112,000 MCP servers with license, quality and maintenance grades, plus an MCP directory API and connectors for agents.","cited_cells":7,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/glama-mcp--glama-ai"},{"id":"golem--golem-cloud","name":"Golem","url":"https://golem.cloud/","section":"Durable execution & workflow engines","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"BUSL-1.1","latest_release":"last commit 2026-10-29","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/golemcloud/golem (1523★)","description":"Agent-native durable runtime that runs each agent in its own WebAssembly VM. After crashes, restarts or rescaling the agent resumes mid-function with memory and files intact, and tool calls execute exactly once under enforced permissions.","cited_cells":15,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/golem--golem-cloud"},{"id":"gong--gong-io","name":"Gong","url":"https://www.gong.io/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Revenue intelligence + AI agents","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2015; the largest conversation-intelligence/revenue-intelligence platform. $7.25B val 2021 ($583M raised); Gong AI (Smart Tracker, AI Forecast, Gong Engage) 2024. Considered category-defining.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/gong--gong-io"},{"id":"google-agent-development-kit-adk--gh-google-adk-python","name":"Google Agent Development Kit (ADK)","url":"https://github.com/google/adk-python","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Framework","license":"Apache-2.0","latest_release":"last commit 2026-10-25","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/google/adk-python (22008★)","description":"Google's code-first Python toolkit for building, evaluating and deploying AI agents.","cited_cells":18,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/google-agent-development-kit-adk--gh-google-adk-python"},{"id":"goose-block--block-github-io","name":"Goose (Block)","url":"https://goose-docs.ai/","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"OSS terminal/desktop agent (Block, Inc.)","license":"Apache-2.0","latest_release":"v1.56.0 (2026-10-23)","deployment":"Self-hosted only — local CLI + desktop app; BYO LLM provider","pricing":"Free (OSS); usage via LLM provider","mcp_support":"yes — MCP client; extensions are MCP servers","a2a_support":"searched not found","backend_storage":"local config + extensions","llm_lock":"","github":"aaif-goose/goose (formerly block/goose) — ~55.7k stars, last commit 2026-10","description":"Block (Square)'s open-source on-machine agent — terminal + desktop GUI. Modular: extensions for shell, computer-control, MCP servers; multi-model via LiteLLM. Released 2024; positioned as a general-purpose local agent, not coding-only. Goose Recipes provide reusable agent workflows.","cited_cells":47,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/goose-block--block-github-io"},{"id":"gpt-engineer--gh-antonosika-gpt-engineer","name":"GPT Engineer","url":"https://github.com/AntonOsika/gpt-engineer","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"archived","last_verified_at":"2026-10-29","type":"Spec-to-codebase agent","license":"MIT","latest_release":"v0.3.1 (2024-06-06)","deployment":"Self-hosted only — CLI","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"AntonOsika/gpt-engineer — ~55k stars, last commit 2025-05 (archived 2026-04-22)","description":"One of the original 'agent writes a whole codebase from a prompt' CLI experiments; precursor to the commercial Lovable (lovable.dev / gptengineer.app). Repository archived (read-only) on 2026-04-22.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/gpt-engineer--gh-antonosika-gpt-engineer"},{"id":"hackerone-hai--hackerone-com","name":"HackerOne Hai","url":"https://www.hackerone.com/solutions/ai","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"AI-assisted pentest + AI red-team service","license":"","latest_release":"","deployment":"","pricing":"Pay-per-finding + retainer service tiers","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"HackerOne's AI-augmented offensive security service — Hai is an LLM-assisted triage/research copilot for hackers, plus a productised 'AI red-team' service connecting customers to skilled human red-teamers for LLM systems. Used by major LLM providers (OpenAI, Anthropic) historically as a vulnerability surface.","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hackerone-hai--hackerone-com"},{"id":"hatchet--hatchet-run","name":"Hatchet","url":"https://hatchet.run/","section":"Durable execution & workflow engines","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"MIT","latest_release":"last commit 2026-10-29","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/hatchet-dev/hatchet (8198★)","description":"Orchestration engine for AI agents, background tasks and durable workflows, available self-hosted or as a managed cloud.","cited_cells":16,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hatchet--hatchet-run"},{"id":"haystack-framework--haystack-deepset-ai","name":"Haystack (framework)","url":"https://haystack.deepset.ai/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"deepset's LLM framework","license":"Apache-2.0","latest_release":"v3.4.1 (2026-10-21)","deployment":"Both (self-hosted + managed cloud) — OSS library; deepset Haystack Enterprise Platform (cloud or custom deployment)","pricing":"OSS framework free; Haystack Enterprise Platform: Studio $0 (1 user, 100 pipeline hours, cloud deployment), Enterprise custom","mcp_support":"yes — MCPTool/MCPToolset client tools via the mcp-haystack integration (Streamable HTTP, SSE, stdio); Hayhooks can expose pipelines as MCP servers","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"deepset-ai/haystack — ~27k stars, last commit 2026-10","description":"deepset's open-source framework for LLM/RAG/agent apps — Pipelines abstraction; deepset Cloud commercial. Memory is a downstream connector.","cited_cells":24,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/haystack-framework--haystack-deepset-ai"},{"id":"hebbia--hebbia-com","name":"Hebbia","url":"https://www.hebbia.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Enterprise research agent (Matrix)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — Headless Hebbia MCP server lets assistants such as Claude and ChatGPT call Hebbia retrieval and analysis","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2020 by George Sivulka (ex-Stanford); Matrix is its enterprise research agent — multi-step research across documents. $130M Series B Jul-2024 ($700M val; Andreessen Horowitz + Index + Google Ventures + Peter Thiel). Used heavily at Tier-1 investment banks + hedge funds.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hebbia--hebbia-com"},{"id":"highlight-ai--highlightai-com","name":"Highlight AI","url":"https://highlightai.com/","section":"Computer-use & desktop agents","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Desktop AI co-pilot (always-on context capture across apps)","license":"","latest_release":"v2.0.20 (2026-10-20)","deployment":"Desktop app (Mac + Windows); local + cloud hybrid","pricing":"Free $0/mo (14-day Pro trial); Pro $35/mo; Max $200/mo","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Local SQLite + optional cloud sync","llm_lock":"","github":"","description":"Always-on desktop AI assistant that watches the user's screen (across all apps) and answers questions / takes actions based on what's currently visible. Mac + Windows. Founded by Mac Bishop (ex-Mixpanel); raised $13M Series A from Aspect / Lightspeed (Oct 2024). Distinguishes itself from Rewind by being action-oriented (not just recall). As of 2026-10 the site repositions it as an AI multitasker for work: it captures meeting and work context and drafts follow-ups, daily briefs and end-of-day recaps in connected tools (Gmail, Slack, Linear, GitHub and others).","cited_cells":35,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/highlight-ai--highlightai-com"},{"id":"horizon3-nodezero--horizon3-ai","name":"Horizon3 NodeZero","url":"https://www.horizon3.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Autonomous pentest platform (NodeZero)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — NodeZero MCP Server built into the SaaS platform (exploit paths, credentials, on-demand pentests)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2019 by Snehal Antani (ex-CTO US SOCOM J6) + ex-NSA team. NodeZero is autonomous pentest — finds + exploits + verifies exploitability. $100M Series D Mar-2024 (NEA; $750M val); >300% YoY revenue growth reported. Federal + commercial.","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/horizon3-nodezero--horizon3-ai"},{"id":"hubspot-breeze-ai-agents--hubspot-com","name":"HubSpot Breeze AI Agents","url":"https://www.hubspot.com/products/artificial-intelligence","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"AI agents for HubSpot Smart CRM (Breeze)","license":"","latest_release":"","deployment":"","pricing":"Agent Hub included in Starter, Professional and Enterprise editions; custom agents consume HubSpot Credits (prepaid packs or pay-as-you-go)","mcp_support":"yes — HubSpot remote MCP server for CRM read/write plus a developer-platform MCP server","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"HubSpot Breeze (launched Sep-2024) is the AI brand spanning Breeze Copilot (assistant) + Breeze Agents (autonomous content/prospecting/social/customer agents). HubSpot parent: NYSE:HUBS, $2.6B+ revenue 2024.","cited_cells":44,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hubspot-breeze-ai-agents--hubspot-com"},{"id":"hume-evi--hume-ai","name":"Hume EVI","url":"https://dev.hume.ai/voice/docs/speech-to-speech-evi/overview","section":"Voice agent platforms","tier":1,"status":"dead","last_verified_at":"2026-10-29","type":"Empathic voice-AI platform (voice + emotion)","license":"","latest_release":"EVI 3 and EVI 4-mini; the EVI API shuts down on 2026-11-13","deployment":"Cloud-managed","pricing":"Per-minute usage; tiered + Enterprise","mcp_support":"yes — official MCP server (HumeAI/mcp-server-hume)","a2a_support":"searched not found","backend_storage":"Session state in Hume cloud","llm_lock":"","github":"HumeAI org (SDKs/examples; hume-api-examples ~250 stars, updated 2026-10) — EVI service closed source","description":"Hume's Empathic Voice Interface (EVI) — voice agent platform with vocal-affect understanding, using Hume's proprietary speech-prosody models. Hume will shut down the EVI and TTS APIs on 2026-11-13 (announced in its docs). Hume raised $50M Series B Mar-2024 (EQT).","cited_cells":46,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hume-evi--hume-ai"},{"id":"hyperbrowser--hyperbrowser-ai","name":"Hyperbrowser","url":"https://www.hyperbrowser.ai/","section":"Computer-use & desktop agents","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"Cloud browser-infrastructure for AI agents (Browserbase competitor)","license":"","latest_release":"Rolling cloud releases","deployment":"Cloud only (no self-host)","pricing":"Per-session-minute + free tier","mcp_support":"yes — official Hyperbrowser MCP server (hyperbrowserai/mcp, MIT)","a2a_support":"searched not found","backend_storage":"Session state in Hyperbrowser-managed Chromium fleet","llm_lock":"","github":"github.com/hyperbrowserai (client SDKs only)","description":"Cloud-hosted headless browser API tuned for AI agents — captcha solving, stealth mode, session recordings. Y Combinator S24; pitched as a faster / cheaper Browserbase alternative. Used as substrate by agents that need browser execution but don't want to run their own Chromium fleet.","cited_cells":46,"third_party_cells":7,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hyperbrowser--hyperbrowser-ai"},{"id":"hyperproof--hyperproof-io","name":"Hyperproof","url":"https://hyperproof.io/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Compliance operations platform with AI agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2018; compliance-operations platform — pre-built frameworks + workflow automation. $40M Series B Dec-2022 (Riverwood Capital + Toba + Madrona). AI agent layer added 2024. Targets enterprise-scale compliance teams.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hyperproof--hyperproof-io"},{"id":"hyperproof-ai-trust-center--hyperproof-io","name":"Hyperproof AI Trust Center","url":"https://hyperproof.io/","section":"Use-case-specific agent harnesses","tier":3,"status":"acquired","last_verified_at":"2026-10-29","type":"Auto-fill security questionnaire / trust center agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Standalone trust-center + AI-questionnaire-fill product from Hyperproof. Listed separately because the trust-center category is a distinct sub-market (Vanta, Drata, Hyperproof, SafeBase, ConveyorAI compete). SafeBase acquired by Drata Mar-2025. As of Oct 2026 the standalone Trust Center page (hyperproof.io/trust-center) is gone; trust-center automation and security-questionnaire response are now presented as the Trust capability of the Hyperproof GRC platform.","cited_cells":12,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/hyperproof-ai-trust-center--hyperproof-io"},{"id":"ibm-contextforge-mcp-gateway--ibm-github-io","name":"IBM ContextForge MCP Gateway","url":"https://ibm.github.io/mcp-context-forge/","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Framework","license":"Apache-2.0","latest_release":"last commit 2026-10-29","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/IBM/mcp-context-forge (4720★)","description":"Open-source registry and proxy that federates MCP, A2A and REST/gRPC APIs behind one endpoint with centralized discovery, guardrails, governance and plugins.","cited_cells":15,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/ibm-contextforge-mcp-gateway--ibm-github-io"},{"id":"imbue-formerly-generally-intelligent--imbue-com","name":"Imbue (formerly Generally Intelligent)","url":"https://imbue.com/","section":"Multi-agent orchestration platforms","tier":3,"status":"active","last_verified_at":"2026-10-27","type":"Coding-agent research lab (foundation models for reasoning + code agents)","license":"","latest_release":"","deployment":"","pricing":"Pre-product (research-focused)","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"single-vendor (Imbue-proprietary 70B + research)","github":"imbue-ai/mngr — ~430 stars, last commit 2026-10","description":"Founded 2017 as Generally Intelligent; rebranded Imbue 2023. Founders Kanjun Qiu + Josh Albrecht. $200M Series B 2023 ($1B valuation). Trained a 70B reasoning model, then shifted to user-owned AI tools: imbue.com now lists Studio (personal AI operating system, waitlist), Bouncer, Cloud in a Bottle, Sculptor, Vet (AI code review) and mngr (CLI for managing coding agents), with open-source repos under github.com/imbue-ai.","cited_cells":21,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/imbue-formerly-generally-intelligent--imbue-com"},{"id":"incident-io-ai--incident-io","name":"incident.io AI","url":"https://incident.io/investigations","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Incident-management platform with AI agents","license":"","latest_release":"","deployment":"","pricing":"Basic free; Team $19/user/mo ($15 annual); Pro $25/user/mo; Enterprise custom; on-call add-on $10–20/user/mo","mcp_support":"yes — hosted incident.io MCP server for assistants such as Claude and Cursor (Team, Pro, Enterprise)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"London-founded incident-management platform — Slack-native, fast-growing. $62M Series B Sep-2024 (Insight Partners + Index; $400M val). AI features (auto-summary, auto-postmortem, suggested-runbook) added 2024.","cited_cells":21,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/incident-io-ai--incident-io"},{"id":"inngest--inngest-com","name":"Inngest","url":"https://www.inngest.com/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Event-driven durable workflows","license":"SSPL-1.0 with delayed Apache-2.0 grant (server; each release becomes Apache-2.0 three years after publication); SDKs Apache-2.0","latest_release":"v4.26.0 (2026-10-22)","deployment":"Both (self-hosted + managed cloud) — Inngest Cloud; self-hosting supported since the 1.0 release","pricing":"searched not found","mcp_support":"yes — AgentKit agents consume MCP servers as tools via mcpServers (Streamable HTTP, SSE, WebSocket)","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"inngest/inngest — ~6k stars, last commit 2026-10","description":"Event-driven durable workflow platform — competes with Temporal for the JS/TS/Python crowd. Inngest AgentKit (memory cross-listed) is the agent extension.","cited_cells":22,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/inngest--inngest-com"},{"id":"instructlab-red-hat-ibm--instructlab-ai","name":"InstructLab (Red Hat / IBM)","url":"https://instructlab.ai/","section":"Multi-agent orchestration platforms","tier":2,"status":"archived","last_verified_at":"2026-10-29","type":"OSS LLM alignment + community-driven fine-tuning framework","license":"Apache 2.0","latest_release":"v0.26.1 (2025-05-05)","deployment":"Self-hosted only — CLI/library (archived)","pricing":"OSS (free); IBM watsonx + Red Hat OpenShift AI commercial pricing for the platforms","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"open (Granite-default; works with any compatible model)","github":"instructlab/instructlab — ~1.4k stars, last commit 2026-03 (archived 2026-04-23)","description":"Red Hat / IBM-stewarded open-source framework for community-driven LLM alignment + fine-tuning (LAB method, IBM Research 2024; Granite models). Apache 2.0. Main CLI repo archived 2026-04-23 after a 2025 refactor into separate libraries — synthetic data generation in SDG Hub and training in Training Hub (Red-Hat-AI-Innovation-Team). Not strictly a multi-agent framework.","cited_cells":34,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/instructlab-red-hat-ibm--instructlab-ai"},{"id":"iris-ai--iris-ai-2","name":"Iris.ai","url":"https://iris.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Scientific research engine + AI agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Oslo-founded 2015; scientific research engine + AI agent for R&D. Bootstrapped + small angel rounds; broader European AI scene. Differentiates with explainable / hallucination-free claims.","cited_cells":13,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/iris-ai--iris-ai-2"},{"id":"ironclad-ai-assistant--ironcladapp-com","name":"Ironclad AI Assistant","url":"https://ironcladapp.com/ai/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"CLM platform with AI agents","license":"","latest_release":"","deployment":"SaaS","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Ironclad's AI agents inside its CLM (contract lifecycle management) platform. Ironclad parent: $200M+ ARR; backed by Accel, Sequoia, YC, BOND. AI features include auto-redline, review, and contract intelligence. Note: separate Rivet Memory Node row already in catalog under Framework-embedded memory — this is the CLM-AI framing.","cited_cells":22,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/ironclad-ai-assistant--ironcladapp-com"},{"id":"jetbrains-ai-assistant--jetbrains-com","name":"JetBrains AI Assistant","url":"https://www.jetbrains.com/ai/","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"IDE AI assistant — chat, completions, AI actions (JetBrains)","license":"","latest_release":"","deployment":"IDE plugin (cloud LLM by default; offline/self-host options)","pricing":"$8.33/mo Personal / $16.50/mo Business AI add-on","mcp_support":"yes — MCP server built into all IntelliJ-based IDEs since 2025.2 (standalone mcp-jetbrains deprecated)","a2a_support":"searched not found","backend_storage":"local IDE + JetBrains AI cloud","llm_lock":"","github":"","description":"JetBrains' in-IDE assistant integrated across IntelliJ, PyCharm, GoLand, WebStorm, Rider, etc. Multi-model: OpenAI, Anthropic, Google, local. Differentiated by its deep IDE-API integration — refactorings, run configs, debugger context.","cited_cells":55,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/jetbrains-ai-assistant--jetbrains-com"},{"id":"jetbrains-junie--jetbrains-com","name":"JetBrains Junie","url":"https://www.jetbrains.com/junie/","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"Autonomous coding agent in JetBrains IDEs","license":"","latest_release":"Junie CLI 26.10.20 (2026-10-21)","deployment":"IDE plugin (cloud LLM)","pricing":"Junie Lite free; AI Pro $8.33/user/mo (10 AI credits per 30 days); AI Ultimate $25/user/mo (35 AI credits per 30 days); top-ups available","mcp_support":"yes — Junie CLI and Junie in JetBrains IDEs share an MCP JSON configuration; /mcp command manages servers","a2a_support":"searched not found","backend_storage":"session state in IDE","llm_lock":"","github":"","description":"JetBrains' answer to Cursor Agent Mode / Devin — an autonomous in-IDE coding agent. Public beta 2024-Q4; runs alongside AI Assistant inside IntelliJ-platform IDEs. Plans, edits, runs tests; multi-model.","cited_cells":36,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/jetbrains-junie--jetbrains-com"},{"id":"keycard--keycard-ai","name":"Keycard","url":"https://www.keycard.ai/","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Runtime auth for agents that gives each agent its own identity and issues just-in-time, scoped credentials after verifying the workload, the user it acts for, and policy.","cited_cells":10,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/keycard--keycard-ai"},{"id":"kiro--kiro-dev","name":"Kiro","url":"https://kiro.dev","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Agentic IDE; spec-driven dev (Requirements → Design → Tasks)","license":"","latest_release":"v1.4.26 (2026-10-22) IDE; Kiro CLI v2.34.0 (2026-10-23)","deployment":"Managed-only — desktop IDE (Code OSS fork) and CLI run locally; agent/model backend AWS-hosted; no self-host","pricing":"Free $0 (50 credits/mo); Pro $20/user/mo (1,000 credits); Pro+ $40; Pro Max $100; Power $200; overage $0.04/credit; Enterprise custom","mcp_support":"yes — MCP client in IDE and CLI (CLI 2.34.0 added MCP elicitation)","a2a_support":"searched not found","backend_storage":"local workspace + .kiro/ directory (specs, steering, hooks)","llm_lock":"","github":"","description":"Spec-driven agentic IDE from AWS — preview launch July 2025. Codifies the AI-coding workflow as Requirements / Design / Tasks files generated before code (\"specs\"); also persists \"steering\" files and Hooks. Built as a VS Code fork; runs Anthropic Claude models and Amazon-Nova by default. AWS positions it as an enterprise-grade alternative to Cursor/Windsurf with native IAM, Bedrock-routing, and an emphasis on durable specs over chat scrollback.","cited_cells":53,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/kiro--kiro-dev"},{"id":"kong-ai-gateway--konghq-com","name":"Kong AI Gateway","url":"https://konghq.com/products/kong-ai-gateway","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"Apache-2.0 (Kong Gateway OSS); enterprise features proprietary","latest_release":"last commit 2026-10-19","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/Kong/kong (44321★)","description":"Kong's gateway for governing LLM, MCP and agent-to-agent (A2A) traffic in one place. It controls access, data leakage and token usage for LLM calls, and generates and secures MCP servers for agents.","cited_cells":13,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/kong-ai-gateway--konghq-com"},{"id":"langchain-framework--langchain-com","name":"LangChain (framework)","url":"https://www.langchain.com/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"LLM orchestration framework","license":"MIT (OSS framework)","latest_release":"v1.4.7 (2026-10-21)","deployment":"Both (self-hosted + managed cloud) — OSS library; agents deploy to LangSmith Deployment (cloud, hybrid or self-hosted)","pricing":"searched not found","mcp_support":"yes — MCP client tools via MCPAdapter in langchain.mcp (langchain[mcp] 1.4+, beta; successor to langchain-mcp-adapters)","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"langchain-ai/langchain — ~149k stars, last commit 2026-10","description":"Dominant Python/JS framework for LLM apps — tool calling, agents, retrievers, runnables. Memory is one component (LangMem cross-listed); the framework itself is the product.","cited_cells":23,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/langchain-framework--langchain-com"},{"id":"langflow--gh-langflow-ai-langflow","name":"Langflow","url":"https://github.com/langflow-ai/langflow","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Product","license":"MIT","latest_release":"last commit 2026-10-22","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/langflow-ai/langflow (156024★)","description":"Visual low-code tool for building and deploying AI agents and workflows, with a Python runtime and API/MCP serving.","cited_cells":18,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/langflow--gh-langflow-ai-langflow"},{"id":"langgraph-orchestration--langchain-com","name":"LangGraph (orchestration)","url":"https://www.langchain.com/langgraph","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Stateful agent graph runtime","license":"MIT","latest_release":"v1.2.18 (2026-10-26)","deployment":"Both (self-hosted + managed cloud) — OSS library; LangSmith Deployment cloud, hybrid, or self-hosted Agent Server","pricing":"searched not found","mcp_support":"yes — MCP tools via LangChain MCPAdapter (langchain.mcp) for LangGraph-based agents","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"langchain-ai/langgraph — ~44k stars, last commit 2026-10","description":"LangChain's stateful graph runtime for agents — explicit state, persistence, time-travel debugging, human-in-the-loop. Memory is one persistence target (LangGraph Persistence cross-listed).","cited_cells":44,"third_party_cells":12,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/langgraph-orchestration--langchain-com"},{"id":"lasso-security--lasso-security","name":"Lasso Security","url":"https://www.lasso.security/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"LLM red-team + runtime threat-intelligence platform","license":"","latest_release":"","deployment":"SaaS + on-prem","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Tel-Aviv-founded LLM security platform — adversarial testing, prompt-injection defence, data-leakage prevention. $6M seed Nov-2023 (Entrée Capital + Samsung Next).","cited_cells":16,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lasso-security--lasso-security"},{"id":"lavender--lavender-ai","name":"Lavender","url":"https://www.lavender.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"AI sales-email coach + writer","license":"","latest_release":"","deployment":"","pricing":"Ora AI sales agent $500 per agent/month; Email Coach free to install","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2020; AI email coach for sellers — Gmail/Outlook plugin scores and rewrites cold outbound. $13.2M Series A Sep-2022 (Norwest Venture Partners + LIONS Capital). $10M+ ARR reported.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lavender--lavender-ai"},{"id":"lawdroid-copilot--lawdroid-com","name":"LawDroid Copilot","url":"https://lawdroid.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Solo / small-firm legal AI copilot","license":"","latest_release":"","deployment":"","pricing":"$60–$200/month per seat","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2017 by Tom Martin (lawyer + technologist); LawDroid Copilot serves solo and small-firm lawyers — drafting, research, client intake automation. Bootstrapped + small angel rounds. Marketed against the 'enterprise BigLaw' positioning of Harvey/Casetext. As of 2026-10 lawdroid.ai no longer lists Copilot; the company now markets LawDroid Assist to legal aid organisations, courts and government agencies.","cited_cells":16,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lawdroid-copilot--lawdroid-com"},{"id":"legora--legora-com","name":"Legora","url":"https://legora.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"EU-built legal agent platform","license":"","latest_release":"","deployment":"Managed-only — SaaS","pricing":"Per-seat enterprise","mcp_support":"yes — Legora aOS takes MCP connectors as agent context sources (client side)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Stockholm-founded (2023) legal agent platform — drafting, review, research. $35M Series B Nov-2024 (Iconiq + Redpoint + Y Combinator; $675M val). Targets EU firms with data residency; pitched as 'European Harvey.'","cited_cells":25,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/legora--legora-com"},{"id":"lindy--lindy-ai","name":"Lindy","url":"https://www.lindy.ai/","section":"Multi-agent orchestration platforms","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"No-code commercial multi-agent automation platform (consumer / SMB)","license":"","latest_release":"","deployment":"Managed cloud (SaaS only)","pricing":"Free: $50 in credits for 7 days, no card; Team $29.99/user/mo (3,000 credits, extra $10 per 1,000); Enterprise custom","mcp_support":"","a2a_support":"planned","backend_storage":"","llm_lock":"multi-vendor (BYO OpenAI / Anthropic; managed by Lindy)","github":"","description":"Lindy is a no-code multi-agent automation platform from Florent Crivello (ex-Teleport, ex-Twitter). Targets consumer / SMB segment with email triage, meeting scheduling, CRM-update agents. $50M Series A Oct-2024 led by Andreessen Horowitz + Sequoia. Distinct from Zapier / n8n traditional automation by putting LLMs at the core of every workflow node.","cited_cells":28,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lindy--lindy-ai"},{"id":"liner--liner-com","name":"Liner","url":"https://liner.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Personal AI research assistant (highlight + research)","license":"","latest_release":"","deployment":"","pricing":"Free $0; Pro $17.99/mo ($14.99 billed annually); Max $35.99/mo ($29.99 billed annually)","mcp_support":"yes — Liner Search MCP, Scholar MCP and Actions MCP (1,100+ apps)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Seoul-founded Liner — started as web-highlighter (2015), pivoted to AI research assistant 2023. $40M Series B Jul-2023 ($350M val; Salesforce Ventures + DSC Investment + Beenext). 10M+ users.","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/liner--liner-com"},{"id":"linq-ai--linq-ai","name":"Linq AI","url":"https://www.linq.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"AI agent for financial analysts","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2023; AI-agent platform for financial analysts — multi-step research, data cleansing, model-building. Small seed round; competes in the AlphaSense / Hebbia / Rogo broader space at lower price point. As of 2026-10-29 linq.ai belongs to an unrelated higher-education company, so this product's current home is unconfirmed.","cited_cells":11,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/linq-ai--linq-ai"},{"id":"litera-ai--litera-com","name":"Litera AI (now Lito)","url":"https://www.lito.app/","section":"Use-case-specific agent harnesses","tier":3,"status":"renamed","last_verified_at":"2026-10-29","type":"Document drafting + workflow AI inside Litera suite","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — Lito supports MCP connectors that are governed centrally and enabled firm-wide (lito.app)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Litera (Hg-backed; 50%+ of AmLaw 200 customers) added a Litera AI overlay 2024 — drafting, redlining, document analytics. Litera parent has been a private-equity rollup of legal-tech (Microsystems, Workshare, Kira Systems acquired 2021). As of Oct 2026 Litera markets its AI as Lito (lito.app), a legal AI agent spanning drafting, contract review and redlining, deal review and firm business intelligence (client and billing questions, pitch drafting), sold with Litera One.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/litera-ai--litera-com"},{"id":"livekit-agents--docs-livekit-io","name":"LiveKit Agents","url":"https://docs.livekit.io/agents/","section":"Voice agent platforms","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Voice-agent framework on LiveKit WebRTC platform","license":"Apache-2.0 (framework); turn-detector models under LiveKit Model License","latest_release":"v1.7.1 (2026-08-27) — livekit-agents (Python)","deployment":"Both (self-hosted + managed cloud) — OSS framework self-host + LiveKit Cloud","pricing":"OSS free; LiveKit Cloud tiered ($50/mo+ + usage)","mcp_support":"yes — native MCP support (agents can use MCP server tools)","a2a_support":"searched not found","backend_storage":"Caller-managed; LiveKit handles WebRTC session state","llm_lock":"","github":"livekit/agents — ~13k stars, last commit 2026-08+","description":"LiveKit Agents — agent framework built on LiveKit's open-source WebRTC media server. LiveKit raised $45M Series B Sep-2024 ($300M val). Powers OpenAI Realtime API's WebRTC transport (LiveKit is the substrate OpenAI chose). Agents framework formally launched 2024.","cited_cells":50,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/livekit-agents--docs-livekit-io"},{"id":"llamaindex-framework--llamaindex-ai","name":"LlamaIndex (framework)","url":"https://www.llamaindex.ai/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Data framework for LLM apps","license":"MIT","latest_release":"v0.14.25 (2026-09-21)","deployment":"Both (self-hosted + managed cloud) — OSS library; LlamaAgents workflows deploy to LlamaCloud or self-host","pricing":"searched not found","mcp_support":"yes — use MCP server tools in workflows and serve LlamaIndex workflows as MCP servers","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"run-llama/llama_index — ~53k stars, last commit 2026-10","description":"Data framework for LLM apps — connectors, indices, query engines, agents, workflows. Memory is one of many subsystems (LlamaIndex Memory cross-listed).","cited_cells":23,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/llamaindex-framework--llamaindex-ai"},{"id":"logicgate-risk-cloud--logicgate-com","name":"LogicGate Risk Cloud","url":"https://www.logicgate.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"GRC platform with AI agents","license":"","latest_release":"","deployment":"Managed-only — Risk Cloud SaaS","pricing":"Quote-based: pay for Applications (30+ GRC use cases) plus Power User licenses; Standard and External user licenses included at no extra cost","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2015; GRC platform (Risk Cloud) — flexible policy engine + workflow + risk register. $113M Series C Dec-2021 (PSG + Silversmith). AI features (auto-policy mapping, issue triage) added 2024.","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/logicgate-risk-cloud--logicgate-com"},{"id":"lovable-dev-harness--lovable-dev","name":"Lovable.dev — harness","url":"https://lovable.dev","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"AI app builder — prompt-to-full-stack app (cross-listing)","license":"","latest_release":"","deployment":"Cloud","pricing":"Free + Pro ($25/mo) + Teams ($50/mo)","mcp_support":"yes — chat connectors connect external tools to Lovable via MCP servers","a2a_support":"searched not found","backend_storage":"Lovable-hosted","llm_lock":"","github":"","description":"Cross-listing of Lovable at the harness layer. Swedish startup (Stockholm) that grew out of GPT Engineer (Anton Osika). Builds full-stack React/Supabase apps from prompts; AI handles git, deploys, DB. The Coding-agent-memory row remains canonical for memory.","cited_cells":57,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lovable-dev-harness--lovable-dev"},{"id":"lunar-dev-mcpx--lunar-dev","name":"Lunar.dev MCPX","url":"https://www.lunar.dev/","section":"MCP gateways & registries","tier":3,"status":"acquired","last_verified_at":"2026-10-29","type":"Product","license":"MIT (open-source gateway); enterprise proprietary","latest_release":"last commit 2026-10-29","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/TheLunarCompany/lunar (506★)","description":"Enterprise MCP and AI gateway (MCPX) that secures and governs AI applications and agents with policy enforcement, cost management and observability. Boomi acquired Lunar.dev in July 2026.","cited_cells":13,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lunar-dev-mcpx--lunar-dev"},{"id":"lutra-ai--lutra-ai","name":"Lutra AI","url":"https://lutra.ai/","section":"Computer-use & desktop agents","tier":2,"status":"archived","last_verified_at":"2026-10-29","type":"AI agent platform for SaaS automations (Gmail/Slack/Sheets)","license":"","latest_release":"","deployment":"Cloud only","pricing":"Free tier + Plus ($20/mo) + Team / Enterprise","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Playbook + run state in Lutra cloud DB","llm_lock":"","github":"","description":"AI agent platform that automated SaaS workflows across Gmail, Slack, Sheets, etc. using natural-language instructions compiled into durable playbooks. Founded by ex-Google/Facebook engineers; raised seed funding 2024. Discontinued: lutra.ai now states support for Lutra has been discontinued (seen 2026-10-27).","cited_cells":36,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/lutra-ai--lutra-ai"},{"id":"magic-dev--magic-dev","name":"Magic.dev","url":"https://magic.dev","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Coding-agent startup; ultra-long-context model + agent","license":"","latest_release":"","deployment":"Cloud (private beta)","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"","github":"","description":"AI-coding startup focused on extremely long-context models (claimed 100M tokens) and a frontier coding agent. Raised $320M Series B from Eric Schmidt, CapitalG, Atlassian Aug 2024. Lower public-product surface than peers — mostly known for the model claims and the funding round. As of 2026-10 magic.dev lists no released product; it describes the company as building frontier code models to automate software engineering and research.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/magic-dev--magic-dev"},{"id":"magnetic-one--microsoft-com","name":"Magnetic-One","url":"https://www.microsoft.com/en-us/research/articles/magentic-one-a-generalist-multi-agent-system-for-solving-complex-tasks/","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"deprecated","last_verified_at":"2026-10-31","type":"Microsoft generalist multi-agent","license":"MIT","latest_release":"v0.7.5 (2025-09-30)","deployment":"Self-hosted only — library (autogen-agentchat / autogen-ext)","pricing":"searched not found","mcp_support":"yes — MCP tools via McpWorkbench / StdioServerParams in autogen_ext.tools.mcp","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"microsoft/autogen — ~62k stars, last commit 2026-10","description":"Microsoft Research's generalist multi-agent system — Orchestrator + WebSurfer/FileSurfer/Coder/ComputerTerminal specialists. Built on AutoGen v0.4.","cited_cells":16,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/magnetic-one--microsoft-com"},{"id":"magnitude--magnitude-run","name":"Magnitude","url":"https://magnitude.dev/","section":"Computer-use & desktop agents","tier":3,"status":"deprecated","last_verified_at":"2026-10-29","type":"OSS browser-agent framework for web tests (YC)","license":"Apache-2.0","latest_release":"v0.x ongoing on GitHub","deployment":"Self-hosted only — local library/desktop app","pricing":"OSS free; cloud / enterprise on roadmap","mcp_support":"no — not mentioned in repo","a2a_support":"searched not found","backend_storage":"Local Playwright state","llm_lock":"","github":"magnitudedev/magnitude — ~7.2k stars, last commit n/a (repo repurposed to inference engine)","description":"Formerly an OSS AI browser-agent / natural-language E2E testing framework (YC 2025). The magnitudedev/magnitude repo now hosts an OSS local inference engine + desktop app that serves open models to agents.","cited_cells":40,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/magnitude--magnitude-run"},{"id":"manus-ai--manus-im","name":"Manus AI","url":"https://manus.im","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"General-purpose autonomous web/computer agent","license":"","latest_release":"Manus 2.0 (2026-09-28)","deployment":"Cloud (browser app)","pricing":"$39/$199/mo tier reportedly post-beta","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"cloud sandbox state per session","llm_lock":"","github":"","description":"Chinese-origin general-purpose autonomous agent launched March 2025 by Butterfly Effect. Operates in a cloud sandbox — browser, file system, shell. Went viral on launch with invite-only access; positioned as a Devin/AutoGPT competitor for non-coding tasks (research, ops, data analysis).","cited_cells":34,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/manus-ai--manus-im"},{"id":"marvin--askmarvin-ai","name":"Marvin","url":"https://www.askmarvin.ai/","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-27","type":"Functional LLM toolkit (Prefect)","license":"Apache-2.0","latest_release":"v3.2.7 (2026-03-04)","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"PrefectHQ/marvin — ~6.2k stars, last commit 2026-09","description":"Prefect's Python framework for structured outputs (cast, classify, extract, generate) and agentic workflows (tasks, agents, threads). Marvin 3.0 merged in ControlFlow's agentic engine, superseding ControlFlow (whose repo was archived 2026-03-19); uses Pydantic AI for LLM providers.","cited_cells":15,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/marvin--askmarvin-ai"},{"id":"mastra--mastra-ai","name":"Mastra","url":"https://mastra.ai/","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"TypeScript agent framework","license":"Apache-2.0 (code under ee/ directories under a separate Mastra enterprise license)","latest_release":"v1.79.0 (2026-10-21)","deployment":"Both (self-hosted + managed cloud) — Apache-2.0 framework self-hosted; Mastra Platform hosted deployments","pricing":"Framework free (Apache-2.0); Mastra Platform Starter $0/mo (100K observability events, 24 CPU hours), Teams $250/mo (1M events, 250 CPU hours, SSO), Enterprise custom; persistent server $100/project; enterprise self-hosted license custom","mcp_support":"yes — consume MCP servers and author MCP servers exposing agents/tools via @mastra/mcp","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"mastra-ai/mastra — ~29k stars, last commit 2026-10","description":"TypeScript-first agent framework — Workflows, Agents, RAG, eval. Built by the Gatsby team. YC W25.","cited_cells":23,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/mastra--mastra-ai"},{"id":"mcp-servers-reference--gh-modelcontextprotocol-servers","name":"MCP Servers (Reference)","url":"https://github.com/modelcontextprotocol/servers","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Reference MCP server collection","license":"Apache-2.0 (transitioning from MIT; contributions without relicensing consent remain MIT; docs CC-BY-4.0)","latest_release":"v2.0.1 (2026-10-25)","deployment":"Self-hosted only — run locally via npx (TypeScript) or uvx/pip (Python)","pricing":"searched not found","mcp_support":"yes — reference MCP server implementations","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"modelcontextprotocol/servers — ~92k stars, last commit 2026-10","description":"Official collection of reference Model Context Protocol servers maintained by the MCP project — currently Everything, Fetch, Filesystem, Git, Memory, Sequential Thinking and Time; earlier servers such as GitHub, Google Drive and PostgreSQL were moved to the servers-archived repo. Substrate for the MCP-memory ecosystem.","cited_cells":41,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/mcp-servers-reference--gh-modelcontextprotocol-servers"},{"id":"merge-agent-handler--merge-dev","name":"Merge Agent Handler","url":"https://www.merge.dev/merge-agent-handler","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Production MCP connectors that link AI agents to thousands of enterprise tools, with guided user authentication, data-access controls and observability built in.","cited_cells":10,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/merge-agent-handler--merge-dev"},{"id":"metagpt-harness--gh-foundationagents-metagpt","name":"MetaGPT","url":"https://github.com/FoundationAgents/MetaGPT","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-31","type":"Multi-agent software-company simulation (OSS)","license":"MIT","latest_release":"v0.8.1 (2024-04-22) marked Latest; v0.8.2 tag (2025-03-09)","deployment":"Self-hosted only — Python library/CLI (pip install metagpt)","pricing":"Free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"local workspace + role memory","llm_lock":"","github":"FoundationAgents/MetaGPT — ~71k stars, last commit n/a","description":"Cross-listing of MetaGPT as a harness. Multi-agent OSS framework that simulates a software company — PM, architect, engineer, QA. Generates docs + code + tests from a one-line prompt. Distinct from \"Agent frameworks (no first-party memory layer)\" row in framing.","cited_cells":46,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/metagpt-harness--gh-foundationagents-metagpt"},{"id":"microsoft-agent-framework--gh-microsoft-agent-framework","name":"Microsoft Agent Framework","url":"https://github.com/microsoft/agent-framework","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-26","type":"Framework","license":"MIT","latest_release":"last commit 2026-10-24","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/microsoft/agent-framework (14314★)","description":"Microsoft's framework for building, orchestrating and deploying AI agents and multi-agent workflows in Python and.NET; the successor to Semantic Kernel and AutoGen.","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/microsoft-agent-framework--gh-microsoft-agent-framework"},{"id":"microsoft-autogen-studio--microsoft-github-io","name":"Microsoft AutoGen Studio","url":"https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/index.html","section":"Multi-agent orchestration platforms","tier":2,"status":"deprecated","last_verified_at":"2026-10-27","type":"Low-code multi-agent orchestration UI (Microsoft Research)","license":"MIT","latest_release":"v0.4.2.2 (2025-05-27)","deployment":"Self-hosted only — local web UI (not intended for production)","pricing":"Free (MIT)","mcp_support":"via community port","a2a_support":"","backend_storage":"","llm_lock":"multi-vendor (OpenAI / Anthropic / Azure OpenAI / local)","github":"microsoft/autogen — ~62k stars, last commit 2026-10","description":"Microsoft Research's low-code GUI for prototyping multi-agent workflows on top of the AutoGen framework (not intended for production). Ships in the microsoft/autogen repo, whose README now says the project is archived and no longer maintained (no bug, security or feature fixes); Microsoft points new users to Microsoft Agent Framework. Distinct from the OSS AutoGen framework row; this row covers the Studio GUI.","cited_cells":34,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/microsoft-autogen-studio--microsoft-github-io"},{"id":"microsoft-mcp-gateway--gh-microsoft-mcp-gateway","name":"Microsoft MCP Gateway","url":"https://github.com/microsoft/mcp-gateway","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Framework","license":"MIT","latest_release":"last commit 2026-10-27","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/microsoft/mcp-gateway (899★)","description":"Reverse proxy and management layer for MCP servers on Kubernetes, providing session-aware stateful routing and lifecycle management.","cited_cells":13,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/microsoft-mcp-gateway--gh-microsoft-mcp-gateway"},{"id":"microsoft-semantic-kernel--gh-microsoft-semantic-kernel","name":"Microsoft Semantic Kernel","url":"https://github.com/microsoft/semantic-kernel","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"maintenance","last_verified_at":"2026-10-29","type":"C#/Python/Java agent framework","license":"MIT","latest_release":"v1.45.0 (2026-10-06)","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"yes — MCP servers usable as plugins","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"microsoft/semantic-kernel — ~29k stars, last commit 2026-10","description":"Microsoft's enterprise-focused agent framework — multi-language (C#, Python, Java); Plugins / Planners / Memory; integrates with Azure AI / Foundry. Its README now names Microsoft Agent Framework as the successor; Semantic Kernel still ships releases (maintenance mode).","cited_cells":22,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/microsoft-semantic-kernel--gh-microsoft-semantic-kernel"},{"id":"mindgard--mindgard-ai","name":"Mindgard","url":"https://mindgard.ai/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Continuous AI red-teaming SaaS (UK)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Lancaster-University spinout; continuous automated AI red-teaming SaaS. $8M seed/A Jun-2024 (.406 Ventures + Atlantic Bridge). Founded by Prof. Peter Garraghan.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/mindgard--mindgard-ai"},{"id":"modal-sandboxes--modal-com","name":"Modal Sandboxes","url":"https://modal.com/docs/guide/sandbox","section":"AI sandbox & runtime environments","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Serverless container runtime + AI-agent sandboxes (Modal Labs)","license":"Apache-2.0 (client SDK only; platform proprietary)","latest_release":"v1.6.2 (2026-10-16)","deployment":"Managed cloud (no self-hosting)","pricing":"Pay-per-second compute (CPU + GPU); free tier (~$30/mo credit); team + enterprise tiers","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"modal-labs/modal-client — ~530 stars, last commit 2026-10","description":"Modal Labs ships a serverless container platform with first-class GPU support; Sandboxes feature (2024) adds ephemeral, AI-agent-friendly compute sandboxes. Founded 2021 by Erik Bernhardsson (ex-Spotify ML, author of Luigi + Annoy). $87M total raised through Series B (Lux Capital + Redpoint + Definition + Amplify). Used by major LLM apps for batch inference + agent code execution.","cited_cells":29,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/modal-sandboxes--modal-com"},{"id":"model-context-protocol-mcp-spec--modelcontextprotocol-io","name":"Model Context Protocol (MCP spec)","url":"https://modelcontextprotocol.io/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Open protocol for LLM-tool I/O","license":"Apache-2.0 (new spec and code contributions; transitioning from MIT, un-relicensed MIT contributions remain MIT); docs CC-BY-4.0","latest_release":"v1.32.2 (2026-10-23) — TypeScript SDK; Python SDK v2.3.0 (2026-10-02); current spec revision 2026-07-28","deployment":"searched not found","pricing":"searched not found","mcp_support":"yes — this is the MCP specification itself","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"modelcontextprotocol/modelcontextprotocol — ~9.5k stars, last commit 2026-10","description":"Anthropic-introduced open protocol (Nov 2024) for connecting LLMs to data sources and tools. Donated by Anthropic to the Linux Foundation's Agentic AI Foundation (announced 2025-12-09); now governed as Model Context Protocol, a Series of LF Projects, LLC. Supported across Claude, ChatGPT, VS Code, Cursor and many other clients.","cited_cells":37,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/model-context-protocol-mcp-spec--modelcontextprotocol-io"},{"id":"multion--multion-ai","name":"MultiOn (now AGI, Inc.)","url":"https://theagi.company/","section":"Multi-agent orchestration platforms","tier":2,"status":"renamed","last_verified_at":"2026-10-29","type":"Web-agent / browser-agent API platform (developer-focused autonomous browsing)","license":"","latest_release":"v1.3.8 (2024-10-08) — multion Python SDK","deployment":"Managed-only (MultiOn API)","pricing":"API pay-per-task; freemium developer tier","mcp_support":"via community port","a2a_support":"","backend_storage":"","llm_lock":"multi-vendor (BYO; can switch OpenAI / Anthropic / Gemini)","github":"","description":"Web-browsing agent API platform (MultiOn Agent API, docs still labelled Agent V1 Beta). Founded 2023 by Div Garg. As of 2026-10 www.multion.ai redirects to AGI, Inc. (theagi.company), which now markets AGI-0, an on-device action model and agent that operates Android apps, plus a developer Platform; the multion Python SDK has had no release since 2024-10.","cited_cells":24,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/multion--multion-ai"},{"id":"n8n-ai-agent-flows--n8n-io","name":"n8n (AI agent flows)","url":"https://n8n.io/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Workflow automation + AI nodes","license":"Sustainable Use License (semi-OSS)","latest_release":"v2.45.4 (2026-10-26)","deployment":"Both (self-hosted + managed cloud) — n8n Cloud (Starter/Pro/Enterprise) or self-hosted Community/Business editions","pricing":"Cloud Starter EUR 20/mo and Pro EUR 50/mo (billed annually); Business EUR 667/mo (self-hosted, billed annually); Enterprise custom; Community Edition self-hosted from GitHub","mcp_support":"yes — built-in instance-level MCP server (Settings, Instance-level MCP) plus MCP Server Trigger node to expose a workflow's tools","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"n8n-io/n8n — ~209k stars, last commit 2026-10","description":"Open-source workflow automation platform with first-class AI Agent / LangChain / Memory / Tool nodes — fastest-growing workflow tool in the AI era.","cited_cells":22,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/n8n-ai-agent-flows--n8n-io"},{"id":"nango--nango-dev","name":"Nango","url":"https://nango.dev/","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"Elastic-2.0","latest_release":"last commit 2026-10-29","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/NangoHQ/nango (13034★)","description":"Code-first integration platform that connects products and AI agents to 1,000+ APIs. It handles end-user OAuth, MCP and tools, syncs, webhooks and a request proxy.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/nango--nango-dev"},{"id":"new-relic-ai--newrelic-com","name":"New Relic AI","url":"https://newrelic.com/platform/new-relic-ai","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"GenAI observability assistant","license":"","latest_release":"","deployment":"","pricing":"Usage-based: 100 GB/month free ingest, then $0.40/GB (Data Plus $0.60/GB) on Standard/Pro; user fees vary by edition (basic users free); Enterprise via sales","mcp_support":"yes — New Relic MCP server lets MCP clients query and act on New Relic data (enabled via feature control manager)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"New Relic's AI agent — natural-language NRQL queries, error summaries, error-grouping. Launched late-2023. New Relic parent: taken private by Francisco Partners + TPG for $6.5B Nov-2023.","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/new-relic-ai--newrelic-com"},{"id":"numerai-signals--signals-numer-ai","name":"Numerai Signals","url":"https://signals.numer.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Crowdsourced AI signals hedge-fund platform","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — Numerai API and MCP for agentic research pipelines (API keys with scopes)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Numerai is a crowdsourced AI hedge fund — data scientists submit predictive signals + are paid in NMR (cryptocurrency) based on signal performance. Numerai Signals is the global-equities tournament. Founded 2015 by Richard Craib. ~$200M AUM reported.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/numerai-signals--signals-numer-ai"},{"id":"obot--obot-ai","name":"Obot","url":"https://obot.ai/","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"MIT","latest_release":"last commit 2026-10-29","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/obot-platform/obot (1136★)","description":"Open-source AI control plane and MCP platform that connects agents to MCP servers through one OAuth setup. It enforces policy on what agents can do and records full audit logs of tool calls and LLM requests.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/obot--obot-ai"},{"id":"official-mcp-registry--registry-modelcontextprotocol-io","name":"Official MCP Registry","url":"https://registry.modelcontextprotocol.io/","section":"MCP gateways & registries","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"Apache-2.0 (transitioning from MIT)","latest_release":"last commit 2026-10-29","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/modelcontextprotocol/registry (7419★)","description":"Community-driven registry service and API run by the Model Context Protocol project, where publishers list MCP servers under namespaced, versioned entries for clients and downstream catalogs to discover.","cited_cells":12,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/official-mcp-registry--registry-modelcontextprotocol-io"},{"id":"okta-cross-app-access-xaa--okta-com","name":"Okta Cross App Access (XAA)","url":"https://www.okta.com/solutions/cross-app-access/","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Okta-backed protocol for secure agent-to-app and app-to-app access, letting enterprise IT admins manage and audit which agents connect to which applications instead of relying on shared credentials or embedded tokens.","cited_cells":7,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/okta-cross-app-access-xaa--okta-com"},{"id":"onspring-ai--onspring-com","name":"Onspring AI","url":"https://onspring.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"GRC + workflow platform with AI agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2010; GRC + business-process automation. Adds AI agent (Sophia) 2024 — natural-language workflow building + automated control assessment. Bootstrapped + small minority growth equity.","cited_cells":15,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/onspring-ai--onspring-com"},{"id":"openai-agents-sdk--gh-openai-openai-agents-python","name":"OpenAI Agents SDK","url":"https://github.com/openai/openai-agents-python","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"OpenAI's official agent framework","license":"MIT","latest_release":"v0.24.0 (2026-10-15) — Python; JS/TS @openai/agents v0.21.0 (2026-10-20)","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"yes — HostedMCPTool plus MCPServerStreamableHttp, MCPServerStdio and MCPServerSse (deprecated) server classes","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"openai/openai-agents-python — ~30k stars, last commit 2026-10 (JS: openai/openai-agents-js ~3.9k)","description":"OpenAI's official Python framework for agents — handoffs, guardrails, tracing built in. Successor to OpenAI Swarm (experimental); officially supported.","cited_cells":43,"third_party_cells":11,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openai-agents-sdk--gh-openai-openai-agents-python"},{"id":"openai-codex-cli--gh-openai-codex","name":"OpenAI Codex CLI","url":"https://github.com/openai/codex","section":"Agent IDEs & coding harnesses","tier":1,"status":"deprecated","last_verified_at":"2026-10-29","type":"Terminal-native agentic coding harness (OpenAI)","license":"Apache-2.0","latest_release":"v0.165.0 (2026-10-27)","deployment":"Self-hosted only — local CLI (npm/Homebrew); model calls go to OpenAI via ChatGPT sign-in or API key","pricing":"CLI free (Apache-2.0); usage via ChatGPT plans (Free/Go limited, Plus $20/mo, Pro $100–200/mo, Business $25/user/mo) or API-key per-token billing","mcp_support":"yes — MCP client (mcp_servers in ~/.codex/config.toml); documented in Codex MCP docs","a2a_support":"searched not found","backend_storage":"local ~/.codex/ + git","llm_lock":"","github":"openai/codex — ~128k stars, last commit 2026-10","description":"OpenAI's actively developed OSS terminal coding agent (Apr 2025), now written in Rust (codex-rs replaced the original TS CLI); also IDE extension + desktop app. Separate from the Codex Web cloud agent and the retired 2021 Codex model API. The codex mcp-server command (Codex as an MCP server) was deprecated on 2026-08-24 and removed in CLI 0.154.0 (2026-09-09); OpenAI points integrations to the experimental Codex app server, and codex mcp still connects Codex to external MCP servers.","cited_cells":69,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openai-codex-cli--gh-openai-codex"},{"id":"openai-deep-research--openai-com","name":"OpenAI Deep Research","url":"https://openai.com/index/introducing-deep-research/","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-31","type":"Autonomous research agent (cross-listing harness)","license":"","latest_release":"","deployment":"","pricing":"Pro $200/mo (100 queries/mo); Plus tier 10 queries/mo (post-Apr 2025)","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Cross-listing: OpenAI Deep Research, launched Feb-2025 inside ChatGPT, is OpenAI's flagship long-horizon research agent (o3 base model). Distinct from the OpenAI Codex / Computer Use rows because the focus is web-research + multi-step synthesis. Available to Pro / Plus / Team / Enterprise users. The separate API models o3-deep-research and o4-mini-deep-research were retired on 2026-07-23, with gpt-5.6-sol as OpenAI's recommended replacement.","cited_cells":42,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openai-deep-research--openai-com"},{"id":"openai-operator--openai-com","name":"OpenAI Operator","url":"https://openai.com/index/introducing-operator/","section":"Computer-use & desktop agents","tier":1,"status":"deprecated","last_verified_at":"2026-10-31","type":"Consumer computer-use agent (browser-only)","license":"","latest_release":"","deployment":"Cloud (OpenAI-hosted browser sandbox) — no self-host","pricing":"Bundled with ChatGPT Pro $200/mo","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"OpenAI-hosted browser session state; no durable cross-session memory by default","llm_lock":"","github":"","description":"OpenAI's general-purpose browser agent — research preview launched January 2025 (US Pro tier). Built on the Computer-Using Agent (CUA) model that processes screenshots and emits mouse / keyboard actions; runs inside an OpenAI-hosted browser sandbox. Operator is the consumer product; the underlying CUA model is the substrate. Superseded by ChatGPT agent (launched 2025-07-17), which absorbed Operator's functionality as agent mode in ChatGPT; operator.chatgpt.com now redirects to ChatGPT agent mode.","cited_cells":57,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openai-operator--openai-com"},{"id":"openai-realtime-api--platform-openai-com","name":"OpenAI Realtime API","url":"https://platform.openai.com/docs/guides/realtime","section":"Voice agent platforms","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Speech-to-speech LLM API (OpenAI Realtime)","license":"","latest_release":"","deployment":"API (Cloud); no self-host","pricing":"Audio token-based: $40/$80 per 1M input/output audio tokens (Oct-2024 launch)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Stateless session API; caller manages durability","llm_lock":"","github":"openai/openai-realtime-agents — ~6.9k stars (MIT reference app on Agents SDK), last commit n/a; API itself closed source","description":"OpenAI's Realtime API for native speech-to-speech multimodal interaction with GPT-4o — launched Oct 2024 (DevDay). Skips the STT → LLM → TTS pipeline by passing speech directly to GPT-4o. The platform substrate that Vapi/Retell/Bland integrate as one of their LLM choices.","cited_cells":66,"third_party_cells":11,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openai-realtime-api--platform-openai-com"},{"id":"openai-swarm-deprecated--gh-openai-swarm","name":"OpenAI Swarm (deprecated)","url":"https://github.com/openai/swarm","section":"Agent frameworks (no first-party memory layer)","tier":4,"status":"deprecated","last_verified_at":"2026-10-29","type":"Experimental multi-agent recipe","license":"MIT","latest_release":"searched not found","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"openai/swarm — ~22k stars, last commit 2026-04 (not archived; no releases)","description":"OpenAI Swarm — experimental educational multi-agent framework released Oct 2024; deprecated in favour of the OpenAI Agents SDK in Mar 2025.","cited_cells":14,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openai-swarm-deprecated--gh-openai-swarm"},{"id":"openbb--openbb-co","name":"OpenBB","url":"https://openbb.co/","section":"Use-case-specific agent harnesses","tier":3,"status":"acquired","last_verified_at":"2026-10-28","type":"OSS investment-research platform with AI agents","license":"Apache-2.0","latest_release":"openbb 5.0.0 (2026-09-29)","deployment":"","pricing":"","mcp_support":"yes — Open Data Platform exposes data to AI agents via MCP servers; Workspace MCP launched 2026-05-26","a2a_support":"","backend_storage":"","llm_lock":"","github":"openbq-org/OpenBB — ~74.8k stars, last commit 2026-10","description":"Founded 2021 by Didier Lopes; OSS investment-research platform — Bloomberg-Terminal-alternative. AGPLv3 + commercial OpenBB Pro. $11M seed 2022 (OSS Capital + Y Combinator). AI agent (OpenBB Copilot) launched 2024.","cited_cells":24,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openbb--openbb-co"},{"id":"opencode-sst--opencode-ai","name":"Opencode (SST)","url":"https://opencode.ai","section":"Agent IDEs & coding harnesses","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"OSS terminal coding agent (SST)","license":"MIT","latest_release":"v1.19.4 (2026-10-22)","deployment":"Self-hosted only — local TUI/CLI (npm, Homebrew) and desktop app; BYO model provider","pricing":"Free (OSS)","mcp_support":"native — Opencode is an MCP client","a2a_support":"searched not found","backend_storage":"local AGENTS.md + config","llm_lock":"","github":"anomalyco/opencode (formerly sst/opencode) — ~222k stars, last commit 2026-10","description":"SST team's open-source terminal coding agent — TypeScript, multi-model, MCP-native. Released 2025; explicitly positioned as a permissively-licensed Claude Code alternative. Memory via AGENTS.md (the emerging cross-harness convention).","cited_cells":49,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/opencode-sst--opencode-ai"},{"id":"openhands-all-hands-ai--all-hands-dev","name":"OpenHands","url":"https://www.openhands.dev/","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-31","type":"OSS autonomous SWE agent platform (formerly OpenDevin)","license":"MIT","latest_release":"v1.24.0 (2026-09-25)","deployment":"Both (self-hosted + managed cloud) — Docker/local self-host + OpenHands Cloud (commercial)","pricing":"Free (OSS) + paid cloud ($20/mo+)","mcp_support":"yes — connects to external MCP servers over SSE, Streamable HTTP or stdio","a2a_support":"searched not found","backend_storage":"Docker sandbox state","llm_lock":"","github":"OpenHands/OpenHands (formerly All-Hands-AI/OpenHands) — ~92k stars, last commit 2026-09","description":"Cross-listing of OpenHands at the harness layer. OSS Devin-alternative — sandboxed full SWE agent with browser + shell + editor. Renamed from OpenDevin Mar 2024. Commercial offering: All Hands AI cloud (managed SaaS).","cited_cells":62,"third_party_cells":49,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/openhands-all-hands-ai--all-hands-dev"},{"id":"opsramp-ai--opsramp-com","name":"OpsRamp AI","url":"https://www.opsramp.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"acquired","last_verified_at":"2026-10-28","type":"AIOps platform (HPE-acquired)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2014; AIOps platform — hybrid + multi-cloud observability with AI event correlation. **Acquired by HPE Jul-2023** (terms undisclosed; reported ~$200M+). AI agent features now integrated into HPE GreenLake.","cited_cells":16,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/opsramp-ai--opsramp-com"},{"id":"outreach-ai--outreach-io","name":"Outreach AI","url":"https://www.outreach.ai/ai-agents","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"AI features inside sales-engagement platform","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — MCP Client (connects Outreach agents to external systems) and MCP Server (exposes Outreach insights and actions to external AI tools)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Outreach (the largest sales-engagement platform; $4.4B val 2021) has added AI features: Smart Email Assist, Smart Account Plan, Smart Forecasting, Kaia conversation intelligence. Strategic pivot to AI-agent platform announced 2024.","cited_cells":19,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/outreach-ai--outreach-io"},{"id":"pagerduty-aiops--pagerduty-com","name":"PagerDuty AIOps","url":"https://www.pagerduty.com/platform/aiops/","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"Incident-response AIOps platform with agents","license":"","latest_release":"","deployment":"","pricing":"AIOps add-on starting at $799/month billed monthly ($699/month billed yearly), usage-based","mcp_support":"yes — hosted PagerDuty Remote MCP Server (the earlier local pagerduty-mcp-server repo is deprecated and read-only)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"PagerDuty's AIOps tier adds AI alert grouping, noise suppression, and AI agent suggestions for incident response. Includes the Jeli acquisition (May-2023, $73M) for incident retrospective AI. PagerDuty parent: $450M+ revenue.","cited_cells":23,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pagerduty-aiops--pagerduty-com"},{"id":"paragon-actionkit--useparagon-com","name":"Paragon ActionKit","url":"https://www.useparagon.com/actionkit","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"One API and MCP server that gives an AI agent product 1,000+ integration actions, with Paragon's embedded UI handling end users' authentication to their external apps.","cited_cells":9,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/paragon-actionkit--useparagon-com"},{"id":"pentera--pentera-io","name":"Pentera","url":"https://pentera.io/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Automated security validation / pentest platform","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2015 (ex-Pcysys); automated security validation — pentest, red-team, attack-surface validation. $60M Series D Jan-2024 ($1B val unicorn; Evolution Equity + K1). Israeli cyber pedigree; more mature than 2024-vintage GenAI pentest agents.","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pentera--pentera-io"},{"id":"people-ai--people-ai","name":"People.ai (now Backstory)","url":"https://www.backstory.ai/","section":"Use-case-specific agent harnesses","tier":2,"status":"renamed","last_verified_at":"2026-10-28","type":"Revenue intelligence + AI SalesAI agent","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — Backstory MCP Server delivers deal context into Claude, ChatGPT, Gemini and other LLM clients","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2016 by Oleg Rogynskyy; revenue intelligence — activity capture + AI account intelligence. $100M Series D Sep-2021 ($1.1B val; Akkadian + ICONIQ). SalesAI agent launched 2024.","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/people-ai--people-ai"},{"id":"perplexity-deep-research--perplexity-ai","name":"Perplexity Deep Research","url":"https://www.perplexity.ai/hub/blog/introducing-perplexity-deep-research","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-29","type":"Autonomous research agent (Perplexity)","license":"","latest_release":"","deployment":"","pricing":"Pro $20/mo (unlimited); free 5/day","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Perplexity's autonomous-research mode, launched Feb-2025 — multi-step research agent inside Perplexity. Perplexity parent: $9B val Dec-2024 ($500M round; IVP + NEA + Andreessen Horowitz).","cited_cells":42,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/perplexity-deep-research--perplexity-ai"},{"id":"phidata-now-agno--agno-com","name":"Phidata (now Agno)","url":"https://www.agno.com/","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"renamed","last_verified_at":"2026-10-27","type":"Multi-modal agent framework","license":"Apache-2.0","latest_release":"v3.1.10 (2026-10-23)","deployment":"Self-hosted only — open-source SDK and AgentOS run in your own cloud; paid tiers add a hosted control plane","pricing":"Free (control plane against local AgentOS); Pro USD 150/mo (one live AgentOS connection, 3 seats); Enterprise custom","mcp_support":"yes — MCPTools class connects agents to MCP servers (stdio, Streamable HTTP)","a2a_support":"searched not found","backend_storage":"","llm_lock":"multi-vendor (50+ providers — OpenAI / Anthropic / Gemini / Groq / Ollama / vLLM)","github":"agno-agi/agno — ~43k stars, last commit 2026-10 (phidatahq/phidata redirects here)","description":"Multi-modal agent framework (renamed from Phidata to Agno in 2025) — agents, memory, knowledge, tools; emphasis on multi-modal pipelines.","cited_cells":36,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/phidata-now-agno--agno-com"},{"id":"pillar-security--pillar-security","name":"Pillar Security","url":"https://www.pillar.security/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Runtime AI security platform (red-team + production guardrails)","license":"","latest_release":"","deployment":"Both (self-hosted + managed cloud) — cloud, self-hosted and hybrid options","pricing":"Enterprise quote","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Tel-Aviv-founded (Dor Sarig + Ziv Karliner, both ex-IDF cyber); end-to-end LLM security platform — discovery, red-teaming, runtime guardrails. $9M seed Apr-2024 (Shield Capital + Greenfield).","cited_cells":22,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pillar-security--pillar-security"},{"id":"pincites--pincites-com","name":"Pincites (now Filevine LOIS for Word)","url":"https://www.filevine.com/platform/lois-for-word/","section":"Use-case-specific agent harnesses","tier":3,"status":"acquired","last_verified_at":"2026-10-29","type":"AI for contract negotiation","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"YC-W24 contract-review AI; auto-redlines vendor contracts based on the in-house playbook. $3.6M seed 2024 (Y Combinator + Liquid 2). Targets in-house legal at SaaS companies. Acquired by Filevine (2025-12; announced 2026-01-14); the product became LOIS for Word, part of Filevine's Legal Operating Intelligence System.","cited_cells":17,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pincites--pincites-com"},{"id":"pipecat-daily--pipecat-ai","name":"Pipecat (Daily)","url":"https://www.pipecat.ai/","section":"Voice agent platforms","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"OSS voice-agent framework (Daily.co)","license":"BSD-2-Clause","latest_release":"v1.7.0 (2026-08-01)","deployment":"Both (self-hosted + managed cloud) — pip self-host + Pipecat Cloud","pricing":"OSS free; runs on Daily.co Cloud or self-host","mcp_support":"Composes with MCP tools (caller-side)","a2a_support":"searched not found","backend_storage":"In-memory context; caller adds durability","llm_lock":"","github":"pipecat-ai/pipecat — ~16.8k stars, last commit 2026-08+","description":"Open-source Python framework for real-time voice + multimodal AI agents, maintained by Daily.co. Pipeline-style architecture (STT → context → LLM → TTS) wired over WebRTC. The OSS substrate that many of the voice platforms build on or compose with.","cited_cells":52,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pipecat-daily--pipecat-ai"},{"id":"pipedream-connect--pipedream-com","name":"Pipedream Connect","url":"https://pipedream.com/connect","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary; components repo under Pipedream Source Available License","latest_release":"last commit 2026-10-28","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/PipedreamHQ/pipedream (11763★)","description":"Integration layer for AI agents with managed per-user auth and 10,000+ prebuilt tools across 3,000+ APIs. It is exposed through a remote MCP server, an SDK or a raw API proxy.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pipedream-connect--pipedream-com"},{"id":"project-mariner--deepmind-google","name":"Project Mariner","url":"https://labs.google.com/mariner/","section":"Computer-use & desktop agents","tier":1,"status":"archived","last_verified_at":"2026-10-31","type":"Google DeepMind browser-agent (research preview)","license":"","latest_release":"","deployment":"Chrome extension + Google Cloud","pricing":"Bundled with Gemini Advanced ($19.99/mo)","mcp_support":"searched not found","a2a_support":"Google's own A2A protocol — likely first-party compatible","backend_storage":"Google-managed session state","llm_lock":"","github":"","description":"Google DeepMind's experimental browser agent built on Gemini 2.0, a Chrome extension that took actions on the user's behalf. Research preview launched Dec 2024 as Google's answer to OpenAI Operator / Anthropic Computer Use. Shut down on 2026-05-04; Google directs users to Gemini for complex agentic tasks.","cited_cells":57,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/project-mariner--deepmind-google"},{"id":"promptfoo--promptfoo-dev","name":"Promptfoo","url":"https://www.promptfoo.dev/","section":"Use-case-specific agent harnesses","tier":2,"status":"acquired","last_verified_at":"2026-10-28","type":"OSS LLM eval + red-team toolkit","license":"MIT","latest_release":"0.125.1 (2026-10-25)","deployment":"Both (self-hosted + managed cloud) — OSS CLI runs locally; Enterprise managed cloud or on-premise","pricing":"Community: free (open source, incl. 10k red-team probes/month); Enterprise: custom (managed cloud); On-Premise: custom","mcp_support":"yes — MCP Proxy product for securing MCP traffic, plus MCP testing integrations","a2a_support":"","backend_storage":"","llm_lock":"","github":"promptfoo/promptfoo — ~26.5k stars, last commit 2026-10","description":"OSS (MIT) prompt-engineering eval and red-team CLI; supports OWASP LLM Top-10 vulnerability tests, jailbreak generation, and CI/CD pipeline integration. $5M seed Mar-2024 (Andreessen Horowitz). Founders ex-Discord + ex-Smile Identity.","cited_cells":27,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/promptfoo--promptfoo-dev"},{"id":"protect-ai--protectai-com","name":"Protect AI","url":"https://www.paloaltonetworks.com/ai-security/prisma-airs","section":"Use-case-specific agent harnesses","tier":2,"status":"acquired","last_verified_at":"2026-10-29","type":"AI/ML model security platform (acquired by Palo Alto Networks 2025)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2022 by Ian Swanson + Daryan Dehghanpisheh (ex-AWS); AI/ML supply-chain + GenAI security. Acquired by Palo Alto Networks (2025-07-22; announced Apr-2025, reported $700M); its capabilities now ship in Prisma AIRS. Products: Recon (red-team), ModelScan (model artifact scanner), Sightline (vulnerability DB).","cited_cells":15,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/protect-ai--protectai-com"},{"id":"pydantic-ai--ai-pydantic-dev","name":"Pydantic-AI","url":"https://pydantic.dev/docs/ai/overview/","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Type-safe LLM agent framework","license":"MIT","latest_release":"v2.62.0 (2026-10-27)","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"yes — MCP client via MCP capability / MCPToolset, agents can run inside MCP servers, MCPServerTool for provider-native MCP","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"pydantic/pydantic-ai — ~21k stars, last commit 2026-10","description":"Pydantic team's agent framework — type-safe agent definitions, structured outputs, tool calls validated by Pydantic schemas.","cited_cells":22,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pydantic-ai--ai-pydantic-dev"},{"id":"reflection-ai--reflection-ai","name":"Reflection AI","url":"https://reflection.ai/","section":"Multi-agent orchestration platforms","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Autonomous coding-agent foundation lab (Misha Laskin / Ioannis Antonoglou)","license":"","latest_release":"","deployment":"Both (self-hosted + managed cloud) — Beam open weights deployable in own environment, or via Reflection Platform API","pricing":"Beam open weights free on Hugging Face; hosted Beam via Reflection's self-serve API Platform (API keys); no public per-token prices on the homepage","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"multi-vendor (uses Claude + GPT internally per reports)","github":"","description":"Founded 2024 by Misha Laskin and Ioannis Antonoglou (ex-DeepMind). Pivoted from autonomous coding agents (Asimov) to open-weight frontier models: its first open-weight model Beam is a 501B-parameter MoE built for coding, reasoning and agentic workloads, offered with open-source harnesses/containers, a Platform API, and self-deployment (private cloud, air-gapped, edge).","cited_cells":24,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/reflection-ai--reflection-ai"},{"id":"reggie-ai--reggie-ai","name":"Reggie.ai","url":"https://www.reggie.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"archived","last_verified_at":"2026-10-29","type":"AI sales agents (Reggie)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2023; AI sales-agent product — autonomous outbound, meeting booking, follow-up. $4.7M seed Jul-2024 (Lightspeed + Mantis). Direct competitor in the 11x.ai / Artisan AI / Bland niche. As of 2026-10 the reggie.ai domain is parked and listed for sale on GoDaddy; the product appears discontinued.","cited_cells":13,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/reggie-ai--reggie-ai"},{"id":"replit-agent-v3--replit-com","name":"Replit Agent v3","url":"https://replit.com/ai","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Cloud IDE with autonomous coding agent (Replit)","license":"","latest_release":"Replit Agent 4 (2026-03-13)","deployment":"Both (self-hosted + managed cloud) — managed SaaS; enterprise Bring Your Own Cloud on AWS, Azure or Google Cloud (Full BYOC private preview, 2026-10)","pricing":"Core $20/mo ($18/mo billed annually); Pro $100/mo ($90/mo billed annually; higher usage tiers up to $2,000/mo); Enterprise custom","mcp_support":"yes — one-click MCP server list plus custom MCP servers; Agent loads their tools","a2a_support":"searched not found","backend_storage":"Replit-hosted","llm_lock":"","github":"","description":"Cross-listing of Replit Agent at the harness layer. Replit Agent v3 (2025) added background agents + agent-driven deploy. The Coding-agent-memory row remains canonical for the memory framing.","cited_cells":53,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/replit-agent-v3--replit-com"},{"id":"resolve-ai--resolve-ai","name":"Resolve.ai","url":"https://resolve.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Autonomous AI SRE agent","license":"","latest_release":"","deployment":"","pricing":"Quote-based (Get Pricing / demo); no list prices published","mcp_support":"yes — plugs into existing tooling via MCP, API and Skills","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2024 by Spiros Xanthos (ex-Splunk Observability SVP; founder of Omnition acq Splunk 2019). Autonomous AI SRE — investigates incidents end-to-end. $35M seed Aug-2024 (Greylock + Unusual). Pitched as 'the AI SRE.'","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/resolve-ai--resolve-ai"},{"id":"restate--restate-dev","name":"Restate","url":"https://restate.dev/","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-27","type":"Durable execution platform","license":"BUSL-1.1 (Restate server); SDKs MIT","latest_release":"v1.8.1 (2026-10-21) — server; TypeScript SDK v1.17.4 (2026-10-20)","deployment":"Both (self-hosted + managed cloud) — Restate Cloud or self-hosted server","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"restatedev/restate — ~4.6k stars, last commit 2026-10","description":"Durable-execution platform from ex-Confluent / Flink team — Restate Cloud + OSS server; emphasises low-latency invocation vs Temporal's polling.","cited_cells":19,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/restate--restate-dev"},{"id":"retell-ai--retellai-com-2","name":"Retell AI","url":"https://www.retellai.com/","section":"Voice agent platforms","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Developer platform for AI voice agents (low-latency)","license":"","latest_release":"","deployment":"Cloud-managed","pricing":"Pay-as-you-go $0.07-$0.31/min for voice agents (Retell voice infra $0.055/min plus TTS and LLM components), $10 free credits, 20 concurrent calls included; Enterprise custom","mcp_support":"yes — agents can call MCP tools during live calls","a2a_support":"searched not found","backend_storage":"Call state in Retell-managed DB","llm_lock":"","github":"github.com/RetellAI (SDKs only)","description":"Voice-agent platform with vendor focus on sub-800ms turn latency and proprietary voice models. Y Combinator S24; raised $4.6M seed Aug 2024 (BoxGroup + others); >$1M ARR by month 6 per founders. Direct competitor to Vapi with proprietary-model focus.","cited_cells":46,"third_party_cells":5,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/retell-ai--retellai-com-2"},{"id":"robust-intelligence--robustintelligence-com","name":"Robust Intelligence","url":"https://www.cisco.com/site/us/en/products/security/ai-defense/robust-intelligence-is-part-of-cisco/index.html","section":"Use-case-specific agent harnesses","tier":2,"status":"acquired","last_verified_at":"2026-10-29","type":"ML/AI risk platform (acquired by Cisco Sep 2024)","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2019 by Yaron Singer (Harvard); ML risk management — model testing, validation, runtime detection. Acquired by Cisco (2024-10); now foundational to Cisco AI Defense and Cisco Foundation AI. Note: Harrison Chase (LangChain CEO) was an early Robust Intelligence ML lead.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/robust-intelligence--robustintelligence-com"},{"id":"rogo--rogo-ai","name":"Rogo","url":"https://rogo.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Investment-banking AI agent","license":"","latest_release":"","deployment":"Managed-only — SaaS platform","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2022 by Gabriel Stengel (ex-Lazard + Stanford); AI agent purpose-built for investment-banking workflows — comps, precedent transactions, IC memo drafting. $50M Series B Mar-2025 ($350M val; Khosla + Thrive Capital + Tiger Global). Customer base: 25+ IBs including Lazard, Tiger Global, Hellman & Friedman.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/rogo--rogo-ai"},{"id":"roo-code--roocode-com","name":"Roo Code","url":"https://github.com/RooCodeInc/Roo-Code","section":"Agent IDEs & coding harnesses","tier":3,"status":"archived","last_verified_at":"2026-10-29","type":"OSS VS Code agentic extension (fork of Cline)","license":"Apache-2.0","latest_release":"Roo Code 3.x rolling","deployment":"Self-hosted only — VS Code extension (shut down 2026-05-15)","pricing":"Discontinued — extension shut down 2026-05-15 (code remains Apache-2.0)","mcp_support":"native (inherited from Cline)","a2a_support":"searched not found","backend_storage":"local workspace + .roorules","llm_lock":"","github":"RooCodeInc/Roo-Code — ~24.3k stars, archived 2026-05-15","description":"Discontinued OSS VS Code agentic extension — Cline fork with custom modes (Architect, Code, Ask, Debug) and .roorules/Memory Bank. Shut down 2026-05-15; repo archived.","cited_cells":44,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/roo-code--roocode-com"},{"id":"runwhen--runwhen-com","name":"RunWhen","url":"https://www.runwhen.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Open-source AI SRE platform with CodeCollection","license":"Apache-2.0","latest_release":"","deployment":"","pricing":"$30k one-time 30-day sprint (3 agents/30 skills); self-hosted license $25k/yr (5,000 tickets), $45k/yr (10,000 tickets+chats), $115k/yr (30,000); outcome-based enterprise contracts; BYO LLM endpoint","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"runwhen-contrib/rw-cli-codecollection — ~26 stars, last commit 2026-10 (plus other runwhen-contrib repos)","description":"OSS-first AI-SRE platform; CodeCollection (the OSS runbook library) is the differentiator — 'GitHub for SRE runbooks.' Apache-2.0. Bootstrapped + small angel funding. RunWhen Local self-hosted.","cited_cells":22,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/runwhen--runwhen-com"},{"id":"sakana-ai-scientist--sakana-ai","name":"Sakana AI Scientist","url":"https://sakana.ai/ai-scientist/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Autonomous AI research-paper-writing agent","license":"The AI Scientist Source Code License v1.0 (based on Responsible AI Source Code License; not OSI-approved)","latest_release":"","deployment":"Self-hosted only — research code","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"SakanaAI/AI-Scientist — ~14.8k stars, last commit 2025-12 (v2: SakanaAI/AI-Scientist-v2 ~7.4k stars)","description":"Tokyo-based Sakana AI's autonomous research agent — generates ideas, runs experiments, writes papers, peer-reviews. v1 paper Aug-2024 (arXiv 2408.06292); v2 update 2025. **Sakana parent: $214M Series A Sep-2024 ($1.5B val; NEA + Khosla)**.","cited_cells":20,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sakana-ai-scientist--sakana-ai"},{"id":"salesforce-agentforce--salesforce-com","name":"Salesforce Agentforce","url":"https://www.salesforce.com/agentforce/","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"Multi-agent platform on Data Cloud (cross-listing harness)","license":"","latest_release":"","deployment":"","pricing":"Foundations free; Flex Credits $500 per 100k credits (pay per action); Agentforce User License $5/user/mo; Agentforce Coworker $50/user/mo; editions with Agentforce from $550/user/mo","mcp_support":"yes — Agentforce MCP Support connects agents to verified MCP servers from AgentExchange partners","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Cross-listing: Salesforce Agentforce already exists under Vertical / Customer-support / voice memory; this row is the Agent-harness framing — Agentforce as the consumer-facing agent IDE / builder on Data Cloud. Agentforce launched Sep-2024; Agentforce 2.0 announced Dec-2024.","cited_cells":40,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/salesforce-agentforce--salesforce-com"},{"id":"sandbase-harness--gh-sandbaseai-sandbase-harness","name":"SandBase Harness","url":"https://github.com/sandbaseai/sandbase-harness","section":"AI sandbox & runtime environments","tier":3,"status":"active","last_verified_at":"2026-10-27","type":"Harness","license":"Apache-2.0","latest_release":"v0.3.8 (2026-08-30)","deployment":"Self-hosted only — local-first runtime (local, Docker, Kubernetes or self-hosted worker sandboxes), no hosted control plane","pricing":"searched not found","mcp_support":"yes — MCP toolsets with permission policies/approvals; listed in the official MCP Registry as an MCP bridge","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"sandbaseai/sandbase-harness — ~640 stars, last commit 2026-10","description":"A local-first, self-hosted runtime for persistent AI-agent sessions, sandboxed execution, MCP tools, approvals, audit, and replay. **Claims / pitch:** The public repository documents local, Docker, and Kubernetes sandbox backends; persistent sessions and event streams; MCP tools; skills and credential management; approval gates; audit and replay workflows. These are suggestions for curator verification, not endorsement claims. Traction: Submitted via intake issue #173","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sandbase-harness--gh-sandbaseai-sandbase-harness"},{"id":"scite-ai--scite-ai-2","name":"scite.ai","url":"https://scite.ai/","section":"Use-case-specific agent harnesses","tier":3,"status":"acquired","last_verified_at":"2026-10-28","type":"Citation-supported AI research assistant","license":"","latest_release":"","deployment":"","pricing":"Basic $12/mo billed yearly (250 MCP credits/mo); Pro $40/mo billed yearly (API access, 2,500 MCP credits/mo); org plans by quote","mcp_support":"yes — Scite MCP server connects AI agents to Scite (credit-metered by plan)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2018 by Josh Nicholson (PhD); citation-supported research search — find supporting/contrasting/mentioning citations for a scientific claim. **Acquired by Research Solutions Sep-2023 for $26M**. scite Assistant is the AI-research-agent overlay launched 2023.","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/scite-ai--scite-ai-2"},{"id":"secureframe-ai--secureframe-com","name":"Secureframe AI","url":"https://secureframe.com/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"Compliance automation with Comply AI","license":"","latest_release":"","deployment":"","pricing":"Fundamentals package starting at $7,500/year; other packages by quote","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2020 by Shrav Mehta; the third major compliance-automation platform (with Vanta + Drata). $56M Series B Mar-2023 (Accel + Kleiner Perkins + Base10). Comply AI launched 2024 — control gap analysis, evidence-collection automation.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/secureframe-ai--secureframe-com"},{"id":"sema4-ai--sema4-ai","name":"Sema4.ai","url":"https://sema4.ai/","section":"Multi-agent orchestration platforms","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"Enterprise multi-agent platform (rebrand of Robocorp; Python-based)","license":"Apache 2.0 (Robocorp framework)","latest_release":"v1.6.6 (2025-12-17) — sema4ai-actions; robocorp v3.1.6 (2026-10-18)","deployment":"OSS framework + managed cloud + on-prem enterprise","pricing":"OSS (Robocorp framework) + Sema4.ai Studio + Enterprise cloud (quote)","mcp_support":"yes — Action Server exposes sema4ai.mcp @tool functions at an /mcp endpoint for MCP clients","a2a_support":"","backend_storage":"","llm_lock":"multi-vendor (BYO OpenAI / Anthropic / local)","github":"robocorp/robocorp — ~650 stars, last commit 2026-10; Sema4AI/actions ~140 stars, last commit 2026-04","description":"Sema4.ai is the AI-agent rebrand of Robocorp (RPA / Python automation OSS). Funded by Benchmark, Canvas Ventures, Slow Ventures. Founded 2019 (as Robocorp); rebranded 2024. Positioned as enterprise Python-based agent runtime with strong RPA heritage and governance focus. OSS Robocorp framework remains open-source (Apache 2.0). Distinct from no-code RPA — Sema4.ai is code-first.","cited_cells":33,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sema4-ai--sema4-ai"},{"id":"semgrep-assistant--semgrep-dev","name":"Semgrep Assistant (now Semgrep Multimodal)","url":"https://semgrep.dev/products/semgrep-multimodal/","section":"Use-case-specific agent harnesses","tier":2,"status":"renamed","last_verified_at":"2026-10-28","type":"AI-assisted triage + auto-remediation for Semgrep findings","license":"","latest_release":"","deployment":"","pricing":"Free tier (up to 10 contributors, 60 AI credits); Teams from $30/month per contributor (20 AI credits per developer/month); Enterprise quote","mcp_support":"yes — Semgrep MCP server now ships in the main semgrep binary (standalone semgrep/mcp repo deprecated)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Semgrep's AI layer (Assistant) on top of its OSS rules-based SAST engine — triages findings, suppresses false positives, drafts fixes via PR. Semgrep parent: $59.5M Series C Nov-2022 ($530M val); >100M scans/year reported.","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/semgrep-assistant--semgrep-dev"},{"id":"skyvern--skyvern-com","name":"Skyvern","url":"https://www.skyvern.com/","section":"Computer-use & desktop agents","tier":2,"status":"active","last_verified_at":"2026-10-31","type":"OSS browser-automation agent (Python; LLM-driven)","license":"AGPL-3.0","latest_release":"v1.0.56 (2026-10-14)","deployment":"Both (self-hosted + managed cloud) — Docker/pip self-host + Skyvern Cloud (cloud anti-bot features not in OSS)","pricing":"Cloud usage tiers + self-host (free OSS)","mcp_support":"yes — MCP server so any MCP-capable LLM client can drive Skyvern","a2a_support":"searched not found","backend_storage":"PostgreSQL for workflow state","llm_lock":"","github":"Skyvern-AI/skyvern — ~23.1k stars, last commit 2026-10","description":"Open-source autonomous browser agent that uses computer vision + LLMs to navigate websites. Workflow-based: agents follow recorded plans that adapt to layout changes. Skyvern Inc. raised $4.5M seed (Sep-2024, Felicis lead). Self-hostable; cloud version on skyvern.com.","cited_cells":53,"third_party_cells":4,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/skyvern--skyvern-com"},{"id":"smithery--smithery-ai","name":"Smithery","url":"https://smithery.ai/","section":"MCP gateways & registries","tier":3,"status":"dead","last_verified_at":"2026-10-31","type":"Product","license":"proprietary; CLI AGPL-3.0","latest_release":"last commit 2026-05-31","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"https://github.com/smithery-ai/cli (849★)","description":"Public directory of MCP servers, now part of Arcade.dev. Until 2026-10-31 it was also a connection layer (hosted MCP proxy, Connect, Toolbox, managed credentials, API, CLI and SDKs); those shut down that day, and verified servers' registry pages now list direct MCP URLs.","cited_cells":14,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/smithery--smithery-ai"},{"id":"smol-developer--gh-smol-ai-developer","name":"smol-developer","url":"https://github.com/smol-ai/developer","section":"Agent IDEs & coding harnesses","tier":3,"status":"inactive","last_verified_at":"2026-10-26","type":"OSS minimalist coding agent (smol AI)","license":"MIT","latest_release":"none — no GitHub releases published","deployment":"Self-hosted only — Python library/CLI","pricing":"Free (OSS)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"local files","llm_lock":"","github":"smol-ai/developer — ~12.2k stars, last commit n/a (dormant)","description":"Early (2023) OSS coding agent by Swyx — minimalist single-prompt-to-codebase loop. More artifact-than-product now (subsumed by Cline / Aider / Claude Code) but historically significant — defined the \"smol\" school of single-file coding agents.","cited_cells":42,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/smol-developer--gh-smol-ai-developer"},{"id":"smolagents-hugging-face--gh-huggingface-smolagents","name":"smolagents (Hugging Face)","url":"https://github.com/huggingface/smolagents","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-31","type":"Minimal code-agent framework","license":"Apache-2.0","latest_release":"v1.26.0 (2026-05-29)","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"yes — MCPClient and ToolCollection.from_mcp load tools from stdio or Streamable HTTP MCP servers","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"huggingface/smolagents — ~30k stars, last commit 2026-10","description":"Hugging Face's minimal agent library — emphasises code-execution agents (agent writes Python, runs it) over JSON tool-calling. Library is intentionally ~1k LOC.","cited_cells":22,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/smolagents-hugging-face--gh-huggingface-smolagents"},{"id":"snapattack--snapattack-com","name":"SnapAttack","url":"https://www.splunk.com/en_us/products/enterprise-security.html","section":"Use-case-specific agent harnesses","tier":3,"status":"acquired","last_verified_at":"2026-10-29","type":"Detection-as-code platform with threat-emulation AI","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2021 inside Booz Allen Hamilton; spun out 2022. Detection-as-code platform — threat emulation + auto-generated detections. Adds GenAI threat-content layer 2024. Acquired by Cisco (2025-01-31; announced 2024-12-16) to extend Splunk Enterprise Security; snapattack.com now redirects to Splunk ES.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/snapattack--snapattack-com"},{"id":"snyk-deepcode-ai--snyk-io","name":"Snyk DeepCode AI","url":"https://snyk.io/platform/deepcode-ai/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"AI-assisted code-vulnerability detection + auto-fix","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — Snyk MCP server built into the Snyk CLI (snyk mcp) exposes Snyk scans to MCP clients","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Snyk's AI-assisted code-fix product built on the 2020-acquired DeepCode AI engine. Combines symbolic analysis + multiple AI models for fix generation. Snyk parent: $530M raised; $7.4B val Dec-2022; reported $300M+ ARR.","cited_cells":20,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/snyk-deepcode-ai--snyk-io"},{"id":"sourcegraph-cody-agent--sourcegraph-com","name":"Sourcegraph Cody (agent)","url":"https://sourcegraph.com/cody","section":"Agent IDEs & coding harnesses","tier":1,"status":"archived","last_verified_at":"2026-10-26","type":"Code-intelligence-backed coding assistant + Agentic Chat","license":"","latest_release":"","deployment":"Cloud + on-prem","pricing":"Cody Free/Pro discontinued 2025-07-23; Cody available to Enterprise customers only (contact sales)","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Sourcegraph code-graph + session state","llm_lock":"","github":"sourcegraph/cody-public-snapshot — ~3.8k stars, archived 2025-08-01 (development moved private)","description":"Sourcegraph's coding assistant — IDE plugin (VS Code, JetBrains) plus web. Distinguishes itself with Sourcegraph's code-search index as the context provider (cross-repo, codebase-wide retrieval). Agentic chat added 2024; runs Claude / GPT / Gemini.","cited_cells":54,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sourcegraph-cody-agent--sourcegraph-com"},{"id":"specter-ops-bloodhound-enterprise--specterops-io","name":"Specter Ops BloodHound Enterprise","url":"https://specterops.io/platform/bloodhound-enterprise/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Attack-path management + AI analysis (BloodHound Enterprise)","license":"BloodHound OSS Apache-2.0 (Enterprise is commercial)","latest_release":"BloodHound CE v9.9.0 (2026-10-26)","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"SpecterOps/BloodHound — ~3.5k stars, last commit 2026-10","description":"Maker of OSS BloodHound (the Active-Directory graph tool); BloodHound Enterprise is the productised attack-path management platform. $33M Series A Aug-2024 (Insight Partners). Adds AI for attack-path prioritisation 2024.","cited_cells":21,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/specter-ops-bloodhound-enterprise--specterops-io"},{"id":"speechmatics-flow--speechmatics-com","name":"Speechmatics Flow","url":"https://www.speechmatics.com/voice-agents","section":"Voice agent platforms","tier":2,"status":"deprecated","last_verified_at":"2026-10-29","type":"Conversational voice-agent platform (Speechmatics)","license":"","latest_release":"","deployment":"Cloud + on-prem / private cloud","pricing":"Enterprise / per-minute","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Cloud or on-prem; caller-controlled in on-prem","llm_lock":"","github":"github.com/speechmatics (SDKs)","description":"Speechmatics (UK; STT leader) launched Flow Q4 2024 — conversational voice-agent platform composed on Speechmatics STT + caller LLM. Speechmatics raised $62M Series B (2022); enterprise + media customers. UK / EU data-residency lead. As of 2026-10 the Flow pages and docs redirect to Agent STT, a speech-to-text API for voice agents (Linden model, from $0.30/hour) used via LiveKit, Pipecat or the API; Flow itself is no longer listed.","cited_cells":42,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/speechmatics-flow--speechmatics-com"},{"id":"stackblitz-webcontainers--webcontainers-io","name":"StackBlitz WebContainers","url":"https://webcontainers.io/","section":"AI sandbox & runtime environments","tier":3,"status":"stale","last_verified_at":"2026-10-27","type":"Browser-native Node.js runtime (WASM) — substrate for Bolt.new and AI agents","license":"","latest_release":"v1.6.4 (2026-04-14) — @webcontainer/api","deployment":"Browser-native (client-side); no cloud compute required","pricing":"Free for prototypes/POCs; commercial license required for production for-profit use (enterprise pricing via sales)","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"stackblitz/webcontainer-core — ~4.7k stars, last commit 2025-04 (public issue tracker and docs only; the runtime source is not published)","description":"StackBlitz's WebContainers technology — browser-native Node.js runtime running fully client-side via WASM. Powers Bolt.new (already in catalog) plus many browser-based AI dev experiences. Founded 2017 by Eric Simons + Albert Pai. $7M Series A 2022. Distinct from server-side sandboxes (e2b / Modal) by running entirely in-browser — zero cloud-execution latency.","cited_cells":31,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/stackblitz-webcontainers--webcontainers-io"},{"id":"stagehand--stagehand-dev","name":"Stagehand","url":"https://www.stagehand.dev/","section":"Computer-use & desktop agents","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"OSS browser-automation framework (Browserbase OSS)","license":"MIT","latest_release":"v3.7.3 (2026-08-28) — @browserbasehq/stagehand","deployment":"Both (self-hosted + managed cloud) — library runs locally; Browserbase cloud browsers optional","pricing":"OSS free; Browserbase Cloud handles runtime","mcp_support":"yes — hosted Browserbase MCP server exposes navigate/act/observe/extract to any MCP client","a2a_support":"searched not found","backend_storage":"Local Playwright state; Browserbase-managed when cloud-hosted","llm_lock":"","github":"browserbase/stagehand — ~25.5k stars, last commit 2026-08+","description":"Open-source browser-automation framework by Browserbase (TypeScript core plus Python and Go SDKs). Mixes Playwright-style code with natural-language act/extract/observe; pairs with Browserbase Cloud.","cited_cells":49,"third_party_cells":7,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/stagehand--stagehand-dev"},{"id":"stanford-storm--storm-genie-stanford-edu","name":"Stanford STORM","url":"https://storm.genie.stanford.edu/","section":"Use-case-specific agent harnesses","tier":2,"status":"stale","last_verified_at":"2026-10-28","type":"Wikipedia-style article-writing agent (OSS)","license":"MIT","latest_release":"knowledge-storm 1.1.1 (2025-09-29)","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"stanford-oval/storm — ~31.7k stars, last commit 2025-09","description":"Stanford NLP's STORM (Synthesis of Topic Outline through Retrieval and Multi-perspective question-asking) — generates Wikipedia-style articles from a topic prompt. NAACL 2024 paper (arXiv 2402.14207). MIT OSS; Apache demo at storm.genie.stanford.edu.","cited_cells":22,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/stanford-storm--storm-genie-stanford-edu"},{"id":"steamship--steamship-com","name":"Steamship","url":"https://www.steamship.com/","section":"Multi-agent orchestration platforms","tier":3,"status":"archived","last_verified_at":"2026-10-29","type":"Multi-agent deployment / hosting platform (LangChain-like infra)","license":"MIT (python-client SDK); hosted platform proprietary","latest_release":"v2.17.34 (2024-01-24) — steamship Python SDK","deployment":"","pricing":"Free + paid tiers (per-call + storage)","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"multi-vendor (BYO)","github":"steamship-core/python-client — ~320 stars, last commit 2024-02","description":"YC W21 startup providing managed hosting + deployment for LLM agents — 'one-click deploy' for LangChain / agent code. Founded by Ted Benson (ex-Google Brain). Pre-seed + seed funded YC + Twin Ventures. Positioned as Heroku for AI agents — but the agent-platform space crowded post-2023, and Steamship's commercial momentum has slowed vs Vercel AI / Modal / Bedrock. As of 2026-10-29 www.steamship.com returns 404 and docs.steamship.com serves an expired TLS certificate; the last Python SDK release was v2.17.34 (2024-01-24); the python-client repo is not archived.","cited_cells":26,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/steamship--steamship-com"},{"id":"steel-dev--steel-dev","name":"Steel.dev","url":"https://steel.dev/","section":"Computer-use & desktop agents","tier":2,"status":"active","last_verified_at":"2026-10-26","type":"OSS + cloud browser-infrastructure for AI agents","license":"Apache-2.0","latest_release":"v0.5.4-beta (2026-08-25)","deployment":"Both (self-hosted + managed cloud) — Docker self-host (steel-browser) + Steel Cloud","pricing":"OSS free; Cloud per-session-hour tiers","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Chromium fleet state; Postgres for control plane","llm_lock":"","github":"steel-dev/steel-browser — ~7.6k stars, last commit 2026-08","description":"Open-source browser API ('the browser for agents') — Chromium fleet with stealth mode, session recordings, CDP. OSS repo + managed cloud. Compatible with Playwright / Puppeteer. Distinguishes itself as the 'OSS Browserbase'.","cited_cells":45,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/steel-dev--steel-dev"},{"id":"strands-agents-aws--strandsagents-com","name":"Strands Agents (AWS)","url":"https://strandsagents.com/","section":"Agent frameworks (no first-party memory layer)","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"AWS open agent framework","license":"Apache-2.0","latest_release":"v1.62.0 (2026-10-21) — Python; TypeScript @strands-agents/sdk v1.22.0 (2026-10-21)","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"yes — MCPClient exposes MCP server tools to agents (Python and TypeScript)","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"strands-agents/harness-sdk (formerly sdk-python) — ~9k stars, last commit 2026-10","description":"AWS-released open-source agent SDK, announced 2025-05-16; model-driven approach in which the model plans next steps and tool use. AWS teams including Amazon Q Developer, AWS Glue and VPC Reachability Analyzer use it in production.","cited_cells":18,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/strands-agents-aws--strandsagents-com"},{"id":"stytch-connected-apps--stytch-com","name":"Stytch Connected Apps","url":"https://stytch.com/connected-apps","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"Turns an app into an OAuth 2.0/OIDC identity provider so AI agents and MCP clients can be authorized against it. It handles token issuance, validation and revocation with user-controlled, token-based permissions.","cited_cells":10,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/stytch-connected-apps--stytch-com"},{"id":"synthflow--synthflow-ai","name":"Synthflow","url":"https://synthflow.ai/","section":"Voice agent platforms","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"No-code voice-agent builder (telephony)","license":"","latest_release":"","deployment":"Cloud-managed (EU + US regions)","pricing":"Enterprise contracts from $30,000/yr, scoped by call volume, concurrency, telephony and integrations","mcp_support":"yes — Synthflow MCP server for managing agents, calls and knowledge bases from MCP clients","a2a_support":"searched not found","backend_storage":"Call state in Synthflow-managed DB","llm_lock":"","github":"","description":"No-code voice-AI platform — drag-and-drop call-flow builder targeted at non-developers. Berlin-based; raised $7.4M Series A Sep-2024 (Singular). Distinguishes itself from Vapi/Retell with visual call-flow builder rather than code-first SDK.","cited_cells":41,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/synthflow--synthflow-ai"},{"id":"sysdig-sage--sysdig-com","name":"Sysdig Sage (now Sysdig GenAI Assistant)","url":"https://www.sysdig.com/products/genai-assistant","section":"Use-case-specific agent harnesses","tier":2,"status":"renamed","last_verified_at":"2026-10-28","type":"Cloud-security AIOps agent for runtime/CNAPP","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — official Sysdig MCP Server (sysdiglabs/sysdig-mcp-server)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Sysdig's GenAI-powered cloud-security agent — runtime workload protection + CNAPP findings explained. Launched May-2024. Sysdig parent: $350M Series G 2022 ($2.5B val); Permira-led 2023 round.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/sysdig-sage--sysdig-com"},{"id":"temporal--temporal-io","name":"Temporal","url":"https://temporal.io/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-27","type":"Durable execution platform","license":"MIT","latest_release":"v1.32.1 (2026-10-08) — server; Python SDK v1.34.0 (2026-09-30)","deployment":"Both (self-hosted + managed cloud) — Temporal Cloud or self-hosted Temporal server","pricing":"Temporal Cloud: Pay-As-You-Go from USD 50 per million actions (volume down to USD 25/M) plus storage; Business from USD 500/mo; Enterprise and Mission Critical custom","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"temporalio/temporal — ~24k stars, last commit 2026-10","description":"Durable-execution platform — Workflows-as-code with crash safety. Used as agent-orchestration backbone at Stripe, Snap, Coinbase, OpenAI Stargate.","cited_cells":21,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/temporal--temporal-io"},{"id":"tines--tines-com","name":"Tines","url":"https://www.tines.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"No-code workflow automation + AI agents for security","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"yes — MCP and AI client management through the Tines AI gateway","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Dublin-founded 2018; no-code automation initially for SOC analysts. $50M Series B Dec-2023 (Felicis + Accel + CrowdStrike's Falcon Fund). AI Agent mode added 2024; Tines Workbench gives analysts an LLM copilot atop their workflows.","cited_cells":21,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/tines--tines-com"},{"id":"tonkean-legalworks--tonkean-com","name":"Tonkean LegalWorks","url":"https://www.tonkean.com/solutions/legal-works","section":"Use-case-specific agent harnesses","tier":3,"status":"acquired","last_verified_at":"2026-10-29","type":"Legal-ops orchestration platform with AI agents","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Tonkean is a workflow-orchestration platform; LegalWorks is the legal-ops vertical with AI agents for intake triage, contract routing, and SLA management. Tonkean: $50M Series C Sep-2022 (Insight + Lightspeed + Accel; $500M+ val). Acquired by Coupa (2026), per the banner on Tonkean's homepage; LegalWorks remains on sale.","cited_cells":17,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/tonkean-legalworks--tonkean-com"},{"id":"toplyne--toplyne-io","name":"Toplyne","url":"https://www.toplyne.io/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"PLG-revenue ML / AI agent platform","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2021; PLG-revenue intelligence — predicts which free users will convert, sales-ready signals. $17.5M Series A May-2023 (Tiger Global + Sequoia + Together Fund). Pivoted to AI-agent positioning 2024.","cited_cells":14,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/toplyne--toplyne-io"},{"id":"torq-hypersoc--torq-io","name":"Torq HyperSOC","url":"https://torq.io/ai-soc-platform/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Hyperautomated SOC platform with agent workflows","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Torq's HyperSOC is the AI-augmented offering of its hyperautomation platform (no-code security workflows + LLM agents). Torq parent: $70M Series C Apr-2024 (Evolution + Bessemer + Notable; >$300M total raised). Founded by Ofer Smadari (ex-Luminate / Symantec acq).","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/torq-hypersoc--torq-io"},{"id":"trade-ideas-holly-ai--trade-ideas-com","name":"Trade Ideas Holly AI","url":"https://www.trade-ideas.com/holly/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"AI trading-idea generation agent","license":"","latest_release":"","deployment":"","pricing":"Standard $89/mo billed annually ($1,068/yr; ~$127 month-to-month); Premium with AI signals $178/mo billed annually ($2,136/yr; ~$254 month-to-month)","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Holly AI is the trading-idea generation agent inside the Trade Ideas platform (founded 2003). Holly back-tests millions of strategies overnight + surfaces 'tradeable ideas' for retail/prosumer traders. Bootstrapped; long-running niche product pre-LLM wave.","cited_cells":16,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/trade-ideas-holly-ai--trade-ideas-com"},{"id":"trigger-dev--trigger-dev","name":"Trigger.dev","url":"https://trigger.dev/","section":"Agent frameworks (no first-party memory layer)","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"Long-running JS jobs","license":"Apache-2.0","latest_release":"v4.8.1 (2026-10-23)","deployment":"Both (self-hosted + managed cloud) — Trigger.dev Cloud or self-hosted (Apache-2.0)","pricing":"Free USD 0/mo; Hobby USD 10/mo; Pro USD 50/mo; Enterprise custom","mcp_support":"yes — Trigger.dev MCP server lets AI assistants search docs, trigger and monitor runs, deploy, and query data","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"triggerdotdev/trigger.dev — ~17k stars, last commit 2026-10","description":"Open-source JS/TS background-jobs platform — long-running, retries, observability. Trigger.dev v3 (2024) added 'tasks' abstraction for agent workflows.","cited_cells":24,"third_party_cells":2,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/trigger-dev--trigger-dev"},{"id":"trustcloud--trustcloud-ai","name":"TrustCloud","url":"https://www.trustcloud.ai/","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-28","type":"GRC automation + trust center platform","license":"","latest_release":"","deployment":"","pricing":"","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2021 by Sravish Sridhar (ex-Kinvey founder); GRC automation + AI trust center. $25M Series A Jun-2023 (Felicis + Cowboy + Cota Capital). Differentiates with cyber-insurance + 'trust center' as a sales-enablement angle.","cited_cells":18,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/trustcloud--trustcloud-ai"},{"id":"ui-tars--gh-bytedance-ui-tars","name":"UI-TARS","url":"https://github.com/bytedance/UI-TARS","section":"Computer-use & desktop agents","tier":2,"status":"active","last_verified_at":"2026-10-31","type":"OSS GUI-agent foundation model + desktop app (ByteDance)","license":"Apache-2.0","latest_release":"UI-TARS-desktop / Agent TARS v0.3.1 (2026-10-09); UI-TARS-2 announced 2025-09-04; latest open weights UI-TARS-1.5-7B (2025-04-16)","deployment":"Self-hosted only — open weights (Hugging Face) + UI-TARS-desktop / Agent TARS app","pricing":"OSS weights free","mcp_support":"yes — via Agent TARS (UI-TARS-desktop): MCP-based kernel that mounts MCP servers","a2a_support":"searched not found","backend_storage":"Caller-side; no built-in storage","llm_lock":"","github":"bytedance/UI-TARS-desktop — ~39.5k stars, last commit 2026-10 (v0.3.1, 2026-10-09); model repo bytedance/UI-TARS — ~11.7k stars, last commit 2025-09","description":"ByteDance Seed's open-source GUI-agent foundation model — released Jan 2025; trained end-to-end on screenshot → action pairs. Comes with UI-TARS-Desktop (Electron app) that runs the model against the user's screen. SOTA on OSWorld at release; weights on HuggingFace.","cited_cells":48,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/ui-tars--gh-bytedance-ui-tars"},{"id":"v0-vercel--v0-app","name":"v0 (Vercel)","url":"https://v0.app","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Vercel's AI app builder — prompt-to-Next.js component/app","license":"","latest_release":"","deployment":"Cloud","pricing":"Free + Pro ($20/mo) + Team","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Vercel-hosted","llm_lock":"","github":"vercel/v0-sdk — ~510 stars (Apache-2.0 SDK for v0 Platform API), last commit n/a; v0 itself closed source","description":"Vercel's AI product (formerly v0.dev) that generates React/Next.js components and full apps from natural-language prompts. Tight integration with Vercel deploy; uses Vercel-hosted models (multi-LLM). Differentiator: best-in-class shadcn/ui generations and Vercel-deploy story.","cited_cells":60,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/v0-vercel--v0-app"},{"id":"vanta--vanta-com","name":"Vanta","url":"https://www.vanta.com/","section":"Use-case-specific agent harnesses","tier":1,"status":"active","last_verified_at":"2026-10-28","type":"Compliance automation platform with AI agent","license":"","latest_release":"","deployment":"Managed-only — SaaS","pricing":"Quote-based tiers (Essentials, Plus, Professional, Enterprise); no list prices published","mcp_support":"yes — Vanta hosted MCP server (the earlier OSS VantaInc/vanta-mcp-server is archived) plus an official Claude Code plugin","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Founded 2018; the largest compliance-automation platform by valuation/headline. $150M Series C Jul-2024 ($2.45B val; Sequoia + Atlassian Ventures + CrowdStrike Falcon Fund). Vanta AI launched 2024 — auto-evidence-collection, control mapping, vendor-review.","cited_cells":24,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/vanta--vanta-com"},{"id":"vapi--vapi-ai","name":"Vapi","url":"https://vapi.ai/","section":"Voice agent platforms","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Developer platform for AI voice agents (programmable telephony)","license":"","latest_release":"","deployment":"Cloud-managed; private deployments on Enterprise tier","pricing":"Per-minute usage ($0.05/min base + provider passthrough)","mcp_support":"yes — Vapi MCP server (remote https://mcp.vapi.ai/mcp, Streamable HTTP; VapiAI/mcp-server, MIT); assistants can also call MCP tools","a2a_support":"searched not found","backend_storage":"Call state in Vapi-managed DB; transcripts retained per config","llm_lock":"","github":"github.com/VapiAI (SDKs only)","description":"Voice-AI developer platform — STT + LLM + TTS pipelines wired to telephony (Twilio / SIP). Used to build outbound + inbound phone agents at scale. Raised $20M Series A from Bessemer + Y Combinator (Dec 2024) at $130M valuation; revenue reported >$10M ARR by Q1 2025.","cited_cells":46,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/vapi--vapi-ai"},{"id":"vercel-ai-sdk--sdk-vercel-ai","name":"Vercel AI SDK","url":"https://ai-sdk.dev/","section":"Agent frameworks (no first-party memory layer)","tier":1,"status":"active","last_verified_at":"2026-10-29","type":"TypeScript LLM toolkit","license":"Apache-2.0","latest_release":"v7.0.154 (2026-10-26)","deployment":"Self-hosted only — library","pricing":"searched not found","mcp_support":"yes — createMCPClient from @ai-sdk/mcp (HTTP, SSE, stdio) converts MCP server tools for AI SDK calls","a2a_support":"searched not found","backend_storage":"","llm_lock":"searched not found","github":"vercel/ai — ~28k stars, last commit 2026-10","description":"Vercel's TypeScript LLM SDK — streaming, tool calls, structured outputs, agents. Dominant framework for Next.js LLM apps.","cited_cells":22,"third_party_cells":3,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/vercel-ai-sdk--sdk-vercel-ai"},{"id":"vonage-ai-studio--vonage-com","name":"Vonage AI Studio","url":"https://www.vonage.com/communications-apis/ai-studio/","section":"Voice agent platforms","tier":2,"status":"acquired","last_verified_at":"2026-10-27","type":"Enterprise CPaaS voice-agent builder (Vonage / Ericsson)","license":"","latest_release":"","deployment":"Cloud-managed","pricing":"Tiered + per-minute / per-message","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"Vonage-managed cloud (sessions + flow state)","llm_lock":"","github":"github.com/Vonage (SDKs)","description":"Vonage's AI Studio — visual conversational-agent designer that runs on Vonage CPaaS (SMS / Voice / WhatsApp). Vonage acquired by Ericsson 2022 ($6.2B); AI Studio is the conversational AI layer of the broader CPaaS. Enterprise focus.","cited_cells":40,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/vonage-ai-studio--vonage-com"},{"id":"windsurf-codeium-openai--windsurf-com","name":"Windsurf (now Devin Desktop)","url":"https://devin.ai/desktop","section":"Agent IDEs & coding harnesses","tier":1,"status":"acquired","last_verified_at":"2026-10-29","type":"Agentic IDE — Cascade Flow + Memories (acquired by OpenAI 2025)","license":"","latest_release":"","deployment":"Cloud (desktop client) + on-prem (enterprise Codeium)","pricing":"Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo plus $40/mo per full seat; Enterprise custom","mcp_support":"yes — Cascade MCP configuration in Devin Desktop (formerly Windsurf)","a2a_support":"searched not found","backend_storage":"local workspace + cloud session state","llm_lock":"","github":"","description":"Codeium-built agentic IDE (VS Code fork); flagship was Cascade, a planning + execution agent that maintains \"Flows\" and \"Memories\" as durable artifacts. Reported acquired by OpenAI in May 2025 for ~$3B (later partly unwound; Google paid ~$2.4B for an inverse-license + key staff; the remaining IDE/IP went to Cognition in July 2025). Renamed Devin Desktop by Cognition on 2026-06-02, with Devin Local replacing Cascade as the primary local agent. The legacy Cascade agent stayed available through 2026-07-01; windsurf.com now redirects to devin.ai/desktop.","cited_cells":57,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/windsurf-codeium-openai--windsurf-com"},{"id":"workato-ai-workflow-bot-builder--workato-com","name":"Workato AI (Workflow Bot Builder)","url":"https://www.workato.com/ai","section":"AI sandbox & runtime environments","tier":2,"status":"active","last_verified_at":"2026-10-27","type":"Enterprise iPaaS with AI-agent / workflow-sandbox tier (Workato AI)","license":"","latest_release":"","deployment":"Managed cloud (SaaS only)","pricing":"Enterprise (quote-only); per-recipe + per-task pricing","mcp_support":"yes — Workato Enterprise MCP (MCP gateway and registry, can proxy third-party MCP servers) plus App and Data MCP Servers","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Workato is the enterprise iPaaS (integration platform) leader — $200M+ ARR, $5.7B valuation 2021. 2023-24 launched Workato AI / Workbot AI with AI-agent workflow sandbox capability inside its automation runtime. Used by Slack-bot / automation customers for AI-augmented workflows. Distinct from pure agent frameworks (CrewAI / LangGraph) by being deeply enterprise-iPaaS-anchored.","cited_cells":29,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/workato-ai-workflow-bot-builder--workato-com"},{"id":"workos-authkit-for-mcp--workos-com","name":"WorkOS AuthKit for MCP","url":"https://workos.com/mcp","section":"Agent identity & auth","tier":3,"status":"active","last_verified_at":"2026-10-29","type":"Product","license":"proprietary","latest_release":"searched not found","deployment":"searched not found","pricing":"searched not found","mcp_support":"searched not found","a2a_support":"searched not found","backend_storage":"searched not found","llm_lock":"searched not found","github":"","description":"WorkOS AuthKit acts as an OAuth 2.1 authorization server for MCP servers, giving AI agents scoped access to an app with PKCE, scopes and tool permissions. WorkOS Connect can provide only the MCP OAuth flows in front of an existing user system.","cited_cells":9,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/workos-authkit-for-mcp--workos-com"},{"id":"xbow--xbow-com","name":"XBOW","url":"https://xbow.com/","section":"Use-case-specific agent harnesses","tier":3,"status":"active","last_verified_at":"2026-10-28","type":"Autonomous AI pentester (web app exploitation agent)","license":"","latest_release":"","deployment":"","pricing":"Usage-based, scoped to environment (request a quote); available via AWS, Google, Oracle and Microsoft marketplaces","mcp_support":"","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"Sequoia-led $20M seed (Jun-2024); founded by Oege de Moor (Semmle / GitHub CodeQL founder). Autonomous offensive-security agent that finds and exploits web vulns end-to-end. Topped HackerOne leaderboard in 2025 (first AI on the leaderboard).","cited_cells":19,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/xbow--xbow-com"},{"id":"you-com-research--you-com","name":"You.com Research","url":"https://you.com/research","section":"Use-case-specific agent harnesses","tier":2,"status":"active","last_verified_at":"2026-10-29","type":"Web-research AI agent","license":"","latest_release":"","deployment":"","pricing":"Research API usage-based: Lite $12, Standard $50, Deep $100, Exhaustive $450 per 1k calls (plus a Frontier tier)","mcp_support":"yes — You.com MCP server (live search via MCP; up to 100 free queries/day without an API key)","a2a_support":"","backend_storage":"","llm_lock":"","github":"","description":"You.com's research-agent mode — multi-step web research + synthesis. You.com parent: $99M Series B Aug-2024 ($700M val; Georgian + NEA + Salesforce Ventures). Founded by Richard Socher (ex-Salesforce Chief Scientist). As of Oct 2026 You.com positions itself as search and inference APIs for AI, and research is offered as a Research API; the consumer /research page now requires sign-in.","cited_cells":21,"third_party_cells":0,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/you-com-research--you-com"},{"id":"zed-agentic-editing--zed-dev","name":"Zed (Agentic Editing)","url":"https://zed.dev","section":"Agent IDEs & coding harnesses","tier":1,"status":"active","last_verified_at":"2026-10-26","type":"Native Rust editor with Agentic Editing + Edit Predictions","license":"GPL-3.0-or-later (primary), with Apache-2.0 components where marked","latest_release":"v1.15.0 (2026-08-12)","deployment":"Self-hosted only — native desktop editor; AI via Zed-hosted models, BYO API keys or local models","pricing":"Free + paid","mcp_support":"yes — MCP client ('context servers': tools + prompts, local or remote, via settings or extensions)","a2a_support":"searched not found","backend_storage":"local workspace + Threads files","llm_lock":"","github":"zed-industries/zed — ~89k stars, last commit 2026-08+","description":"Native (Rust) collaborative code editor by Zed Industries (founded by the Atom + Tree-sitter team). Added Agentic Editing in 2024 — multi-step coding agent driven by Claude or local models; .rules markdown + Threads form the memory layer. GPU-accelerated rendering and CRDT collaboration are core differentiators vs VS Code forks.","cited_cells":47,"third_party_cells":1,"page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/zed-agentic-editing--zed-dev"}]}