| System | Status | Tier | Section | What it is | MCP support | Deployment | Pricing | License | Latest release | GitHub | Verified |
|---|---|---|---|---|---|---|---|---|---|---|---|
Active | T1 | File-backed / editor paradigms | Cross-tool open standard ↗ 2 | · | · | · | MIT ↗ ● | · | agentsmd/agents.md — ~25k stars ↗ ● | 2026-10-22 | |
Deprecated | T1 | Agent IDEs & coding harnesses | AWS-hosted developer AI agent + IDE plugins ↗ 2 | yes — MCP support in Q Developer agentic coding (carried over to successor Kiro per AWS) ↗ 2 | Managed-only — AWS-hosted service via IDE plugins, AWS Console and CLI ↗ 2 | Free tier (50 agentic requests/mo); Pro $19/user/mo — new subscriptions closed from 2026-05-15 ↗ 2 | · | · | · | 2026-10-31 | |
Acquired | T1 | Coding-agent memory | Real-time semantic Context Engine + curated Agent Memory ↗ 2 | yes — Augment Agent is an MCP client (Easy MCP, settings panel, JSON import) ↗ 2 | Both ↗ 2 | Standard $20/mo (incl. $20 usage, up to 50 seats); Business $100/mo (incl. $100 usage); Enterprise custom ↗ 2 | · | · | · | 2026-10-29 | |
Inactive | T1 | Agent IDEs & coding harnesses | Browser-only AI app builder (StackBlitz WebContainer) ↗ 2 | yes — client: connect MCP servers so Bolt can use external apps/data in chat ↗ 2 | Managed-only — browser-based (StackBlitz WebContainers); apps hosted on Bolt ↗ 2 | Free (1M tokens/mo, 300K/day cap); Pro $25/mo (10M tokens); Teams $30/member/mo; Enterprise custom ↗ 2 | · | · | stackblitz/bolt.new — ~16.6k stars, last commit 2024-12 (open-source repo, not archived) ↗ ● | 2026-10-28 | |
Active | T1 | Agent IDEs & coding harnesses | OpenAI's ChatGPT-integrated cloud coding agent ↗ 2 | Managed-only — OpenAI-hosted sandboxed cloud environments, via ChatGPT web/app (chatgpt.com/codex), IDE extension and CLI ↗ ● | 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 ↗ 2 | · | · | · | 2026-10-26 | ||
Active | T1 | Agent IDEs & coding harnesses | Terminal-native agentic coding harness ↗ 2 | yes — MCP client (claude mcp add; stdio and HTTP servers) ↗ 2 | Both (self-hosted + managed cloud) — local CLI/IDE/desktop client plus cloud sessions on web; models via Anthropic API (or Bedrock/Vertex) ↗ 2 | 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 ↗ 2 | proprietary — © Anthropic PBC, use subject to Anthropic Commercial Terms (repo public, not OSS) ↗ ● | v2.1.310 (2026-10-23) ↗ 2 | anthropics/claude-code — ~153k stars, last commit 2026-10 ↗ ● | 2026-10-28 | |
Active | T1 | Claude Code memory mechanisms | Per-project file directory ↗ 2 | native (first-party) — Claude Code consumes MCP ↗ 2 | · | · | · | · | · | 2026-10-22 | |
Active | T1 | Claude Code memory mechanisms | Episodic / session-log compression ↗ ● | native (first-party) ↗ ● | local — SQLite + FTS5 per project; optional Chroma vector; no cloud ↗ ● | Open-source engine free (Apache-2.0, local memory); CMEM Pro hosted observation + cloud sync + private MCP recall: Pro $30/mo, Heavy $70/mo, CMEM Max $100/mo (with billed overage), 30-day free trial; TeamBrain team pricing not announced (pilot) ↗ 2 | Apache-2.0 ↗ ● | v15.0.1 (2026-10-20) ↗ ● | thedotmack/claude-mem — ~104k stars, last commit 2026-10 ↗ 2 | 2026-10-29 | |
Active | T1 | File-backed / editor paradigms | Git-backed persistent instructions ↗ 2 | · | · | · | · | · | · | 2026-10-22 | |
Active | T1 | Claude Code memory mechanisms | Tree-sitter knowledge-graph MCP for code ↗ ● | native (first-party MCP server) ↗ ● | Local — single static binary (macOS arm64/amd64; Linux arm64/amd64; Windows amd64) ↗ ● | free / open source (MIT); no paid tier ↗ ● | MIT ↗ ● | v0.11.0 (2026-09-15) ↗ ● | DeusData/codebase-memory-mcp — ~43.3k stars, last release 2026-09 ↗ ● | 2026-10-22 | |
Active | T1 | Agent IDEs & coding harnesses | Devin successor — autonomous coding agent + spec-mode (cross-listing) ↗ 2 | yes — MCP marketplace plus custom MCP servers (STDIO and remote) configurable in Devin; Devin also ships its own Devin MCP server ↗ 2 | Managed-only — Cognition cloud agents plus Devin Desktop and CLI; enterprise plan offers a dedicated deployment option ↗ 2 | Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo plus $40/mo per full seat; Enterprise custom ↗ 2 | · | Devin release notes update (2026-10-26) ↗ 2 | · | 2026-10-29 | |
Acquired | T1 | Agent IDEs & coding harnesses | Agentic IDE; Agent Mode + Background Agents (VS Code fork) ↗ 2 | yes — install and manage MCP servers in Cursor (editor and CLI) ↗ 2 | Managed-only — desktop app backed by vendor cloud; Agent SDK agents can also run as a Node process on own infrastructure ↗ 2 | 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 ↗ 2 | · | Agent SDK (2026-10-20) ↗ 2 | · | 2026-10-27 | |
Active | T1 | File-backed / editor paradigms | IDE-embedded code memory ↗ 2 | · | · | · | · | · | · | 2026-10-22 | |
Active | T1 | Coding-agent memory | Server-side Knowledge + auto-Repo Knowledge ↗ 2 | via official adapter — Devin supports MCP servers ↗ 2 | Both ↗ 2 | Free $0; Pro $20/mo; Max $200/mo; Teams $80/mo; Enterprise custom ↗ 2 | · | · | · | 2026-10-29 | |
Active | T1 | AI sandbox & runtime environments | Code-execution sandbox infrastructure for AI agents (firecracker microVMs) ↗ 2 | native (MCP server for sandbox tools) ↗ 2 | Both (self-hosted + managed cloud) — E2B Cloud; open-source Apache-2.0 runtime (e2b-dev/infra) can be self-hosted; enterprise BYOC ↗ ● | 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 ↗ 2 | Apache-2.0 ↗ ● | v2.61.0 (2026-10-26) ↗ 2 | e2b-dev/E2B — ~15k stars, last commit 2026-10 ↗ ● | 2026-10-27 | |
Active | T1 | Agent IDEs & coding harnesses | IDE Copilot extension — chat, completions, Agent Mode ↗ ● | yes — client: custom MCP servers in agent mode/cloud agent; admins can allow-list MCP servers ↗ ● | Managed-only — GitHub-hosted service via IDE extensions, Copilot CLI and github.com cloud agent ↗ ● | Free $0 (2,000 completions/mo); Pro $10/mo; Pro+ $39/mo; Max $100/mo; Business $19/user/mo; Enterprise $39/user/mo ↗ ● | · | · | · | 2026-10-26 | |
Active | T1 | File-backed / editor paradigms | .github/copilot-instructions.md + path-scoped ↗ 2 | · | not applicable — GitHub-hosted; no separate deployment ↗ 2 | not applicable — file pattern included in GitHub Copilot subscription ($10/mo individual; $19/mo business) ↗ ● | · | · | not applicable — docs feature, no GitHub repo ↗ 2 | 2026-10-22 | |
Archived | T1 | Agent IDEs & coding harnesses | Agentic IDE — GitHub-hosted plan/code/test workspace ↗ 2 | MCP support added 2025 (Copilot Agent Mode) ↗ 2 | Managed-only — GitHub-hosted (technical preview ended; discontinued) ↗ ● | Discontinued — successor features (Copilot cloud agent) in Copilot Pro $10/mo, Business $19/user/mo, Enterprise $39/user/mo ↗ ● | · | · | githubnext/copilot-workspace-user-manual — archived 2025-09-02 (product closed source) ↗ ● | 2026-10-26 | |
Active | T1 | Claude Code memory mechanisms | Temporal KG with bi-temporal edges ↗ 2 | native (first-party) ↗ ● | cloud (Zep managed) or self-hosted via Graphiti OSS + Neo4j/local graph DB ↗ 2 | free tier: 2500 messages/mo + 2.5MB graph data; paid: $1.25/1000 messages + $2.50/MB extra; Enterprise custom ↗ 2 | Apache-2.0 ↗ ● | v0.31.2 (2026-10-20) ↗ 2 | getzep/graphiti — ~31.9k stars, last commit 2026-10 ↗ ● | 2026-10-22 | |
Active | T1 | Agent IDEs & coding harnesses | IDE AI assistant — chat, completions, AI actions (JetBrains) ↗ 2 | yes — MCP server built into all IntelliJ-based IDEs since 2025.2 (standalone mcp-jetbrains deprecated) ↗ ● | IDE plugin (cloud LLM by default; offline/self-host options) ↗ 2 | $8.33/mo Personal / $16.50/mo Business AI add-on ↗ 2 | · | · | · | 2026-10-26 | |
Active | T1 | Agent IDEs & coding harnesses | Agentic IDE; spec-driven dev (Requirements → Design → Tasks) ↗ 2 | yes — MCP client in IDE and CLI (CLI 2.34.0 added MCP elicitation) ↗ 2 | Managed-only — desktop IDE (Code OSS fork) and CLI run locally; agent/model backend AWS-hosted; no self-host ↗ 2 | 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 ↗ 2 | · | v1.4.26 (2026-10-22) IDE; Kiro CLI v2.34.0 (2026-10-23) ↗ 2 | · | 2026-10-26 | |
Active | T1 | Agent IDEs & coding harnesses | AI app builder — prompt-to-full-stack app (cross-listing) ↗ 2 | yes — chat connectors connect external tools to Lovable via MCP servers ↗ 2 | Cloud ↗ 2 | Free + Pro ($25/mo) + Teams ($50/mo) ↗ 2 | · | · | · | 2026-10-27 | |
Archived | T1 | Claude Code memory mechanisms | Hybrid vector + graph via cloud API ↗ ● | native (first-party) ↗ ● | superseded — use Mem0's hosted MCP endpoint (mcp.mem0.ai/mcp) or the mem0-mcp-server PyPI package ↗ ● | free tier (Hobby: 10K memories 1K retrieval/mo); Starter $19/mo; Pro $249/mo (graph memory included); Enterprise custom ↗ 2 | Apache-2.0 ↗ ● | mem0ai/mem0-mcp — ~658 stars, archived 2026-03-24 ↗ ● | 2026-10-29 | ||
Active | T1 | Coding-agent memory | Cloud-hosted async coding agents with teleportable session state ↗ 2 | native (first-party — Mistral Agents support MCP) ↗ 2 | Managed cloud (la Plateforme + Le Chat) + NVIDIA NIM containers ↗ 2 | API: $1.5/M input tokens; $7.5/M output tokens (Medium 3.5); Vibe via Pro/Team/Enterprise plans ↗ 2 | Apache-2.0 (Vibe CLI); Modified MIT (Medium 3.5 weights) ↗ 2 | mistral-vibe v3.0.1 (2026-10-20) ↗ 2 | mistralai/mistral-vibe — ~4.9k stars, last commit not confirmed ↗ ● | 2026-10-23 | |
Active | T1 | AI sandbox & runtime environments | Serverless container runtime + AI-agent sandboxes (Modal Labs) ↗ 2 | · | Managed cloud (no self-hosting) ↗ 2 | Pay-per-second compute (CPU + GPU); free tier (~$30/mo credit); team + enterprise tiers ↗ 2 | Apache-2.0 (client SDK only; platform proprietary) ↗ ● | v1.6.2 (2026-10-16) ↗ 2 | modal-labs/modal-client — ~530 stars, last commit 2026-10 ↗ ● | 2026-10-27 | |
Active | T1 | Claude Code memory mechanisms | KG-based persistent memory MCP ↗ ● | native (first-party) — reference implementation ↗ ● | local (Node.js MCP server; local JSON file) ↗ ● | free / open source (Apache-2.0 / MIT) ↗ ● | Apache-2.0 AND MIT (new contributions Apache-2.0; legacy code MIT; docs CC-BY-4.0) ↗ ● | 2026.8.31 (2026-08-31) — @modelcontextprotocol/server-memory@2026.8.31 ↗ ● | modelcontextprotocol/servers — ~90.0k stars, last release 2026-08 ↗ ● | 2026-10-22 | |
Active | T1 | Coding-agent memory | File-backed ~/.codex/memories + Chronicle ↗ 2 | native (first-party) ↗ 2 | Both (cloud agent via ChatGPT platform + CLI tool local) ↗ 2 | Included in ChatGPT Plus/Pro/Business/Edu/Enterprise plans (memory feature) ↗ 2 | Apache-2.0 (Codex CLI; cloud agent proprietary) ↗ ● | 0.165.0 (2026-10-27) (Codex CLI) ↗ 2 | openai/codex — ~128k stars, last commit 2026-10 ↗ ● | 2026-10-29 | |
Deprecated | T1 | Agent IDEs & coding harnesses | Terminal-native agentic coding harness (OpenAI) ↗ ● | yes — MCP client (mcp_servers in ~/.codex/config.toml); documented in Codex MCP docs ↗ 2 | Self-hosted only — local CLI (npm/Homebrew); model calls go to OpenAI via ChatGPT sign-in or API key ↗ ● | 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 ↗ 2 | Apache-2.0 ↗ ● | v0.165.0 (2026-10-27) ↗ 2 | openai/codex — ~128k stars, last commit 2026-10 ↗ ● | 2026-10-29 | |
Active | T1 | Agent IDEs & coding harnesses | OSS autonomous SWE agent platform (formerly OpenDevin) ↗ 2 | yes — connects to external MCP servers over SSE, Streamable HTTP or stdio ↗ 2 | Both (self-hosted + managed cloud) — Docker/local self-host + OpenHands Cloud (commercial) ↗ ● | Free (OSS) + paid cloud ($20/mo+) ↗ 2 | MIT ↗ 2 | v1.24.0 (2026-09-25) ↗ ● | OpenHands/OpenHands (formerly All-Hands-AI/OpenHands) — ~92k stars, last commit 2026-09 ↗ ● | 2026-10-31 | |
Active | T1 | Coding-agent memory | Project-files-as-memory + Temporal orchestration ↗ 2 | yes — Agent connects to listed or custom MCP servers via Integrations (OAuth or custom headers), with one-click install links ↗ 2 | Managed-only ↗ 2 | Starter free; Core $20/mo ($18 annual); Pro $100/mo ($90 annual); Enterprise custom ↗ 2 | · | · | · | 2026-10-22 | |
Active | T1 | Agent IDEs & coding harnesses | Cloud IDE with autonomous coding agent (Replit) ↗ 2 | yes — one-click MCP server list plus custom MCP servers; Agent loads their tools ↗ 2 | Both (self-hosted + managed cloud) — managed SaaS; enterprise Bring Your Own Cloud on AWS, Azure or Google Cloud (Full BYOC private preview, 2026-10) ↗ 2 | Core $20/mo ($18/mo billed annually); Pro $100/mo ($90/mo billed annually; higher usage tiers up to $2,000/mo); Enterprise custom ↗ 2 | · | Replit Agent 4 (2026-03-13) ↗ 2 | · | 2026-10-27 | |
Archived | T1 | Agent IDEs & coding harnesses | Code-intelligence-backed coding assistant + Agentic Chat ↗ 2 | Cloud + on-prem ↗ 2 | Cody Free/Pro discontinued 2025-07-23; Cody available to Enterprise customers only (contact sales) ↗ 2 | · | · | sourcegraph/cody-public-snapshot — ~3.8k stars, archived 2025-08-01 (development moved private) ↗ ● | 2026-10-26 |