Agent frameworks (no first-party memory layer)

Originally Microsoft Research's multi-agent framework — fork branded AG2 (2024-10) led by community. Memory is one optional component (AutoGen Memory cross-listed).

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.

Multi-agent framework — Crews (sequential) + Flows (event-driven). Open-source core + CrewAI Enterprise. Memory available via Mem0 / Letta adapters (CrewAI Memory cross-listed).

deepset's open-source framework for LLM/RAG/agent apps — Pipelines abstraction; deepset Cloud commercial. Memory is a downstream connector.

Event-driven durable workflow platform — competes with Temporal for the JS/TS/Python crowd. Inngest AgentKit (memory cross-listed) is the agent extension.

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.

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).

Data framework for LLM apps — connectors, indices, query engines, agents, workflows. Memory is one of many subsystems (LlamaIndex Memory cross-listed).

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 PostgreS…

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 s…

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…

Open-source workflow automation platform with first-class AI Agent / LangChain / Memory / Tool nodes — fastest-growing workflow tool in the AI era.

OpenAI's official Python framework for agents — handoffs, guardrails, tracing built in. Successor to OpenAI Swarm (experimental); officially supported.

Durable-execution platform — Workflows-as-code with crash safety. Used as agent-orchestration backbone at Stripe, Snap, Coinbase, OpenAI Stargate.

Vercel's TypeScript LLM SDK — streaming, tool calls, structured outputs, agents. Dominant framework for Next.js LLM apps.

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.

The first viral autonomous agent demo (March 2023) — GPT-4 + memory + tool use + self-direction. Significant Gravitas raised $12M to commercialise the AutoGPT Platform.

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.

Authentication and tool-execution platform for AI agents — 100+ apps with OAuth handled, function-call schemas, observability.

ai16z's TypeScript agent framework popularised in the crypto/Web3 agent space — multi-platform (Discord, X, Telegram). Brand evolved into elizaOS.

TypeScript-first agent framework — Workflows, Agents, RAG, eval. Built by the Gatsby team. YC W25.

Pydantic team's agent framework — type-safe agent definitions, structured outputs, tool calls validated by Pydantic schemas.

Hugging Face's minimal agent library — emphasises code-execution agents (agent writes Python, runs it) over JSON tool-calling. Library is intentionally ~1k LOC.

Open-source JS/TS background-jobs platform — long-running, retries, observability. Trigger.dev v3 (2024) added 'tasks' abstraction for agent workflows.

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).

Cisco + LangChain-led 'Internet of Agents' collective — open standards for discovery, messaging, observability of agent networks.

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.

Framework for production-ready AI agents in Python and TypeScript (Linux Foundation / IBM BeeAI).

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).

Open-source multi-agent framework for role-playing agent societies, data generation and agent scaling research.

Anthropic's SDK for building agents on the Claude Code agent loop (tools, sub-agents, MCP); published to PyPI as claude-agent-sdk.

Open-source platform to build agentic workflows and RAG pipelines in a visual, collaborative workspace; self-hosted or Dify Cloud.

Stanford's framework for programming, not prompting, language models: declarative modules and optimizers for prompts and weights.

Google Firebase's open-source framework for building AI-powered applications, with libraries for Node.js and Go (Go in alpha).

Google's code-first Python toolkit for building, evaluating and deploying AI agents.

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.

Visual low-code tool for building and deploying AI agents and workflows, with a Python runtime and API/MCP serving.

Microsoft Research's generalist multi-agent system — Orchestrator + WebSurfer/FileSurfer/Coder/ComputerTerminal specialists. Built on AutoGen v0.4.

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 202…

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.

Multi-modal agent framework (renamed from Phidata to Agno in 2025) — agents, memory, knowledge, tools; emphasis on multi-modal pipelines.

Durable-execution platform from ex-Confluent / Flink team — Restate Cloud + OSS server; emphasises low-latency invocation vs Temporal's polling.

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.

OpenAI Swarm — experimental educational multi-agent framework released Oct 2024; deprecated in favour of the OpenAI Agents SDK in Mar 2025.