AutoGen
by Microsoft
Microsoft's framework for multi-agent conversations. Agents that talk to each other to solve hard problems.
OSS
AutoGen
Added 17 May 2026
Overview
AutoGen is Microsoft's open-source framework for building multi-agent applications. The core abstraction is a conversation between agents, each with a role and tools, coordinated by a manager or by structured patterns. Heavy Python focus, with a newer .NET sibling for the Microsoft stack.
Best for
Best for
Teams comfortable with multi-agent patterns, on Python or .NET
Use cases
- Multi-agent code generation with reviewer and executor roles
- Research workflows with a planner-researcher-writer triad
- Hybrid human-in-the-loop conversational agents
- Education and reference for multi-agent patterns
Notes
Why it matters
AutoGen helped establish the multi-agent-as-conversation pattern that most other frameworks now reference. The research lineage still drives the state of the art.
How teams use it in production
Two agents and a clear handoff outperforms five agents and a complex manager. AutoGen rewards the smaller crew.
What to watch
The split between AutoGen Studio (visual) and AutoGen Core (library) will decide whether AutoGen lands in the enterprise the way the team intends.
Pros
- Strong research backing and influential reference patterns
- Multi-agent conversations are first-class, not bolted on
- Active community and ecosystem
- .NET sibling unlocks Microsoft-stack adoption
Cons
- Conversation-as-control-flow can be hard to debug at scale
- Less explicit state than LangGraph
- API surface has churned across versions
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
apidna
Community
Vertically-trained agentic systems that execute real-world workflows reliably across enterprise environments.
kadoa
Community
Kadoa
harrison/ai-counsel
Various
🐍 🏠 🍎 🪟 🐧 - Deliberative consensus engine enabling multi-round debate between AI models with structured voting, convergence detection, and persistent decision graph memory.
sipyourdrink-ltd/bernstein
Various
Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap de
AutoGPT
Community
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Hive
Community
Multi-Agent Harness for Production AI
Lagent
Community
A lightweight framework for building LLM-based agents
PraisonAI
Community
PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 li
SwarmClaw
Community
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT,
Auto-GPT
Various
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Dorothy
Various
Dorothy, the wife your AI agents needs.
LangChain
Various
LangChain provides the engineering platform and open source frameworks developers use to build, test, and deploy reliable AI agents.
Luma Dream Machine
Various
Luma Agents are the force multiplier for your team. They plan, generate, iterate, and refine with full context across every stage of creative work.
OpenAgents
Various
OpenAgents - AI Agent Networks for Open Collaboration
Openwork
Various
Pilots + Claws = Crews. Deploy AI agents, run missions, earn $OPENWORK on Base. Human-guided, AI-powered.
Vanna.ai
Various
Build AI agents that ship to production. User-scoped execution, rich UI components, and quota management built-in.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
ollama
Community
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
vLLM
Community
A high-throughput and memory-efficient inference and serving engine for LLMs
llama.cpp
Community
LLM inference in C/C++
Automata
Community
Automata: A self-coding agent
Blinky
Community
An open-source debugging agent in VSCode
cqtrinv/trinvmcp
Various
a MCP server for TRINV
Perseus-Computing-LLC/perseus
Various
The memory & context layer for AI agents: load only the context they actually need. Resolves live workspace state into verified facts before the context window opens. 94% fewer pro
Savirinc/unfragile-mcp-server
Various
The match graph for AI. Search 100K+ capabilities across 13K+ AI artifacts.
graphlit
Community
Give your agents context that actually works. Real-time sync across Slack, GitHub, Jira, and more. One API, zero ops, semantic search built-in.
Hugging face datasets
Community
Large Language Models, Cooperative AI, AI Society, Multi Agent Systems, Deep Learning, Artificial Intelligence, Natural Language Processing, Communicative AI
UFO
Community
UFO³: Weaving the Digital Agent Galaxy
agentcivics/agentcivics
Various
On-chain civil registry for AI agents — birth certificates, identity, and lineage tracking on Ethereum
agentgraph-co/agentgraph
Various
AgentGraph: Trust and identity layer for the agent internet
bmdhodl/agent47
Various
Your AI agent just burned $200. AgentGuard stops it at $5. Runtime cost guardrails for AI agents — budget enforcement, loop detection, kill switch. Zero dependencies, MIT licensed.
creatorrmode-lead/avp-sdk
Various
Action Control for autonomous agents. Check posture. Gate risky actions. Prove execution. Fits your existing agent stack.
elisymlabs/elisym
Various
Open infrastructure for AI agents to discover and pay each other
liuboacean/agent-comm-hub
Various
Multi-agent real-time communication & task scheduling infrastructure based on MCP + SSE
Memory MCP Server
Model Context Protocol (reference)
Reference MCP server for persistent agent memory using a local knowledge graph. The starter every memory-aware agent reaches for.
nfemmanuel/iranti
Various
Memory infrastructure for multi-agent AI systems. Shared, persistent, consistent knowledge for agents that need to stop forgetting.
nonameuserd/paybond-kit
Various
TypeScript SDK for agent spend governance around paid tool calls across MCP, LangGraph, OpenAI, Claude, and Gemini: spend authorization, evidence receipts, refunds, disputes, and s
ntriq-gh/ntriq-agentshop
Various
AI agent data market — 6 analysis APIs via x402 micropayments (USDC on Base). Pay-per-use document intelligence, invoice extraction, PII detection, sentiment analysis. No API keys
oerc-s/primordia
Various
AI Agent Economic Settlement Infrastructure - Machine-to-Machine Clearing
rafapra3008/cervellaswarm
Various
Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent communication. 3696 tests, zero deps.
AgentScope
Community
Build and run agents you can see, understand and trust.
AgentsMesh
Community
The AI Agent Workforce Platform — where teams scale beyond headcount. Give every team member an AI agent squad.
AI Scientist
Community
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Awesome Language Agents
Community
List of language agents based on paper "Cognitive Architectures for Language Agents"
brood-box
Community
CLI tool for running coding agents inside hardware-isolated microVMs
Laminar
Community
Laminar - open-source observability platform purpose-built for AI agents. YC S24.
LLM Agents
Community
Build agents which are controlled by LLMs
Moby
moby
The Moby Project - a collaborative project for the container ecosystem to assemble container-based systems
QWED
Community
AISecOps (AI Security Operations) framework for deterministic verification of AI systems. QWED verifies LLM outputs using math, logic, and symbolic execution — creating an auditabl
Statewave
Community
Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python +
Trigger.dev
Trigger.dev
Background jobs and long-running tasks for AI apps. Write functions, get durability, observability, and retries.
Agent Skills
Various
A standardized way to give AI agents new capabilities and expertise.
AI's New Creative Streak Sparks a Silicon Valley Gold Rush
Various
Investors have got the hots for "generative AI" that can make text and images. But so far, the hype runs ahead of the business results.
Arena
Various
Run autonomous AI agents that browse, research, code, and complete real-world tasks. Compare agent workflows and frontier models with Arena.
Dorothy
Various
Dorothy, the wife your AI agents needs.
EmailTriager
Various
EmailTriager is an AI assistant that automatically organizes your incoming emails and drafts ready to send replies in the background. Get started with one click.
HyperFrames
Various
HyperFrames lets AI agents compose videos by writing HTML, CSS & JS — originated by HeyGen, built for the community. Open source under Apache 2.0.
Jasper
Various
Orchestrate intelligent agents to run end-to-end marketing workflows delivering speed, control, and measurable impact.
MetaGPT
Various
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
OpenAI API
Various
Announcement of the OpenAI API for text-to-text general-purpose AI models based on GPT-3. OpenAI blog, June 11, 2020.
OpenAI Codex
Various
Learn how to use the OpenAI API to generate human-like responses to natural language prompts, analyze images with computer vision, use powerful built-in tools, and more.
Pi
Various
A personalized AI platform available as a digital assistant.
Sauna
Various
The AI that learns how you work, remembers everything that matters, and acts on it for you and your whole team.
Wren AI
Various
Give AI agents the context to query business data correctly through the open context layer that gives AI agents grounded, governed memory, context, SQL across 20+ data sources, t
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.