microsoft

AutoGen

Multi-agent conversation framework for building LLM applications with cooperating agents.

★ 59,526⑂ 8,961● Python⚖ CC-BY-4.0updated 2 months ago

README.md

AutoGen is a framework for building LLM apps from multiple agents that converse to solve tasks, with support for tool use, human participation and flexible conversation patterns.

pip install autogen-agentchat

Continue your stack

What teams reach for next — and why each earns a place beside AutoGen.

Pairs well with

Ragas

Evaluation toolkit for your RAG and agent pipelines — faithfulness, relevance, and more.

Why it fitsScore the outputs of your multi-agent conversations for faithfulness and relevance.

Alternative to

CrewAI

Orchestrate role-playing, autonomous AI agents that collaborate on tasks.

Why it fitsBoth do multi-agent collaboration; CrewAI is more opinionated about roles, AutoGen about conversation.

paperclip

Open-source control plane for running fleets of heterogeneous AI agents as a "company" — bring your own agent, assign goals, org charts, budgets, governance, and an audited ticket system.

Why it fitsAutoGen is a multi-agent framework for cooperating LLM agents — same coordination job as Paperclip, but as a library you build with rather than a dashboard you run external agents under.

Built with / on

Ollama

Run Llama, Mistral and other open models locally with a single command and a clean API.

Why it fitsBack your agents with a local model server.