LLMs & AI Infra AI Agent Framework stable

AutoGen

Microsoft's multi-agent conversation framework

38.0K stars 400 contributors Since 2023
Website → GitHub

Framework for building multi-agent systems where AI agents converse, collaborate, and use tools to solve complex tasks with human-in-the-loop capabilities.

License
MIT
Min RAM
512 MB
Min CPUs
1 core
Scaling
single_node
Complexity
intermediate
Performance
medium
Self-hostable
K8s native
Offline
Pricing
fully free
Docs quality
good
Vendor lock-in
none

Use cases

  • Multi-agent coding assistants that debug each other
  • Group chat between specialized AI agents
  • Human-in-the-loop approval for agent actions
  • Automated research with web browsing agents

Anti-patterns / when NOT to use

  • Can generate very long conversations (token-heavy)
  • Debugging agent interactions is complex
  • Less opinionated than CrewAI — more setup needed

Replaces / alternatives to

  • Custom multi-agent code

Technical specs

Language
Python
API type
SDK
Protocols
HTTP
Deployment
pip
SDKs
python

Community

GitHub stars 38.0K
Contributors 400
Commit frequency daily
Plugin ecosystem none
Backing Microsoft
Funding corporate

Release

Latest version
Last release
Since 2023

Best fit

Team size
solosmallmedium
Industries
generalresearchenterprise

Tags

  • multi-agent
  • conversable-agents
  • group-chat
  • code-execution
  • human-in-loop
  • tool-use