The open-source multi-agent framework built by the creators of AutoGen. Backed by research and ready for production.
Quick Start
Intelligent, composable agents that collaborate through shared context.
pip install ag2[openai]from autogen import ConversableAgent, LLMConfig
coding_agent = ConversableAgent("coding_agent", llm_config=LLMConfig(config_list={"model": "gpt-5-nano"}))
response = coding_agent.run(message="Write a Python function to calculate fibonacci and when you're done say 'TERMINATE'.")
response.process()Key Capabilities
Specialized agents that work together. Define roles, share context, validate outputs.
Group chat, supervisor, round-robin, auto-selection. Or define your own.
Observable reasoning. Intervention points. Context-aware handoffs.
Tutorials, integrations, and real-world projects from AG2 developers worldwide.
Visit the community blogResearch
Built on AutoGen's research foundation. Powering published research at leading universities.
faster cosmology research
Cambridge University
faster clinical decisions
Healthcare AI study
GAIA benchmark ranking
Agentic reasoning
ICLR 2024 Award
AutoGen research
Get early access and shape the future of multi-agent systems with us.