AutoGen
Multi-agent conversation framework from Microsoft Research
View on GitHubWhat it solves
How to coordinate multiple specialized agents toward a shared goal without writing low-level orchestration logic by hand.
Overview
AutoGen is a framework for building multi-agent systems through conversable agents; each agent can participate in conversations, use tools, generate code, and execute it. Best suited for tasks where splitting work across specialized agents outperforms a single capable generalist.
Key facts
- Language
- Python
- License
- MIT
- Maturity
- Fast-moving
- Maintainer
- microsoft
- Reviewed
- 2026-06-11
Where to start
The two-agent example is the clearest starting point for AutoGen's conversation model.
python/samples/agentchat_two_agents.pyTechnologies
More in this domain
LangGraph
Stateful multi-agent orchestration for LLM applications
The state management problem in multi-agent systems: how you build agents that pass context across turns without losing the execution thread.
CrewAI
Role-based multi-agent orchestration for collaborative task execution
The boilerplate problem in multi-agent setup: defining roles, delegation rules, and task routing without writing a custom orchestration graph.
OpenAI Agents SDK
Lightweight Python SDK for building production-grade AI agents
The bootstrapping problem: going from a one-shot prompt to a real agent loop with handoffs, tool execution, and tracing without writing infrastructure from scratch.