AutoGen

Hybrid (offline or cloud)

Microsoft's multi-agent framework. Conversation-first orchestration of role-played agents.

Editorial verdict: “Multi-agent role-played framework, now archived. Microsoft points new users to Microsoft Agent Framework.”

Agent framework
Free
MIT
★ 4.2 / 5
GitHub ★ 61,732

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported
ollamaopenai-compat
§ OS / platform
linuxmacoswindows

What it is

AutoGen is Microsoft Research's multi-agent framework. The mental model is conversations between role-played agents (e.g., 'coder' agent + 'reviewer' agent). Supports any OpenAI-compatible endpoint including local Ollama. Microsoft has since archived the project: it is no longer maintained by Microsoft, which advises against production use and points new users to Microsoft Agent Framework.

✓ Strengths

  • +Multi-agent paradigm is the right model for some workloads
  • +Pioneered in Microsoft Research
  • +Strong conversation-debugging features

△ Caveats

  • −Mental model is heavier than single-agent frameworks
  • −Best results need a strong base model (32B+)
  • −Archived and no longer maintained by Microsoft