AutoGen
by Microsoft
Microsoft's framework for multi-agent conversations. Agents that talk to each other to solve hard problems.
OSS
AutoGen
Added 17 May 2026
Overview
AutoGen is Microsoft's open-source framework for building multi-agent applications. The core abstraction is a conversation between agents, each with a role and tools, coordinated by a manager or by structured patterns. Heavy Python focus, with a newer .NET sibling for the Microsoft stack.
Best for
Best for
Teams comfortable with multi-agent patterns, on Python or .NET
Use cases
- Multi-agent code generation with reviewer and executor roles
- Research workflows with a planner-researcher-writer triad
- Hybrid human-in-the-loop conversational agents
- Education and reference for multi-agent patterns
Notes
Why it matters
AutoGen helped establish the multi-agent-as-conversation pattern that most other frameworks now reference. The research lineage still drives the state of the art.
How teams use it in production
Two agents and a clear handoff outperforms five agents and a complex manager. AutoGen rewards the smaller crew.
What to watch
The split between AutoGen Studio (visual) and AutoGen Core (library) will decide whether AutoGen lands in the enterprise the way the team intends.
Pros
- Strong research backing and influential reference patterns
- Multi-agent conversations are first-class, not bolted on
- Active community and ecosystem
- .NET sibling unlocks Microsoft-stack adoption
Cons
- Conversation-as-control-flow can be hard to debug at scale
- Less explicit state than LangGraph
- API surface has churned across versions
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.