AutoGen
Build multi-agent pipelines where AI agents converse, execute code, and solve problems collaboratively. Microsoft Research's framework for applications that need more than a single model call.
Overview
AutoGen is Microsoft Research's open-source framework for building multi-agent AI applications where agents can converse with each other, use tools, execute code, and collaborate to solve problems that require multiple rounds of reasoning. The ConversableAgent pattern lets you define human proxies, coding agents, and assistant agents that hand tasks back and forth until a problem is solved — or escalate to a human when they're stuck. Used by researchers and developers building complex AI pipelines, automated research workflows, and coding agents that write, test, and iterate on code autonomously.
Key Features
- ConversableAgent pattern
- Human-in-the-loop support
- Code execution sandbox
- Group chat between agents
- Tool use and function calling
- Flexible model backend
- • Best for complex research and coding tasks that need iterative agent collaboration
- • Human proxy pattern makes it easy to build supervised autonomy workflows
- • Microsoft backing means strong long-term development
- • Higher complexity than simpler agent frameworks for basic tasks
- • Python-only with a steeper learning curve than visual tools