AutoGen
A framework for building AI agents and applications
AutoGen is an open-source framework developed by Microsoft for building AI agent applications. It provides multiple layers including a web-based Studio UI for no-code prototyping, an AgentChat programming layer for conversational agent apps, and a Core event-driven system for scalable multi-agent architectures. Extensions allow integration with external services like OpenAI, MCP servers, and Docker.
AutoGen provides layered abstractions—from a no-code Studio UI to Python AgentChat APIs to an event-driven Core runtime—that let developers prototype, build, and deploy single or multi-agent AI workflows.
developers and researchers building AI agent applications
Background.
- Status
- launched
- Business model
- open-source
- Company
- Microsoft
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.