AutoGen
AutoGen is a framework that lets developers build multi-agent AI applications for their own domain. It is archived and no longer maintained by Microsoft.
What it is good for
- Building several AI agents that work together on a task
- Prototyping multi-agent workflows without writing much code
- Running a no-code interface for multi-agent workflows
- Evaluating how well AI agents perform on tasks
At a glance
- Who it is for
- Setup
- Requires programming
Level 5 of 5. You need to write code to use it.
- Cost
- Free and open source
- Type
- Framework or SDK
- Tasks
- Works with
- OpenAI, Azure OpenAI, Playwright MCP server, Microsoft Agent Framework
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 61,672
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is AutoGen free?
- Yes. It is free and open source (CC-BY-4.0 license).
- Do I need to know how to code to use AutoGen?
- Yes. You need to write code to use it.
- What does AutoGen work with?
- According to its own documentation, it works with OpenAI, Azure OpenAI, Playwright MCP server, and Microsoft Agent Framework.
- What is AutoGen good for?
- Building several AI agents that work together on a task, prototyping multi-agent workflows without writing much code, running a no-code interface for multi-agent workflows, and evaluating how well AI agents perform on tasks.
Similar agents
- browser-use
Browser Use is an open-source Python library and cloud service that lets AI agents control a web browser to finish tasks for you.
- Haystack
Haystack is a Python framework that helps developers build production LLM apps and agent workflows for search and question answering.
- OpenSandbox
OpenSandbox is a sandbox runtime that lets developers run AI agents in isolated environments on their own infrastructure.
- Open Ontologies
Open Ontologies is an agent app that plans changes to a production ontology and checks their consequences for developers and data teams.
- RPent
RPent is an open framework for building physical robot agents that learn from interaction with the real world for robotics developers and researchers.
- Neuro SAN Studio
Neuro SAN Studio is a framework and playground for building multi-agent systems that split a task across several AI agents for developers and domain experts.