Agents open-source 58,400 stars

AutoGen

Multi-agent AI framework from Microsoft Research for building conversational agent systems with AgentChat, Core API, and Extensions.

AutoGen is Microsoft Research's open-source framework for building multi-agent AI systems. It provides three layers — AgentChat for quick prototyping, Core API for fine-grained control, and Extensions for ecosystem integrations — giving developers a flexible foundation for agent collaboration patterns.

terminal
$ pip install autogen-agentchat
# Install the AgentChat package for quick prototyping, or install autogen-core for the full Core API.
Decision signals
Open source
Tags
workflow orchestrationopen sourcedeveloper workflow

Quick answer

What is AutoGen?

AutoGen is Microsoft Research's framework for building multi-agent AI systems. It treats agent conversations as the fundamental building block and provides a layered architecture that scales from quick prototypes to production systems.

AutoGen is an open-source framework for building conversational multi-agent systems. It offers three layers: AgentChat for rapid prototyping with pre-built conversation patterns, Core API for fine-grained control over agent state and messaging, and Extensions for integrating with external tools and services. Agents collaborate through structured message passing.

Fit check

When to use it

Good fit if

  • Developers building conversational multi-agent systems
  • Research teams studying agent collaboration patterns and emergent behavior
  • Engineers who need fine-grained control over agent state, messaging, and orchestration

Not a fit if

  • Developers who only need a single-agent terminal coding tool
  • Teams looking for a drag-and-drop workflow builder with a visual UI

First test

How to evaluate it before committing

Run one narrow workflow in a sandbox account, then inspect logs, permissions, and failure cases before expanding scope.

Keep the first test small enough that you can inspect the source, understand the permissions, and compare the result with nearby OpenAgent resources.

Workflows

Common ways to evaluate it

Agent research and experimentation

Use AutoGen to study how agents collaborate, debate, and refine outputs through structured conversations.

Complex task decomposition

Break down complex tasks into sub-tasks handled by specialized agents that pass results and context between each other.

Automated code generation pipelines

Build agent teams where one agent writes code, another reviews it, and a third tests it, iterating until quality thresholds are met.

Compare

How it compares

Choose AutoGen for fine-grained agent control vs CrewAI

AutoGen's Core API offers more control over agent state and messaging. CrewAI's role-based API is more intuitive but less flexible for advanced patterns.

Resource Category License Stars
Aider Agents Apache-2.0 45,400
Claude Code Agents Proprietary 127,000
Codex CLI Agents Apache-2.0 86,100

FAQ

Questions search visitors ask

Is AutoGen open source?

Yes. AutoGen is released under the CC-BY-4.0 license, making the source code available for inspection, modification, and redistribution.

Who should use AutoGen?

Developers building conversational multi-agent systems, especially those who need fine-grained control over agent state, messaging, and orchestration patterns.

How does AutoGen compare to other multi-agent frameworks?

AutoGen's main advantage is its layered architecture and conversation-centric design. It offers more low-level control than CrewAI but has a steeper learning curve.