# AutoGen

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

## Summary
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.


## Guide
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.

### What it is
AutoGen is an open agent resource to evaluate by action surface: what software it can operate, which tools or browser steps it touches, and how much supervision it needs before it can run real work.

### Why it matters
Multi-agent systems are becoming the standard approach for complex AI tasks, but building them from scratch is hard. AutoGen provides the primitives — agent registration, message routing, conversation management, state handling — so developers can focus on designing agent behaviors rather than infrastructure.

### How it works
Start with one safe workflow for AutoGen. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.


## Use Cases
- Multi-agent code generation: Build a pipeline where a planner agent designs the implementation, a coder agent writes it, and a reviewer agent checks it before committing.
- Research synthesis: Create agents that specialize in different aspects of a research question and synthesize their findings into a coherent analysis.
- Customer support orchestration: Route customer queries through a triage agent to specialized support agents, with escalation patterns for complex issues.

## Alternatives
- Use CrewAI for a more accessible API vs CrewAI: AutoGen offers more control and flexibility. CrewAI has a gentler learning curve and more intuitive role-based design.
- Use a single agent for simple tasks vs Claude Code: If your task doesn't require multiple specialized agents, a single-agent tool like Claude Code or Aider will be simpler and faster.

### Getting Started
- Read the documentation: https://microsoft.github.io/autogen/docs/
- Inspect the repository: https://github.com/microsoft/autogen

### FAQ
- What should I check before using AutoGen?
  - Start with one safe workflow for AutoGen. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.
- Is AutoGen open source?
  - AutoGen is listed with CC-BY-4.0 based on the official source links in this profile. Re-check the repository, model card, or docs before production use.
- Who should evaluate AutoGen?
  - AutoGen is most worth evaluating for developers building conversational multi-agent systems.
- 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.
## Why It Matters
AutoGen matters because it comes from one of the most well-resourced AI research labs in the world and is designed around the principle that agent conversations are the fundamental primitive for multi-agent systems. Its layered architecture lets developers start simple and add complexity as needed.


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

## What It Actually Does
- Layered architecture: AutoGen provides three layers: AgentChat for rapid prototyping, Core API for fine-grained control, and Extensions for ecosystem integrations.
  - Why it matters: Developers can start with the simplest layer and add complexity as their needs grow, without rewriting their codebase.
- Conversation-centric design: Agent conversations are the fundamental primitive. Agents collaborate through structured message passing with built-in conversation patterns.
  - Why it matters: Conversation-centric design makes it natural to model complex multi-agent interactions like debates, reviews, and iterative refinement.
- Microsoft ecosystem integration: Backed by Microsoft Research with deep integration into Azure AI services and the broader Microsoft developer ecosystem.
  - Why it matters: Teams already on Azure get first-class support, and the Microsoft backing means long-term maintenance and enterprise readiness.

## Typical Use Cases
- 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.

## 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.

## Command Line
### Install AutoGen
Install the AgentChat package for quick prototyping, or install autogen-core for the full Core API.

```bash
pip install autogen-agentchat
```

## Facts
- Category: agents
- Resource type: agent
- Open source: yes
- License: CC-BY-4.0
- Last verified: 2026-05-27
- GitHub repo: microsoft/autogen
- GitHub stars: 58400

## Capabilities
- workflow-orchestration

## Structured Use Case Tags
- developer-workflow

## Getting Started
- Open the GitHub repository: https://github.com/microsoft/autogen
- Read the documentation: https://microsoft.github.io/autogen/docs/
- Visit the project website: https://microsoft.github.io/autogen/

## Links
- GitHub: https://github.com/microsoft/autogen
- Homepage: https://microsoft.github.io/autogen/
- Docs: https://microsoft.github.io/autogen/docs/

## Structured Outputs
- JSON: https://www.openagent.bot/agents/autogen.json
- Markdown: https://www.openagent.bot/agents/autogen.md
- Canonical: https://www.openagent.bot/agents/autogen