AutoGen

Frameworks & SDKs 💻 Python ⚖️ CC-BY-4.0 🟡 Quiet lately
60.8k stars

AutoGen is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans. It provides a layered architecture with high-level and low-level APIs to build agent-based systems. It is intended for developers building AI applications that require multiple collaborating agents.

AutoGen Tutorial 🚀 Create Custom AI Agents EASILY (Incredible)

🎬 AutoGen Tutorial 🚀 Create Custom AI Agents EASILY (Incredible) · Matthew Berman

AutoGen demo
🖼️ Screenshot from the project README

✨ Key features

  • Layered design: Core, AgentChat, and Extensions APIs
  • Event-driven agents with local and distributed runtime
  • Cross-language support for .NET and Python
  • No-code GUI with AutoGen Studio for prototyping
  • Benchmarking suite with AutoGen Bench
  • Integration with MCP servers for tool use

🎯 Use cases

  • Build a simple assistant agent that responds to tasks
  • Create a web browsing assistant using MCP servers
  • Orchestrate multiple specialized agents for complex tasks
  • Prototype multi-agent workflows without code using AutoGen Studio

📦 Installation

🧰 Requirements: Python 3.10 or later, and an OpenAI API key for samples using OpenAI models.

# Install AgentChat and OpenAI client from Extensions
pip install -U "autogen-agentchat" "autogen-ext[openai]"
# Install AutoGen Studio for no-code GUI
pip install -U "autogenstudio"

🚀 Usage

import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

async def main() -> None:
    model_client = OpenAIChatCompletionClient(model="gpt-4.1")
    agent = AssistantAgent("assistant", model_client=model_client)
    print(await agent.run(task="Say 'Hello World!'"))
    await model_client.close()

asyncio.run(main())

⚠️ Good to know

AutoGen is in maintenance mode and will not receive new features or enhancements; it is community managed. New users are directed to Microsoft Agent Framework.

❓ FAQ

What is the current status of AutoGen?

AutoGen is in maintenance mode, meaning it will not receive new features or enhancements and is community managed going forward.

What Python version is required?

AutoGen requires Python 3.10 or later.

How do I get an OpenAI API key?

You need to create an account with OpenAI and export your key as an environment variable: export OPENAI_API_KEY="sk-...".

Can I use AutoGen Studio for production?

No, AutoGen Studio is meant for rapid prototyping and is not a production-ready app. Developers should build their own applications with proper security.

📊 Repository

Stars★ 60,816
Forks🍴 9,178
Open issues🐛 1,047
Last commit🕒 Apr 15, 2026
Created📅 Aug 2023
Language💻 Python
License⚖️ CC-BY-4.0

🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.