https://github.com/microsoft/autogen
A programming framework for agentic AI
https://github.com/microsoft/autogen
agentic agentic-agi agents ai autogen autogen-ecosystem chatgpt framework llm-agent llm-framework
Last synced: about 4 hours ago
JSON representation
A programming framework for agentic AI
- Host: GitHub
- URL: https://github.com/microsoft/autogen
- Owner: microsoft
- License: cc-by-4.0
- Created: 2023-08-18T11:43:45.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2026-11-12T10:19:36.000Z (6 days ago)
- Last Synced: 2026-11-14T21:33:56.018Z (3 days ago)
- Topics: agentic, agentic-agi, agents, ai, autogen, autogen-ecosystem, chatgpt, framework, llm-agent, llm-framework
- Language: Python
- Homepage: https://microsoft.github.io/autogen/
- Size: 142 MB
- Stars: 61,822
- Watchers: 522
- Forks: 9,404
- Open Issues: 1,181
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
- Support: SUPPORT.md
- Copilot: .github/copilot-instructions.md
Awesome Lists containing this project
- awesome-generative-ai - AutoGen - AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. (Agents / Autonomous agents)
- awesome-openclaw-money-maker - **Microsoft Autogen** - A programming framework for agentic AI. Multi-agent conversations, tool use, code execution. (AI Agent Frameworks / General Agent Frameworks)
- awesome-vector-databases - AutoGen - Open-source framework from Microsoft Research for building AI agents and facilitating multi-agent cooperation with support for two-agent chat, sequential chat, and group chat patterns. ([Read more](/details/autogen.md)) `Microsoft` `multi-agent` `conversational-ai` (LLM Frameworks)
- awesome-production-machine-learning - AutoGen - AutoGen is an open-source framework for building AI agent systems. (Agentic Framework)
- awesome-python - microsoft/autogen - A programming framework for agentic AI (Other / Scientific Computing)
- awesome-python - autogen - A programming framework for building agentic AI applications. (AI and Agents)
- awesome-ai-agents-2026 - AutoGen - Microsoft のマルチエージェント会話フレームワーク(Microsoft Agent Framework に統合)。 (🏗️ エージェントフレームワーク / その他の標準)
- awesome-agents - autogen - agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour | framework | 44,300 | 6,677 | 556 | 444 | 1 days, 6 hrs, 6 mins | 88 | Creative Commons Attribution 4.0 International | (Table of Open-Source AI Agents Projects)
- awesome-gpt - https://github.com/microsoft/autogen
- awesome-agent-frameworks - AutoGen - Microsoft's foundational multi-agent conversation framework. (Agent SDK / framework)
- awesome-lowcode - AutoGen - AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. (AI)
- Awesome-Self-Evolving-Agents - 💻 GitHub
- Awesome-AGI - autogen
- ai-game-devtools - AutoGen - Gen Large Language Model Applications. |[arXiv](https://arxiv.org/abs/2308.08155) | | Agent | (<span id="game">Game (World Model & Agent)</span> / <span id="tool">LLM (LLM & Tool)</span>)
- awesome-ai - Autogen - A programming framework developed by Microsoft for agentic AI. (Agent)
- awesome-a2a-libraries - AutoGen Studio - based model; lacks protocol-level interoperability. (UI / Visual Orchestration for A2A / C#)
- awesome-LLM-resources - AutoGen - AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. [AutoGen AIStudio](https://autogen-studio.com/) (智能体 Agents)
- awesome-data-analysis - autogen - Framework for building multi-agent conversational systems. (🧠 AI Applications & Platforms / Tools)
- awesome-llm-tools - AutoGen
- awesome-mistral - AutoGen - agent framework. (Agents & Orchestration / Agent Frameworks)
- awesome-generative-ai - AutoGen - AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. (Agents / Autonomous agents)
- awesome-ai - AutoGen - AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. (Coding / Autonomous agents)
- awesome-agentic-engineering-resources - **AutoGen**
- awesome-ai - AutoGen
- Awesome-AI-Agents - AutoGen - AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.  (Frameworks / Advanced Components)
- Awesome-AITools - Github
- awesome-agent-loop-papers - autogen - agent conversation and group-chat orchestration | (Real-world artifacts / Frameworks and coding harnesses)
- stars - microsoft/autogen - Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ (Jupyter Notebook)
- awesome-agents - Autogen - Gen Large Language Model Applications.  (Frameworks)
- awesome-genai - AutoGen - A programming framework for agentic AI. [](https://github.com/microsoft/autogen/network/members) [](https://github.com/microsoft/autogen/stargazers) (Tools & Frameworks / Development Frameworks)
- awesome-opc - AutoGen - agent workflows with tools, human input, and conversational handoff. (🛠 Tools / AI-Powered)
- awesome-ai - **AutoGen (Microsoft)** - agent conversation framework. (🤝 Agent Frameworks & MCP / Agent Frameworks)
- recommendations-for-engineers - AutoGen - gen large language model applications (🤖 LLM / shell)
- awesome-harness-engineering - AutoGen - agent conversation framework with a complete AgentChat layer covering agent loop, tool integration, termination conditions, and human-in-the-loop. The most comprehensive open-source reference for large-scale multi-agent harness design.  (Design Primitives / Task Runners & Orchestration)
- awesome-generative-ai-data-scientist - AutoGen
- Awesome-RAG-Production - AutoGen
- acu - AutoGen
- alan_awesome_llm - AutoGen - studio.com/) (Agents)
- awesome-agent-swarm - **AutoGen** - Programming framework for agentic AI by Microsoft. Build multi-agent applications with conversational patterns and group chat. by [@microsoft](https://github.com/microsoft) (59,201 stars) (Swarm Frameworks)
- Awesome-Local-LLM - _Website_ - discord) | [_Docs_](https://microsoft.github.io/autogen/docs/Getting-Started) (Agents)
- AiTreasureBox - microsoft/autogen - 11-09_51508_15](https://img.shields.io/github/stars/microsoft/autogen.svg)|Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ| (Repos)
- awesome-agents - Autogen - Microsoft's framework for building multi-agent conversational AI systems. (Frameworks)
- awesome-llm-agent - AutoGen
- awesome-local-llm - autogen - a programming framework for agentic AI (Tools / Agent Frameworks)
- awesome-ai-agents - microsoft/autogen
- awesome-mac-mini-homeserver - AutoGen - Multi-agent conversation framework from Microsoft.   (Agentic AI  / Agentic frameworks)
- awesome-agent-harness - AutoGen - 09 | (Agent Framework 🧠 / 5. The Convergence: Harness-as-a-Service (HaaS))
- awesome-agent-infra - AutoGen - Multi-agent framework (Runtime and Control Plane / Projects)
- awesome-chatgpt-claude-agents - Autogen - Enable Next-Gen Large Language Model Applications (🛠️ Frameworks & Platforms / Multi-Agent Orchestration)
- awesome-langchain-zh - Autogen
- awesome-agent-protocols - AutoGen / AG2 - agent framework. Agents exchange messages to solve tasks. (Inter-Agent Protocols / Orchestration Frameworks)
- awesome-agi-agents - autogen
- awesome-cli-agentic-tools - AutoGen - agent conversations by Microsoft Research. | `pip install autogen` | Python | (Agent Frameworks / Community)
- awesome-AI-driven-development - autogen - A programming framework for agentic AI (Multi-Agent & Orchestration / Other IDEs)
- awesome_ai_agents - AutoGen by Microsoft - AutoGen is a multi-agent conversation framework facilitating the development of next-gen LLM applications, highlighted by various accomplishments and offering enhanced LLM inferences, customizable agents, and comprehensive documentation [github](https://github.com/microsoft/autogen) | [video](https://www.youtube.com/watch?v=DXhqhpHWRuM) (Learning / Repositories)
- awesome-llm-agents - AutoGen - BY-4.0 | 2026-10 | Conversational multi-agent systems | (Multi-Agent Orchestration)
- awesome-ai-coding-tools - AutoGen - agent framework for building AI agent teams that collaborate on coding tasks. (Coding Agents)
- awesome-ml-python-packages - autogen
- awesome-ai-agent-testing - AutoGen - **20k+ stars** - Microsoft's framework for building conversational agents with comprehensive testing tools. (Testing Frameworks / Open Source Frameworks)
- awesome-autonomous-gpt - autogen - Enable Next-Gen Large Language Model Applications. (Projects / Applications)
- awesome-ai-coding - autogen - → AI Agent Frameworks (📋 Changelog / 2026-07-19 — Weekly Update)
- awesome-manus - AutoGen - Next-gen LLM applications via multi-agent conversation (Multi-Agent Systems / LangManus)
- awesome-internet-of-ai-agents - https://github.com/microsoft/autogen - Multi-agent orchestration with conversational workflows and tool/function calling. (Frameworks)
- awesome-ai-tools - AutoGen - agent conversation framework. Agents collaborate, code, and debate to solve problems. CC-BY-4.0. (Other AI Agents / Multi-Agent / Orchestration Frameworks)
- best-of-ai-open-source - GitHub - 8% open · ⏱️ 07.01.2025): (AI Agents & Orchestration)
- awesome-llm-knowledge-bases - AutoGen - Microsoft's framework for building multi-agent conversational AI systems. (LLM Agents & Frameworks)
- awesome-ai-agents - AutoGen - agent conversations, GPT-4 integration, customizable workflows | (🌟 Core Frameworks)
- awesome-azure-openai-copilot - AutoGen - Customizable multi-agent conversation and tool orchestration framework (community AG2 and Microsoft variants). (Agent Frameworks)
- Awesome-RAG - AutoGen
- awesome-ai - 🔗
- Awesome-Embodied-AI - AutoGen, EcoOptiGen
- awesome-ai-agents - AutoGen - Multi-agent AI framework by Microsoft. (Open-source Projects)
- awesome-opensource-ai - AutoGen (AG2) - Flexible multi-agent conversation framework.  (4. Agentic AI & Multi-Agent Systems)
- awesome-deepreview - 2308
- awesome-vibe-coding - AutoGen - agent framework. Agents that chat with each other. | (AI Frameworks & SDKs / Agent Frameworks)
- awesome-ChatGPT-repositories - autogen - Enable Next-Gen Large Language Model Applications. Join our Discord: <https://discord.gg/pAbnFJrkgZ> (Chatbots)
- awesome-ai - AutoGen
- awesome-opensource-ai - Microsoft AutoGen - agent conversation framework, now in maintenance mode. Community fork continues as [AG2](https://github.com/ag2ai/ag2). (Honorable Mentions)
- awesome-gui-agents - AutoGen
- awesome-ai-lead-generation - AutoGen - Microsoft's multi-agent framework for building conversational AI sales agents. `Python` `Free` (AI Sales Agents & Outreach)
- awesome-deep-research - Autogen - A framework for developing multi-agent conversation systems. (🤖 Deep Research Systems / 🌐 Open-Source Deep Research Implementations)
- awesome-hacking-lists - microsoft/autogen - A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: <https://aka.ms/autogen-discord> Office Hour: <https://aka.ms/autogen-officehour> (Python)
- awesome-ai-agent-stack - microsoft/autogen - Conversational multi-agent framework from Microsoft Research. (Agent Frameworks & Orchestration)
- awesome-ai-agents-2026 - AutoGen - Microsoft multi-agent conversations. (🧱 Agent Frameworks / Multi-Agent Orchestration)
- awesome-ai-agents-2026 - Microsoft AutoGen - agent conversation, actor model | Research, enterprise multi-agent dialogue | (1. Agent Frameworks (Production-Ready))
- awesome-github-projects - autogen - A programming framework for agentic AI ⭐61,365 `Python` (🤖 AI & Machine Learning)
- awesome-llm-agents - GitHub
- github-ultimate-repos - microsoft/autogen - | ⭐ 61,554★ | 🍴 9,313 | 💻 `Python`🔗 <https://github.com/microsoft/autogen>📝 A programming framework for agentic AI⚙️ `Goal decomposition DAG -> dynamic tool routing (MCP JSON-RPC) -> state graph & shared memory scratchpad -> multi-agent execution swarm -> critic-refiner consensus loop.` (📜 Master Categorized Repository Directory (100% Clickable Links) / [03] MULTI-AGENT SYSTEMS, AUTONOMOUS SWARMS, AI ORCHESTRATION & MCP TOOLS)
- awesome-llm-tools - AutoGen - agent conversation framework | Collaborative multi-agent problem solving | (2. Libraries & Frameworks / Python)
- jimsghstars - microsoft/autogen - A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour (Jupyter Notebook)
- awesome-microsoft-agent-framework - AutoGen - Multi-agent conversation framework. (Related Technologies / Microsoft AI Ecosystem)
- awesome-ai-agents - AutoGen - Microsoft's framework for building multi-agent conversational systems. (Multi-Agent Frameworks / Agent Collaboration)
- llmops - AutoGen - agent conversation framework |  | (Orchestration / Agent Frameworks)
- awesome-ai-agents - AutoGen - agent conversation framework. Supports complex agent topologies. (Frameworks & Libraries / Multi-Agent Orchestration)
- Awesome-Ai-Tools - AutoGen - Microsoft's framework for multi-agent AI with parallel execution and event-driven architecture. (Miscellaneous / AI Agents & Automation)
- Awesome-Prompt-Engineering - GitHub
- awesome-agent-cortex - AutoGen - Multi-agent conversation framework from Microsoft Research. (Agent Frameworks)
- Awesome-AI-Scientists - AutoGen / AG2 - Microsoft. A multi-agent conversation framework. (Agent Frameworks (General-Purpose) / Single-Cell & Omics)
- Ultimate-AI-Resources - Autogen - agent conversations (🌟 Hidden Gems: Underrated Tools / Resources)
- fucking-awesome-python - autogen - A programming framework for building agentic AI applications. (AI and Agents)
- awesome-agent-collaborate-tools - AutoGen - Microsoft's framework for conversational multi-agent workflows. Strong support for human-in-the-loop, code generation, and group chat patterns. (Multi-Agent Orchestration)
- awesome-harness-engineering - microsoft/autogen
- awesome-ai-pulse-georgia - AutoGen - ის Python ფრეიმვორკი, სადაც რამდენიმე AI აგენტი ერთმანეთთან ესაუბრება და კომპლექსურ პრობლემებს ერთობლივად წყვეტს. conversation pattern-ები, tool use, human-in-the-loop, code execution — ყველა abstractions-ი ჩაშენებულია. 2026 წლის აპრილში Semantic Kernel-თან ერთად Microsoft Agent Framework 1.0-ის ოფიციალურ ნაწილად გამოცხადდა. Python-ში, MIT ლიცენზიით. Microsoft Azure-სთან ღრმა ინტეგრაცია, enterprise AI deployments-ისთვის გამოიყენება. | (🧬 AI აგენტების ფრეიმვორკები)
- awesome-agi-aci-asi - AutoGen -  (Frameworks and Platforms / Established Agent Frameworks)
- awesome-prediction-markets - AutoGen - agent framework. Works with any REST API. (Agent Frameworks & Examples / Frameworks)
- awesome-local-ai-agents - AutoGen - <br>Stars: 50K+ · Language: Python · Ollama Support: Via OpenAI-compat<br>Best For: Conversational multi-agent, Microsoft research (Local Agent Frameworks)
- awesome-ai-agents - microsoft/autogen - AutoGen is a Microsoft-developed framework for building multi-agent AI applications that operate autonomously or with human collaboration, featuring layered APIs, developer tools, and community support. (AI Agent Frameworks & SDKs / Multi-Agent Collaboration Systems)
- awesome-langchain - Autogen - Enable Next-Gen Large Language Model Applications. (Other LLM Frameworks)
- awesome-workflow-automation - AutoGen (Microsoft) - agent framework. Agents collaborate, iterate, and execute with minimal human input. Popular in academic and training environments. (🧩 Agent Frameworks & Dev Libraries / Multi-Agent Orchestration)
- awesome-dev-advocacy - microsoft/autogen: A programming framework for agentic AI
- awesome-production-llm - AutoGen
- awesome - microsoft/autogen - A programming framework for agentic AI (Python)
- Awesome-LLMOps - autogen - commit/microsoft/autogen?color=green) (Orchestration / Agent Framework)
- Awesome-GitHub-Repo - AutoGen - 微软开源的多Agent对话框架,支持Agent之间自主对话协作完成复杂任务,提供灵活的对话模式和人类介入机制。 (AI开源项目 / AI Agent)
- awesome - microsoft/autogen - A programming framework for agentic AI (Python)
- awesome-os-llm - AutoGen - Microsoft's multi-agent framework. Model calls go through an OpenAI-compatible client, so a local runtime can sit behind it. (Use cases / Agents)
- awesome-agent-vault - AutoGen
- awesome-agent-harness - GitHub - 59099-f4b400?style=flat-square)](https://github.com/microsoft/autogen) | multi-agent, orchestration, framework | Programming framework for agentic AI with multi-agent interaction and orchestration. | (Catalog / Harness Architecture & Orchestration)
- awesome-projects - autogen - A programming framework for agentic AI (Uncategorized / Uncategorized)
- awesome-agents - AutoGen - Enable next-gen LLM applications via multi-agent conversations (🤖 Agent Projects / 🎨 Content Creation Agents)
- Awesome-Graph-Engineering - AutoGen/GraphFlow
- awesome-agent-evolution - **autogen** - Programming framework for building agentic AI systems with multi-agent conversations. by [@microsoft](https://github.com/microsoft) (61,393 stars) (Multi-Agent Frameworks)
- awesome-context-ai - AutoGen - agent conversations with context |  | (AI Frameworks with Context Support / Commercial)
- awesome-agentic-ai - AutoGen - Microsoft multi-agent conversation framework (Frameworks and Libraries)
- awesome-vibe-research - AutoGen - Framework de Microsoft para agentic AI. Útil para agents especializados como scout, critic, experimenter o writer. (Orquestadores de Agents / Etapas de Autonomía del Agent)
- Awesome-Agentic-Engineering - AutoGen - agent conversations; v0.4 redesigned for async event-driven execution. | `[official]` · `[benchmark]` | (⚙️ Orchestration Frameworks / Frameworks Landscape)
- awesome-ai-tools - Microsoft AutoGen - yellow) — MAINTENANCE MODE. Event-driven multi-agent. Users directed to Microsoft Agent Framework. · `CC-BY-4.0` · Python, .NET · ≈59.1k★ *GitHub API, 2026-06-19* (🧩 Agent Frameworks & SDKs / The three-vendor SDK race)
- awesome-specification-driven-development - Microsoft AutoGen - A programming framework for agentic AI.  (Agentic Programming / Frameworks and Tools)
- awesome-x-ops - AutoGen - agent conversation framework for building complex agentic AI applications with flexible conversation patterns and human-in-the-loop workflows. (Agentic Workflow)
- awesome-scientific-peer-review - AutoGen - Multi-agent application framework. (🧱 Infrastructure and Building Blocks / General RAG and Agent Frameworks)
- awesome-rust-ai-libraries - AutoGen by Microsoft - Multi-agent conversation framework facilitating the development of next-gen LLM applications, offering enhanced LLM inferences, customizable agents, and comprehensive documentation. ([Read more](/details/autogen-by-microsoft.md)) `Microsoft` `Multi Agent` `Conversation` (Agentic Systems)
- awesome-offensive-mcp - Microsoft AutoGen
- awesome-ai-agents - Autogen
- awesome-ai-agents-2026 - AutoGen - `🚀` `[Python]` `[Multi-Agent]` - Event-driven multi-agent framework merged with Semantic Kernel for production workflows. (Orchestration Frameworks)
- awesome-production-agentic-systems - AutoGen - AutoGen is an open-source framework for building AI agent systems. (Agentic Frameworks)
- awesome-agent-operating-systems - Microsoft AutoGen / AG2 - Conversational multi-agent framework. Role-based GroupChat coordination for Azure environments. *Checked: 2026-08-16* (Orchestration Frameworks)
- awesome-agent-orchestration - AutoGen - Microsoft's framework for building multi-agent conversational systems (Core Frameworks / Multi-Agent Orchestration Frameworks)
- awesome-ai-coding-agent-tools - AutoGen / Microsoft Agent Framework - Microsoft's open-source framework combining multi-agent patterns with enterprise features. (Agent SDKs & Frameworks / Orchestration Frameworks)
- awesome-list - autogen: A programming framework for agentic AI
- awesome-ai - github.com/microsoft/autogen
- awesome-agentic-engineering - Microsoft AutoGen - Programming framework for building multi-agent AI systems with conversable agents that collaborate to solve tasks.  (Multi-Agent Frameworks / Commercial Offering)
README
[](https://twitter.com/pyautogen)
[](https://www.linkedin.com/company/105812540)
[](https://aka.ms/autogen-discord)
[](https://microsoft.github.io/autogen/)
[](https://devblogs.microsoft.com/autogen/)
# AutoGen [](https://github.com/microsoft/agent-framework)
**AutoGen** is a framework for creating multi-agent AI applications that can act autonomously or work alongside humans.
> [!CAUTION]
> **⚠️ Project archived and no longer maintained**
>
> This project has been archived and is no longer actively maintained by Microsoft.
>
> Microsoft is not providing bug fixes, security fixes, new features, or support for this project. The repository remains available for historical/reference purposes.
>
> **Use archived repositories with caution.** Without ongoing maintenance or security fixes, vulnerabilities in this project and its dependencies may remain unaddressed, increasing the security risks of continued use. Carefully assess these risks before using AutoGen, particularly when handling sensitive data. AutoGen was developed for research and experimentation and as it transitions to archived, we continue to advise against production use.
>
> We thank the AutoGen community for the code, documentation, bug reports, ideas, and discussions that helped shape this project.
>
> New users should start with [Microsoft Agent Framework](https://github.com/microsoft/agent-framework). Existing users are encouraged to migrate using the [AutoGen → Microsoft Agent Framework migration guide](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-autogen/).
>
> Microsoft Agent Framework (MAF) is the enterprise‑ready successor to AutoGen. Microsoft Agent FrameworkAF in now available as a production-ready release: stable APIs, and a commitment to long-term support. Whether you're building a single assistant or orchestrating a fleet of specialized agents, Microsoft Agent Framework 1.0 gives you enterprise-grade multi-agent orchestration, multi-provider model support, and cross-runtime interoperability via A2A and MCP.
## Installation
AutoGen requires **Python 3.10 or later**.
```bash
# Install AgentChat and OpenAI client from Extensions
pip install -U "autogen-agentchat" "autogen-ext[openai]"
```
The current stable version can be found in the [releases](https://github.com/microsoft/autogen/releases). If you are upgrading from AutoGen v0.2, please refer to the [Migration Guide](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/migration-guide.html) for detailed instructions on how to update your code and configurations.
```bash
# Install AutoGen Studio for no-code GUI
pip install -U "autogenstudio"
```
## Quickstart
The following samples call OpenAI API, so you first need to create an account and export your key as `export OPENAI_API_KEY="sk-..."`.
### Hello World
Create an assistant agent using OpenAI's GPT-4o model. See [other supported models](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/models.html).
```python
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())
```
### MCP Server
Create a web browsing assistant agent that uses the Playwright MCP server.
```python
# First run `npm install -g @playwright/mcp@latest` to install the MCP server.
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StdioServerParams
async def main() -> None:
model_client = OpenAIChatCompletionClient(model="gpt-4.1")
server_params = StdioServerParams(
command="npx",
args=[
"@playwright/mcp@latest",
"--headless",
],
)
async with McpWorkbench(server_params) as mcp:
agent = AssistantAgent(
"web_browsing_assistant",
model_client=model_client,
workbench=mcp, # For multiple MCP servers, put them in a list.
model_client_stream=True,
max_tool_iterations=10,
)
await Console(agent.run_stream(task="Find out how many contributors for the microsoft/autogen repository"))
asyncio.run(main())
```
> **Warning**: Only connect to trusted MCP servers as they may execute commands
> in your local environment or expose sensitive information.
### Multi-Agent Orchestration
You can use `AgentTool` to create a basic multi-agent orchestration setup.
```python
import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.tools import AgentTool
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient
async def main() -> None:
model_client = OpenAIChatCompletionClient(model="gpt-4.1")
math_agent = AssistantAgent(
"math_expert",
model_client=model_client,
system_message="You are a math expert.",
description="A math expert assistant.",
model_client_stream=True,
)
math_agent_tool = AgentTool(math_agent, return_value_as_last_message=True)
chemistry_agent = AssistantAgent(
"chemistry_expert",
model_client=model_client,
system_message="You are a chemistry expert.",
description="A chemistry expert assistant.",
model_client_stream=True,
)
chemistry_agent_tool = AgentTool(chemistry_agent, return_value_as_last_message=True)
agent = AssistantAgent(
"assistant",
system_message="You are a general assistant. Use expert tools when needed.",
model_client=model_client,
model_client_stream=True,
tools=[math_agent_tool, chemistry_agent_tool],
max_tool_iterations=10,
)
await Console(agent.run_stream(task="What is the integral of x^2?"))
await Console(agent.run_stream(task="What is the molecular weight of water?"))
asyncio.run(main())
```
For more advanced multi-agent orchestrations and workflows, read
[AgentChat documentation](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html).
### AutoGen Studio
Use AutoGen Studio to prototype and run multi-agent workflows without writing code.
> **Caution**: AutoGen Studio is meant to help you rapidly prototype multi-agent workflows and
> demonstrate an example of end user interfaces built with AutoGen. It is **not meant to be a
> production-ready app**. Developers are encouraged to use the AutoGen framework to build their own
> applications, implementing authentication, security and other features required for deployed
> applications. See the [security note](https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/index.html#a-note-on-security) for more details.
```bash
# Run AutoGen Studio on http://localhost:8080
autogenstudio ui --port 8080 --appdir ./my-app
```
## Why AutoGen?
Pioneered in Microsoft Research, AutoGen opened the door to experimental multi-agent orchestration patterns that inspired the community. AutoGen is now archived and no longer maintained by Microsoft; the architecture described below remains available for historical/reference purposes. **For new projects, we recommend [Microsoft Agent Framework](https://github.com/microsoft/agent-framework)**, which builds on the lessons learned from AutoGen with enterprise-grade support.
The autogen _framework_ uses a layered and extensible design. Layers have clearly divided responsibilities and build on top of layers below. This design enables you to use the framework at different levels of abstraction, from high-level APIs to low-level components.
- [Core API](./python/packages/autogen-core/) implements message passing, event-driven agents, and local and distributed runtime for flexibility and power. It also support cross-language support for .NET and Python.
- [AgentChat API](./python/packages/autogen-agentchat/) implements a simpler but opinionated API for rapid prototyping. This API is built on top of the Core API and is closest to what users of v0.2 are familiar with and supports common multi-agent patterns such as two-agent chat or group chats.
- [Extensions API](./python/packages/autogen-ext/) enables first- and third-party extensions continuously expanding framework capabilities. It support specific implementation of LLM clients (e.g., OpenAI, AzureOpenAI), and capabilities such as code execution.
The ecosystem also supports two essential _developer tools_:
- [AutoGen Studio](./python/packages/autogen-studio/) provides a no-code GUI for building multi-agent applications.
- [AutoGen Bench](./python/packages/agbench/) provides a benchmarking suite for evaluating agent performance.
You can use the AutoGen framework and developer tools to create applications for your domain. For example, [Magentic-One](./python/packages/magentic-one-cli/) is a state-of-the-art multi-agent team built using AgentChat API and Extensions API that can handle a variety of tasks that require web browsing, code execution, and file handling.
For community support, visit our [Discord server](https://aka.ms/autogen-discord) or [GitHub Discussions](https://github.com/microsoft/autogen/discussions). Note that AutoGen is now community-managed and responses may be limited.
## Where to go next?
> **Starting a new project?** Head to [Microsoft Agent Framework](https://github.com/microsoft/agent-framework) for the latest multi-agent capabilities with long-term support.
>
> **Existing AutoGen user?** Use the [migration guide](https://learn.microsoft.com/en-us/agent-framework/migration-guide/from-autogen/) to transition, or refer to the resources below for current AutoGen documentation.
| | [](./python) | [](./dotnet) | [](./python/packages/autogen-studio) |
| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Installation | [](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/installation.html) | [](https://microsoft.github.io/autogen/dotnet/dev/core/installation.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/installation.html) |
| Quickstart | [](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/quickstart.html#) | [](https://microsoft.github.io/autogen/dotnet/dev/core/index.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/usage.html#) |
| Tutorial | [](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/tutorial/index.html) | [](https://microsoft.github.io/autogen/dotnet/dev/core/tutorial.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/usage.html#) |
| API Reference | [](https://microsoft.github.io/autogen/stable/reference/index.html#) | [](https://microsoft.github.io/autogen/dotnet/dev/api/Microsoft.AutoGen.Contracts.html) | [](https://microsoft.github.io/autogen/stable/user-guide/autogenstudio-user-guide/usage.html) |
| Packages | [](https://pypi.org/project/autogen-core/)
[](https://pypi.org/project/autogen-agentchat/)
[](https://pypi.org/project/autogen-ext/) | [](https://www.nuget.org/packages/Microsoft.AutoGen.Contracts/)
[](https://www.nuget.org/packages/Microsoft.AutoGen.Core/)
[](https://www.nuget.org/packages/Microsoft.AutoGen.Core.Grpc/)
[](https://www.nuget.org/packages/Microsoft.AutoGen.RuntimeGateway.Grpc/) | [](https://pypi.org/project/autogenstudio/) |
Interested in contributing? See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines. As AutoGen is in maintenance mode, contributions are limited to bug fixes, security patches, and documentation improvements. For feature development, consider contributing to [Microsoft Agent Framework](https://github.com/microsoft/agent-framework).
Have questions? Check out our [Frequently Asked Questions (FAQ)](./FAQ.md) for answers to common queries. Community support is available through [GitHub Discussions](https://github.com/microsoft/autogen/discussions) and the [Discord server](https://aka.ms/autogen-discord), though response times may vary as AutoGen is now community-managed. For actively supported tooling, see [Microsoft Agent Framework](https://github.com/microsoft/agent-framework).
## Legal Notices
Microsoft and any contributors grant you a license to the Microsoft documentation and other content
in this repository under the [Creative Commons Attribution 4.0 International Public License](https://creativecommons.org/licenses/by/4.0/legalcode),
see the [LICENSE](LICENSE) file, and grant you a license to any code in the repository under the [MIT License](https://opensource.org/licenses/MIT), see the
[LICENSE-CODE](LICENSE-CODE) file.
Microsoft, Windows, Microsoft Azure, and/or other Microsoft products and services referenced in the documentation
may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries.
The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks.
Microsoft's general trademark guidelines can be found at .
Privacy information can be found at
Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents,
or trademarks, whether by implication, estoppel, or otherwise.