- Fix docs dotnet core typo
- Fix loading streaming Bedrock response with tool usage with empty argument
- Support linear memory in RedisMemory
- Fix message ID for correlation between streaming chunks and final mes…
- fix: extra args not work to disable thinking
- Add thinking mode support for anthropic client
AutoGen by Microsoft
Microsoft's open-source framework for multi-agent conversations and event-driven agent systems.
Use it in: API / SDK Works with: MCP Local models Multi-agent
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What AutoGen does
AutoGen is a multi-agent framework from Microsoft. You use it through a Python library and .NET library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from OpenAI, Azure, Anthropic, Google and Meta. It is used from Python and Csharp. It is free and open source (MIT); you pay only for the models it calls.
Status: Microsoft's README (2026-10-16) says AutoGen is archived and no longer maintained: no bug fixes, security fixes, new features or support; Microsoft Agent Framework is its successor.
Key facts
| Maker | Microsoft |
|---|---|
| Type | Multi-agent framework |
| License | MIT |
| Interfaces | Python library, .NET library |
| Main language | Python |
| Open issues and PRs | 1,186 |
Pricing
AutoGen is open source and free to use; you pay only for the models and infrastructure it runs on.
Checked Nov 9, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Where you use itPython library, .NET library
- Supports MCP?Yes
- Model providersopenai, azure, anthropic, google, meta, local
- Subagents / multi-agent?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain
AgentGid articles about AutoGen
Get started with AutoGen
| PyPI | pip install autogen-agentchat |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Add-ons for AutoGen: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for AutoGen or for agent frameworks in general. Savings and results depend on your workload.
AutoGen alternatives
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.1M | up 5.7% | down 2.7% | 150K+76/day | 1.5.22d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.1M | up 5.5% | up 29.2% | 45.1K+48/day | 1.2.23yesterday | Free (OSS) | |||
| 3 |
AI SDKVercel |
68 | 47.2M | up 3.9% | up 38.4% | 28.1K+30/day | 7.0.1772d ago | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
64 | 29.3M | up 5.9% | up 37.6% | 8,588+9/day | 0.2.185yesterday | Free (OSS) | |||
| 5 |
MastraMastra |
63 | 3.7M | up 14.9% | up 49.9% | 29.6K+23/day | 1.84.02d ago | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
62 | 7.2M | up 4.8% | up 38.9% | 30.8K+21/day | 0.25.02d ago | Free (OSS) | |||
Tools used with AutoGen
What 185 public GitHub projects that depend on AutoGen use with it, from their dependency files.
- python-dotenv73.5%
- AutoGen Extensions73.5%
- OpenAI Python Library61.6%
- Pydantic47.6%
- AutoGen Core44.9%
- Requests40.0%
- pandas40.0%
- NumPy36.8%
- tiktoken (Python)36.2%
- FastAPI30.3%
Used far more often here than in AI-built projects overall: what sets AutoGen projects apart.
- jsonref18.4% · 383.1×
- jiter18.4% · 41.0×
- tiktoken (Python)36.2% · 38.4×
- distro18.4% · 32.8×
- Protocol Buffers20.0% · 28.4×
- azure-identity17.3% · 25.2×
- OpenTelemetry API21.6% · 22.9×
- MarkupSafe15.1% · 21.0×
Ratings from people who use AutoGen
No ratings yet. Used AutoGen? Rate it and say what it is good and bad at.
What changed: recent AutoGen releases
- Update docs for 0.7.3
- Update readme with agent-as-tool
- Fix Redis Deserialization Error
- Redis Doesn't Support Streaming
- update version to 0.7.4
- Update doc 0.7.4
Earlier releases
- Update website for 0.7.2
- Typo in docs for 'NoOpTracerProvider'
- Fix MCP example in readme
- Extend pydantic model capability for anyOf/oneOf item typing
- Update README.md with correct stable version
- fix: Add proper serialization to RedisStore for complex objects
- Update website 0.7.1
- Update OpenAIAssistantAgent doc
- Update 0.7.1 website ref
- Remove assistant related methods from OpenAIAgent
- Make DockerCommandLineCodeExecutor the default for MagenticOne team
- Add approval_func option to CodeExecutorAgent
- Feat/OpenAI agent builtin tools 6657
- Supporting Teams as Participants in a GroupChat
- Adds Redis Memory extension class
- Upgrade_mcp_version
- Expand MCP Workbench to support more MCP Client features
- Upgrade GraphRAG to v2.3+
- Fix GraphFlow to support multiple task execution without explicit reset
- Fix GraphFlowManager termination to prevent \_StopAgent from polluting conversation context
- Add tool name and description override functionality to Workbench implementations
- Update documentation version
- Fix function calling support for Llama3.3
- Fix GraphFlow to support multiple task execution without explicit reset
AutoGen prices over time
AutoGen popularity and usage data
AutoGen was downloaded 102K times from PyPI in the week ending Nov 17, 2026, down 2.8% on the week before and up 14.7% over the last 30 days compared with the 30 before. The GitHub repository has 61.9K stars, 547 of them added in the last 30 days. The latest stable release is 0.7.5, published Sep 30, 2025. It was mentioned in 31 Hacker News posts and comments over the last 30 days.
Download the raw daily series: autogen.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
AutoGen FAQ
How much does AutoGen cost?
AutoGen is open source and free to use; you pay only for the models and infrastructure it runs on.
Is AutoGen open source?
Yes. AutoGen is open source, released under the MIT license.
How popular is AutoGen?
AutoGen was downloaded 102K times from PyPI in the week ending Nov 17, 2026, down 2.8% on the week before and up 14.7% over the last 30 days compared with the 30 before. The GitHub repository has 61.9K stars, 547 of them added in the last 30 days. The latest stable release is 0.7.5, published Sep 30, 2025.
What is the latest version of AutoGen?
The latest stable release we track is 0.7.5, published on Sep 30, 2025.
What are the alternatives to AutoGen?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of AutoGen badges, corrections
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: autogen-agentchat. GitHub: microsoft/autogen. See data sources for how each one is collected.