AutoGen
✓ VerifiedOpen-source multi-agent framework (Python/.NET) with AgentChat and Studio
Pricing and features change frequently—confirm on the vendor site.
About
AutoGen is Microsoft's open-source framework for building agentic applications with your own model API keys. The current stable release (python v0.7.5, Sep 30 2025) ships a layered architecture: Core for event-driven message passing across Python and .NET runtimes, AgentChat for common multi-agent patterns, Extensions for model/tool connectors (OpenAI and Azure OpenAI, Anthropic, Gemini via OpenAI-compatible endpoints, and local models via Ollama), plus AutoGen Studio for no-code multi-agent prototyping and AutoGen Bench for evaluation. It's MIT-licensed and maintained in the open on GitHub.
Key Features
- ✓Layered Core, AgentChat, and Extensions architecture with event-driven agents
- ✓AutoGen Studio for visual multi-agent workflow building
- ✓AutoGen Bench and Magentic-One reference agents for evaluation and examples
- ✓Python and .NET SDKs with cross-language runtime
- ✓Supports OpenAI and Azure OpenAI, Anthropic (experimental), Gemini (OpenAI-compatible), and Ollama/local endpoints
- ✓Human-in-the-loop patterns and tool execution support
Use Cases
- →Multi-agent AI systems
- →Complex task automation
- →AI research projects
- →Collaborative AI workflows
- →Prototyping and evaluation with AutoGen Studio and Bench
Technical Details
Languages
AI Models
Integrations
Frequently Asked Questions
What is AutoGen?
AutoGen is Microsoft's open-source framework for building agentic applications with your own model API keys. The current stable release (python v0.7.5, Sep 30 2025) ships a layered architecture: Core for event-driven message passing across Python and .NET runtimes, AgentChat for common multi-agent patterns, Extensions for model/tool connectors (OpenAI and Azure OpenAI, Anthropic, Gemini via OpenAI-compatible endpoints, and local models via Ollama), plus AutoGen Studio for no-code multi-agent prototyping and AutoGen Bench for evaluation. It's MIT-licensed and maintained in the open on GitHub.
Is AutoGen free?
Yes, AutoGen is open source and free to use. MIT-licensed framework and tools, AutoGen Core, AgentChat, and Extensions packages, AutoGen Studio no-code multi-agent builder
What programming languages does AutoGen support?
AutoGen supports 2+ programming languages including Python, .NET.
What AI models does AutoGen use?
AutoGen is powered by OpenAI and Azure OpenAI models (GPT-4.1, GPT-4o family), Anthropic Claude (experimental), Google Gemini via OpenAI-compatible API, Local models via Ollama or OpenAI-compatible servers.
What platforms does AutoGen support?
AutoGen is available on macOS, Windows, Linux.
What can AutoGen do?
AutoGen provides AI chat, agentic/autonomous mode. Key features include: Layered Core, AgentChat, and Extensions architecture with event-driven agents, AutoGen Studio for visual multi-agent workflow building, AutoGen Bench and Magentic-One reference agents for evaluation and examples.
Pricing
Free (open source)
$0 (BYO model API keys)- •MIT-licensed framework and tools
- •AutoGen Core, AgentChat, and Extensions packages
- •AutoGen Studio no-code multi-agent builder
- •Works with OpenAI/Azure OpenAI, Anthropic (experimental), Gemini (OpenAI-compatible), and local models via Ollama
Company
- Name
- Microsoft
- Founded
- 1975
- Location
- Redmond, WA
Links
Similar Tools
Compare AutoGen with these alternatives
