Key Features • Quickstart • Documentation • Agent Catalog
BeeAI is an open-source platform that makes it easy to discover, run, and share AI agents across frameworks. Built on the Agent Communication Protocol (ACP) and hosted by the Linux Foundation, BeeAI bridges the gap between different agent ecosystems.
Teams trying to operationalize AI agents face three critical challenges:
- Framework Fragmentation: Different agent frameworks create silos and duplicated efforts
- Deployment Complexity: Each agent requires its own setup, limiting scalability
- Discovery Challenges: No central hub exists for finding and using available agents
BeeAI provides a standardized platform to discover, run, and share agents from any framework - for both individuals and teams.
BeeAI makes it easy to experiment with agent capabilities on your own machine:
- 🧪 Try agents instantly from the community catalog without complex setup
- 📦 Use standard interfaces that create consistent user experiences
- 🛠️ Package existing agents from any framework using standardized containers
- 🌍 Share agents with others through a consistent web interface
As you scale from personal experimentation to team adoption, BeeAI grows with you:
- 🌐 Deploy a centralized BeeAI instance that the entire team can access
- 📚 Create a team catalog where developers publish and end users discover agents
- 🧰 Standardize agent interfaces for consistent user experiences
- 🔐 Centrally manage LLM connections to control costs and access
| Feature | How It Works | Business Value |
|---|---|---|
| Agent Catalog | One BeeAI platform serves your entire team | Everyone works from the same system with unified management |
| Framework Agnostic | BeeAI implements the Agent Communication Protocol (ACP) to standardize agent interfaces regardless of how they're built | Developers use their preferred tools while maintaining compatibility |
| Containerized Agents | Each agent runs in its own container with defined resource limits | Better performance, improved security, and efficient resource usage |
| Consistent Interfaces | Predictable agent interactions | Learn once, use everywhere |
| Agent Discovery | All agents appear in a searchable catalog with capability details | End users easily find agents and developers see usage patterns |
| LLM Provider Flexibility | Connect to any LLM provider | Use the best model for each task and easily switch providers |
Tip
This is the short version. See the installation guide for detailed instructions.
uv tool install beeai-cli- Start the BeeAI platform:
beeai platform start- Configure the LLM provider:
beeai env setup- Use the CLI:
# List all available agents
beeai list
# Run an agent interactively
beeai run chat
# Run an agent with direct input
beeai run chat "Hello! How are you?"
# Get agent details and parameters
beeai info chat
# View all CLI options
beeai --help- Launch the web interface:
beeai uiNote
The web UI is intentionally simplified for end-users who need basic agent interactions without CLI complexity. Think of the web UI as a deployment target for your agents, not your primary development environment.
Visit docs.beeai.dev for full documentation.
Visit beeai.dev/agents for the list of reference agent implementations.
The BeeAI 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 BeeAI Discord server.
Please note that our Code of Conduct applies to all BeeAI community channels. We strongly encourage you to read and follow it.
For information about maintainers, see MAINTAINERS.md.
Contributions to BeeAI 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 BeeAI.
Special thanks to the following outstanding projects for their inspiration and influence:
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.
