BeeAI is designed for a local-first experience - agents run directly on your laptop, giving you full control over your data and seamless integration with local inference engines like ollama.

The platform is built around several core components, illustrated in the diagram below:

​
Core Components

​
Agents

An agent is a lightweight container that communicates using the Agent Communication Protocol (ACP). Agents may also define tools to extend their capabilities.

BeeAI comes with several built-in agents. Browse the full list in our Agent Catalog.

​
BeeAI Server

Dive into the beeai-server source code.

The BeeAI server coordinates the platform:

  • Manages the lifecycle of agents (spawning and destroying containers)
  • Routes communication between agents and clients via the ACP interface
  • Handles agent configs and environment variables
  • Collects telemetry data and sends it to Arize Phoenix via OpenTelemetry (OTEL)

The server uses an official agent registry on GitHub to discover available agents.

​
BeeAI CLI and UI

Check out the beeai-cli and beeai-ui repositories.

BeeAI offers two main interfaces:

  • The CLI, for scripting and command-line control
  • The UI, for interacting through a graphical interface (e.g., chat or hands-off mode)

To start interacting with an agent: beeai run <name>

Or open the web interface at localhost:8333.

​
Python Client Integration

You can also integrate BeeAI into your Python applications using the ACP SDK. This makes it easy to coordinate multiple agents programmatically within your own workflows.

​
Monitoring and Observability

​
Arize Phoenix Integration

BeeAI supports observability through Arize Phoenix, an open-source tool for tracing agent behavior.

For more details, see our Observe Agents guide.