# OWL

A multi-agent framework built on the CAMEL-AI framework for automating real-world tasks, coordinating several AI agents that use tools such as browsers and MCP servers to complete work.

OWL is a framework for multi-agent collaboration, built on top of the CAMEL-AI framework, aimed at automating real-world tasks by coordinating multiple AI agents.

It installs with uv, pip in a virtual environment, conda, or Docker, and configures models through environment variables or a .env file. Agents reach external capabilities through toolkits, including the Model Context Protocol and a Playwright-based browser toolkit, and support both multimodal and text-based tasks.

A web interface is included for running and monitoring tasks. It is written in Python and depends on the CAMEL-AI framework for its underlying agent implementation.

Website: https://github.com/camel-ai/owl