Magentic-UI is a research prototype from Microsoft that provides a human-centered interface for web automation using multi-agent systems. Built on AutoGen, it features specialized agents (Orchestrator, WebSurfer, Coder, FileSurfer) that work together to browse websites, execute code, and handle files. Key features include collaborative planning, real-time task monitoring, action guards for sensitive operations, and parallel task execution. The system supports OpenAI, Azure OpenAI, and Ollama models, requires Docker for operation, and has been evaluated on benchmarks like GAIA (42.52%) and WebVoyager (82.2%). Installation is available via PyPI or from source, with comprehensive documentation for setup and configuration.
Table of contents
Quick Navigation:🟪 How it Works🛠️ Installation⚠️ Troubleshooting🤝 Contributing📄 License3 Comments
Sort: