This project provides a desktop application for controlling a local Chrome browser with AI agents, making websites accessible for automated interaction. It targets developers and researchers looking to integrate LLMs with web browsing capabilities, offering a user-friendly interface and broad LLM support.

How It Works

The application leverages Electron for its desktop UI and Gradio for interactive elements, building upon the browser-use library. It allows AI agents to directly interact with a user's existing Chrome browser instance, preserving login states and cookies. This approach avoids the complexities of managing separate browser environments or authentication challenges.

Quick Start & Requirements

• Primary install/run command:

  git clone https://github.com/browser-use/desktop
  cd desktop
  npm install
  vite dev
  

• Prerequisites: Node.js, Google Chrome browser.
• Setup time: Estimated 5-10 minutes.

Highlighted Details

• Expanded LLM Support: Integrates with Google, OpenAI, Azure OpenAI, Anthropic, DeepSeek, Ollama, and more.
• Custom Browser Support: Utilizes existing Chrome profiles, retaining login sessions and cookies.
• High-Definition Screen Recording: Supports HD screen recording for agent interactions.

Maintenance & Community

No specific contributors, sponsorships, or community links (Discord/Slack) are mentioned in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial or closed-source use is undetermined.

Limitations & Caveats

Desktop application downloads for macOS, Windows, and Linux are listed as "Coming soon." The project appears to be in an early development stage with no explicit versioning or release history provided.