What it does
This project adds an easy web interface to Browser Use, a tool that lets AI agents use websites. You type a task, and the AI controls a browser to complete it.
It works with many AI models, including those from Google, OpenAI, Anthropic and DeepSeek, as well as local models through Ollama. You can use your own browser, so you don't have to log in to sites again, and you can record the screen in high definition.
You can keep the browser window open between tasks to see the whole history of what the AI did.
Who it's for
People curious about AI that browses the web for them, and developers testing browser agents.
Can I use it without coding?
With some setup. Needs installing Python packages with a few commands. You also need an AI model key. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Mac, Windows, Linux, Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Download the project and set it up with Python, or run it with Docker.
- Add your AI provider's API key to the settings file, or use a local model through Ollama.
- Open the web page it starts and tell the AI agent what to do in the browser.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe