github.com
Browser Use
A framework for connecting AI agents to web browsers.
https://github.com/browser-use/browser-useAbout This Resource
A framework for connecting AI agents to web browsers. It provides browser interaction capabilities so agents can navigate pages and carry out tasks across websites.
Saved Notes
Original notes saved with this link. They may describe an earlier version.
GitHub - browser-use/browser-use: Make websites accessible for AI agents
Make websites accessible for AI agents 🤖.
Browser use is the easiest way to connect your AI agents with the browser.
Features
- Vision + html extraction
- Automatic multi-tab management
- Extract clicked elements XPaths and repeat exact LLM actions
- Add custom actions (e.g. save to file, push to database, notify me, get human input)
- Self-correcting
- Use any LLM supported by LangChain (e.g. gpt4o, gpt4o mini, claude 3.5 sonnet, llama 3.1 405b, etc.)
- Parallelize as many agents as you want