Browser-Use
lastmod 2024-11-11created 2024-11-111 edits
Open-Source Web Automation library with any LLM
Features
- A library that helps LLMs interact with websites through a simple interface
- Universal LLM support - works with every language model supported by LangChain
- Interactive element detection - automatically finds interactive elements on the page
- XPath extraction for scraping - no more manual inspection in DevTools
- Vision model support - processes visual page information
- Customizable actions - you can add your own browser interactions (e.g., adding data to a database the LLM can use)
- Dynamic content handling - no need to worry about cookies or content changes
- Chain-of-thought with memory - can solve Long-Term Tasks
- Self-correction - if the LLM makes a mistake, the agent corrects its own actions
- Usage examples
- "Go to hackernews on show hn and give me top 10 post titles, their points and hours. Calculate for each the ratio of points per hour"
- "Search the top 3 AI companies 2024 and find what out what concrete hardware each is using for their model."
- "Go to kayak.com and find a one-way flight from Zürich to San Francisco on 12 January 2025"