Browser Use is an open-source library that lets an AI agent operate a real web browser to finish a task you describe in words.
In plain words
Many jobs live behind websites with no API. Browser Use connects a language model to a real browser. You give the agent a task in plain language, and it works through the web to get the result. The Python library runs inside your own code, with the model you pick and either a local browser or a cloud one. The same team also sells a hosted agent service and cloud browsers.
A quick example
The project's own starter code creates an agent whose task is to count the stars on the browser-use repository, runs it, and prints the final answer. By default it uses the team's hosted model and a cloud browser, but you can pass your own model and a fresh local Chrome instead.
Where you'll meet it
- Agents that complete tasks on websites.
- Automating your own browser tasks from a command line.
- Hosted browser agents called through an API.
Related
Sources
- Docsbrowser-use/browser-use, Browser Use (GitHub) · read 13 Nov 2026
- DocsQuick start, Browser Use documentation · read 9 Nov 2026
- Docsbrowser-use README, Browser Use (GitHub) · read 13 Nov 2026
Checked by WhatIsAI against the sources above · 13 Nov 2026. Spotted an error? Report it.