AI Agent Platforms / All platforms / Browser Use
Browser Use
Python library that lets AI agents control a web browser to complete online tasks.
Browser Use is a Python library that lets an AI agent use a web browser the way a human does: opening pages, clicking buttons, typing, and filling forms. Developers install it as a pip package and drive tasks with natural language instructions; a hosted cloud version is also offered.
| Category | Browser agents |
| License | MIT |
| Hosting | self-hosted; vendor cloud available |
| Repository | github.com/browser-use/browser-use |
| Website | docs.browser-use.com |
| Last verified | 2026-09-02 |
Documented features
- Controls a browser to open pages, click, type, and fill forms
- Runs tasks from natural language instructions
- Fills out forms such as job applications from provided data
- Extracts structured data from pages and exports it, for example to CSV
- Installs as a Python package (pip or uv) on Python 3.11+
- Works with LLM API keys from OpenAI, Google, Anthropic, or Browser Use Cloud
- Cloud offering adds proxy rotation, CAPTCHA solving, and parallel execution
- Cloud offering provides 1000+ integrations and persistent storage
Feature summaries come from the project's own repository and documentation and describe the software as documented on the verification date, not an evaluation.