Browser use
A tool that lets Claude Code, Codex or Cursor use your own logged-in Chrome to browse, click, and download files for you.
What it is good for
- Downloading files from sites that require your login
- Clicking through web pages and filling in forms automatically
- Letting a coding agent work inside your everyday Chrome profile
- Automating repetitive browser tasks without rebuilding the setup each time
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Skill or plugin
- Tasks
- Works with
- Claude Code, Codex, Cursor, Chrome, Browser Use Cloud
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 18,813
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is Browser use free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use Browser use?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does Browser use work with?
- According to its own documentation, it works with Claude Code, Codex, Cursor, Chrome, and Browser Use Cloud.
- What is Browser use good for?
- Downloading files from sites that require your login, clicking through web pages and filling in forms automatically, letting a coding agent work inside your everyday Chrome profile, and automating repetitive browser tasks without rebuilding the setup each time.
Similar agents to Browser use
- agent-browser
agent-browser is a command-line tool that lets AI agents control a web browser to click, fill forms, and read pages for developers and automation builders.
- Lightpanda
Lightpanda is a headless browser (a browser with no window) that lets AI agents and automation scripts load web pages using little memory, for developers.
- OpenCLI
OpenCLI is a command-line tool that lets AI agents and people run browser tasks on any website using their logged-in Chrome for automation-minded users.
- web-access
web-access is a skill that gives a local AI agent full web access, including a real browser, for multi-step research and browsing tasks.
- BrowserAct Skills
BrowserAct Skills is a browser automation tool that lets AI agents control a real browser for web scraping and multi-account tasks.
- Unbrowse
Unbrowse is a tool that lets AI agents call a website's own APIs directly instead of driving a browser, making web tasks faster and cheaper for agents.