# Browser Use CLI The Browser Use CLI (`browser-use`) is a command-line interface for the [[Browser Use]] platform. It provides two main capabilities: **Direct browser control**: navigate pages, click elements, fill forms, upload files, take screenshots, and run JavaScript. Supports three browser modes: managed headless Chromium, real Chrome with existing user profiles and logins, and cloud-hosted browsers via the Browser Use Cloud API. **Cloud platform management**: a generic REST passthrough to the Browser Use API (v2 and v3) for managing agent tasks, cloud browser sessions, profiles, workspaces, files, skills, and billing. The CLI uses a multi-session daemon architecture. The first command starts a background daemon that keeps the browser alive, and subsequent commands communicate via Unix socket (or TCP on Windows) with ~50ms latency. Each session gets its own daemon, socket, and PID file in `~/.browser-use/`. The core browser workflow is: navigate to a page, run `state` to get numbered element indices, then interact using those indices. It also supports persistent [[Python]] sessions for scripting, cookie management, tab management, JavaScript execution, and Cloudflare tunnels for exposing local dev servers to cloud browsers. It ships with a companion skill for coding agents (Claude Code, Cursor, Copilot) that provides full command context. ## References - https://docs.browser-use.com/open-source/browser-use-cli - https://github.com/browser-use/browser-use ## Related - [[AI Agents Web Browsing]] - [[Browser Use]] - [[Vercel Agent Browser]] - [[Playwright]] - [[Python]] - [[AI Agents]] - [[AI Agent Skills]]