Control a Chrome browser directly from your code. Use the Chrome DevTools Protocol to reuse your existing login sessions. This helps you automate tasks like opening pages, taking snapshots, and extracting auth tokens.
First check if any Chrome windows are open. If not, launch a special debug version. Then send commands to open URLs, run JavaScript, or click buttons. Always ask for permission before closing the user's Chrome to prevent losing unsaved work.
This tool is great for developers who need to automate web tasks without logging in every time. It works on macOS, Linux, and Windows. Use simple command line tools to control the browser.
Global
mkdir -p ~/.claude/skills/browser-cdpProject
mkdir -p .claude/skills/browser-cdpSource Repository
Agent Browservercel-labs/agent-browser
Fast browser automation tool for AI agents to control any website
Just Scrapescrapegraphai/just-scrape
Search, scrape, crawl, and monitor web pages with an easy command line tool
Develop Userscriptsxixu-me/skills
Build and debug browser userscripts for Tampermonkey and ScriptCat
Browser Usebrowser-use/browser-use
Automate web testing, form filling, and screenshots with simple CLI commands
Firecrawlfirecrawl/cli
Search, scrape, and crawl websites with one simple command line tool
Playwright Climicrosoft/playwright-cli
Automate browser tasks and test web pages with simple terminal commands
Firecrawl Scrapefirecrawl/cli
Extract clean text from any webpage, even JavaScript-heavy sites, instantly
Agent Browserqu-skills/skills
Let your AI agent browse the web, click, type, and capture screenshots