What problem does it solve? AI agents need a reliable way to interact with websites and desktop apps—navigating pages, filling forms, clicking elements, and capturing screenshots—without heavy dependencies like Playwright or Puppeteer. ## Core Features & Use Cases - Browser Automation via CDP: Control Chrome/Chromium through the DevTools Protocol with accessibility-tree snapshots and compact element refs for reliable interaction. - Specialized Workflows: Automate Electron desktop apps (VS Code, Slack, Discord, Figma), manage Slack workspaces, run exploratory QA and dogfooding sessions, or derive API clients from recorded HAR files. - Cloud & Sandbox Support: Run browser automation inside Vercel Sandbox microVMs or AWS Bedrock AgentCore cloud browsers. - Use Case: Ask your AI agent to log into a web app, fill out a signup form, take a screenshot of the result, and extract the confirmation data—all through CLI commands. ## Quick Start Install the CLI with npm i -g agent-browser, run agent-browser install, then load the workflow guide with agent-browser skills get core before automating any website.