What problem does it solve? AI agents need a reliable way to interact with websites—navigating pages, filling forms, clicking buttons, and extracting data—without heavy dependencies like Playwright or Puppeteer. ## Core Features & Use Cases - Browser Automation via CDP: Control Chrome/Chromium directly 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 testing, and operate cloud browsers in Vercel Sandbox or AWS Bedrock AgentCore. - Session Management: Use sessions, an authentication vault, state persistence, and video recording for repeatable automation. - Use Case: Ask your agent to log into a web app, fill out a multi-step form, take a screenshot of the result, and extract the confirmation data for a QA report. ## Quick Start Install the CLI with npm, run agent-browser install, then ask your agent to load the core skill with agent-browser skills get core before automating any website.