What problem does it solve? AI agents need a programmatic way to interact with websites—navigating pages, filling forms, clicking buttons, and extracting data—without relying on heavyweight frameworks like Playwright or Puppeteer. ## Core Features & Use Cases - Browser Automation via CDP: Controls Chrome/Chromium through the DevTools Protocol with accessibility-tree snapshots and compact element refs for reliable interaction. - Specialized Workflows: Covers Electron desktop apps (VS Code, Slack, Discord, Figma), Slack workspace automation, exploratory QA testing, Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. - Session & State Management: Provides sessions, an authentication vault, state persistence, video recording, and an observability dashboard on port 4848. - Use Case: Ask the 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 browser task.