
Browser agents and cloud browsers for AI, with an MCP server for web tasks
- 7 tools
- Remote
- Freemium
- 121K GitHub stars
- Browser automation

Browser agents and cloud browsers for AI, with an MCP server for web tasks
Run recorded app workflows from your agent and check each save before moving on
Runs locally
Persistent memory for Claude Code, Codex and OpenCode, stored in SQLite on your machine
Runs locallyGive an assistant a cloud browser to scrape, search, crawl and audit pages
Turns websites into typed JSON tool calls that agents can search, read, log in and act on
Not checked yetCloud Android phones an AI agent can see, tap and drive, or hand a task in plain words
Not checked yetRun 56 web performance snippets in headless Chromium and read Core Web Vitals results
Runs locallyBuild, run, test and submit browser extensions to four stores from your AI agent
Not checked yetLocal MCP server for browser control and session recording for coding agents
Runs locallyVerify a running web app from inside: look, act, observe and assert, without screenshots
Runs locallyCloud browsers for AI agents, driven by MCP, Playwright, Puppeteer or plain-English tasks
Runs locallyLet an AI agent drive Android, iOS, TV and web apps, and save the steps as test suites
Runs locallyRead-only Playwright CI results for agents: new versus known failures and flaky tests
Runs locallyTurns websites into callable tools so agents skip the browser, with a cloud fallback
Not checked yetCloud and local browser agent for MCP clients, with encrypted logins and approval gates
Runs locallyTurns websites and signed-in accounts into callable APIs, run in the cloud or locally
Not checked yetLaunch and check mobile device simulations from an AI agent in your editor
Not checked yetBrowser API as agent tools: Markdown, screenshots, structured data, automation, crawls
Runs locallySee every kind of AI for browser automation: tools, agents, MCP servers and skills.Ranked: the best AI for browser automation.