agent-in-browser
Local installReal browser for any agent: Chrome/Edge/Brave via CDP, Firefox via BiDi. Refs, forms, console, net.
485 servers in Browser Automation
Real browser for any agent: Chrome/Edge/Brave via CDP, Firefox via BiDi. Refs, forms, console, net.
Windows computer use in the background: UI Automation and Win32 messages, every action read back.
Android computer use over plain ADB: screen, gestures, SMS, notifications, files. No root, no app.
Screenshots, PDFs, visual diffs and accessibility audits, returned inline so a model can see them
SHAFT browser automation, capture, and offline deterministic failure diagnosis
104 tools: drive YOUR real Chrome via CDP + browse/install/publish Threads in chat. webloom.run.
Open live web and mobile app sessions from an e2e project to inspect the app and try locators.
Let agents see and drive a Mac: screenshots, clicks, typing, apps and virtual displays.
Sealed X11/Wayland sessions to see, drive and check real GUI programs: a11y, pictures, sound.
Create, launch, check and drive Nullprint multi-profile browser profiles from any MCP agent.
Drive your real Chrome over MCP: real logins and cookies, multi-tab automation, deny-all by default.
Let your AI agent see, use and control the apps on your phone: screen as text, tap by label.
Read and act on Safari — history, tabs and reading list, writes off by default
Stealthy browser automation, testing, and web-scraping via CDP Mode.
Let AI agents see, tap, type, scroll, screenshot and debug your Expo app on a real phone.
Real Chromium browser for AI agents: compact outlines, diff-only replies, real input, you approve.
Native WebKit for Mac. Human approval and persistent sign-ins. Requires the companion app.
Accessibility-first desktop control for any agent: background input, agent pointer, zoom, Chrome.
Solve reCAPTCHA v2/v3/Enterprise, Turnstile, DataDome and image captchas from AI agents.
Computer use for Hyprland: semantic desktop state over IPC, plus vision and native input
See and drive Android emulators on a Mac: screenshot, tap, type, UI tree, logs, root.
Your AI agent decides what to enter. OpenAdapt enters it in the app and checks that it saved.
Let AI agents use your real Android phones safely, with permissions, approvals and an audit log.
Chrome automation via nodriver: 70 tools, isolated browsers, profiles and configurable startup.
Safe same-session CAPTCHA handoff and fresh-evidence resume for Browser Use and Playwright agents.
Control and debug Firefox: navigate, fill forms, inspect network and console, profile.
Drive Veilus browser profiles from an AI assistant: profiles, pages, scripts, schedules.
Native Swift macOS automation — 153 tools: AX, EventKit, voice, browser DOM, undo.
Local browser automation for AI agents: real-browser fetch, capture, smoke tests, cross-engine QA.
Let AI agents drive VS Code's built-in browser alongside you, with click-to-source.