a11y-computer-use: accessibility-first computer use for AI agents. Pruned a11y-tree snapshots, element refs instead of pixel coordinates, a safety layer, an MCP server and CLI. macOS, Windows, Linux, and Chromium over CDP.
Multi-runtime automation infrastructure for AI agents. Native CDP browser control, metadata-driven Recipe system, and persistent Run context management.
🚇 A plugin-based MCP server for React Native runtime debugging, inspection, and automation. Connects to Metro bundler via Chrome DevTools Protocol — no app code changes needed for most features.
MCP server that connects AI assistants to Chrome DevTools Protocol for runtime debugging - set breakpoints, inspect variables, monitor network traffic, and automate browser interactions
Open-source Vibe Testing suite: an MCP server for the coding agent you already run, a VS Code review cockpit, and CI. Your agent explores your app and crystallizes each flow into a plain @playwright/test spec you own — record == replay, runs in CI with zero AI.
Stops Claude, Codex, and friends from stealing each other's Chrome tabs. Per-agent port + profile lanes. CLI + MCP server + live dashboard. Windows-first.
cuttle is a browser for your agent. Websites do not block it. It keeps your logins. When a website asks for a person, you can take control. It works with playwright-cli, agent-browser and browser-use.
🚇 CDP/Metro bridge for React Native development tooling. Provides target discovery, a WebSocket CDP session, a proxy multiplexer, a high-level bridge API, DevTools launcher, and an optional app-side client SDK.
Reversible theming runtime for AI desktop apps: CLI, app adapters, CDP injection, verification, store publishing. | AI 桌面应用换肤运行时:CLI、适配器、CDP 注入、验证与商店发布。
Drive Orca's embedded Chromium with Playwright (or raw CDP): multi-tab, device/media/offline emulation, and network mocking — by bridging its internal CDP proxy. Unofficial.