QwebBridge gives AI agents full control over your real Chrome browser — navigate, click, fill forms, screenshot, and extract data using your own login sessions.
A three-layer pipeline connects your AI agent to your real browser through Chrome DevTools Protocol.
Everything an AI agent needs to browse the web, interact with pages, and extract information.
Navigate to any URL. Opens new tabs with session-based grouping and auto-load waiting.
Get the full accessibility tree with @eN refs for reliable element targeting.
Capture screenshots in PNG, JPEG, or WebP. Supports full-page and element capture.
Click elements by CSS selector or accessibility ref. Auto-scrolls into view.
Fill forms, textareas, and rich editors (ProseMirror, Lexical, Slate, Quill).
Run arbitrary JavaScript in the page. Supports async/await.
Real mouse event dispatch at element coordinates.
Type text character by character via CDP.
Keyboard shortcuts with modifier keys — Control, Alt, Shift, Meta.
Upload files to inputs. Supports multiple files.
Monitor network requests — start, stop, list, inspect.
Find an open tab by URL. Target active tab or first match.
List all open tabs with URL, title, and session group.
Close the current tab or a specific tab by ID.
Close all tabs in an AI session — one command cleanup.
Render page to PDF with configurable format and scale.
From automated testing to AI-powered research — if you can do it in a browser, your AI agent can too.
Have your agent search, read, and compile information from hundreds of pages automatically.
Pull structured data from SaaS dashboards, CRM systems, and internal tools — APIs not required.
Run end-to-end tests through real browser sessions with full network monitoring.
Automate repetitive browser tasks: form filling, file uploads, multi-step approvals.
Track prices, job listings, product changes, and competitor moves as they happen.
Let your agent handle login forms, job applications, and vendor portals.
Connect your preferred coding agent through the protocol that fits your workflow.
Kimi WebBridge compatible protocol. Connect any agent that speaks WebSocket.
ws://localhost:10086/selector/commandStandard MCP server for Claude Desktop, Cursor, Windsurf, and any MCP client.
qweb-bridge mcpSimple HTTP POST interface for custom scripts and integrations.
POST /api/tool/<name>Direct terminal access for quick browser automation from your shell.
qweb-bridge <command>One-curl install or build from source — pick your path. Prerequisites: Chrome browser and Node.js ≥ 18.
Run qweb-bridge start or node packages/daemon/dist/cli.js run. The daemon listens on localhost:10086.
Open chrome://extensions, enable Developer mode, click "Load unpacked", and select packages/extension/dist.
Point your agent to ws://localhost:10086/selector/command (WebSocket) or run qweb-bridge mcp (MCP).
Run qweb-bridge status — you should see extensions_connected: true. Your agent is ready to browse.
localhost:10086, which forwards them to the Chrome extension. The extension uses Chrome DevTools Protocol (CDP) to control the browser — navigating, clicking, screenshotting, and reading pages. Everything runs locally on your machine.SKILL.md that AI agents can auto-discover.localhost only. No browser data, login sessions, cookies, or page content ever leaves your machine. The daemon is not accessible from external networks. QwebBridge is fully self-hosted and open source — you control everything.pnpm install && pnpm build, then start with node packages/daemon/dist/cli.js run. Load the extension from packages/extension/dist in Chrome via chrome://extensions with Developer mode enabled. See the install section above for step-by-step instructions.tabs, debugger, storage, alarms, tabGroups, windows, and host permissions for <all_urls>. These are necessary for CDP-based browser control and tab management. All data stays local.