Overview
chrome-bridge is a tool that allows AI agents to control the user's existing Chrome browser, including their logged-in profile, open tabs, cookies, and SSO sessions. It consists of a small Chrome extension and a zero-dependency Node CLI. The extension connects over WebSocket to a local Node server, and any agent that can run shell commands can drive the browser via the CLI. The bridge provides commands such as snap, click, fill, and shot, and uses accessibility-tree snapshots with element references for actions. Tabs controlled by the bridge display a purple pill that narrates the agent's actions, and the human can release tabs at any time. The tool is designed to work with any AI agent, including Claude Code, Cursor, Qwen, and GLM, without requiring an MCP-capable client or server configuration.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use chrome-bridge to let AI agents interact with web pages using accessibility snapshots and element references.
- Teams use chrome-bridge to click on elements by reference.
- Teams use chrome-bridge to fill in form fields.
- Teams use chrome-bridge to take screenshots of pages.
- Teams use chrome-bridge to set a repository's social preview image via the CLI.
- Teams use chrome-bridge to drive the browser from a script, a cron job, or a terminal.
Features
AI assistant
Natural language interface
Workflow automation
Reviews
No reviews yet. Be the first to share your experience!