browser-relay
CommunityControl your real Chrome with AI.
Software Engineering#browser automation#ai agents#mcp#authenticated browsing#dom snapshot#click type scroll#local http api
Authorreliefeai
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Browser Relay lets AI agents interact with the exact Chrome session you already use, avoiding the friction of automation profiles that lack your login state, cookies, and extensions.
Core Features & Use Cases
- Interact with login-protected web apps: click, type, scroll, and take screenshots in the same authenticated browser session.
- Get structured page context: generate an annotated snapshot of the DOM with actionable markers like inputs, buttons, and links.
- Run JavaScript in-page: evaluate expressions directly in the tab context for dynamic behavior and quick data extraction.
- Use for agent browsing: ideal for dynamic dashboards and SPAs where static fetchers can’t reliably render or access authenticated content.
Quick Start
In your AI chat, ask the browser-relay agent to list attached tabs, navigate to the target page if needed, take a snapshot of the page, then click or type into the appropriate elements and confirm the result with another snapshot.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: browser-relay Download link: https://github.com/reliefeai/browser-relay/archive/main.zip#browser-relay Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.