skills.rest
reliefeai
reliefeaiCOMMUNITY
Explore all skills by this author →
GitHub

browser-relay

Control a local Chrome session via CLI and HTTP API for browsing and interaction.

120|15|Updated Apr 28, 2026
Search Tags:#browser automation#ai agents#mcp#authenticated browsing#dom snapshot#click type scroll#local http api
One-click install
npx skills add https://github.com/reliefeai/browser-relay --skill browser-relay
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-relay
Source: https://github.com/reliefeai/browser-relay/tree/main/skill
Command: npx skills add https://github.com/reliefeai/browser-relay --skill browser-relay

SYSTEM DOCUMENTATION & REQUIREMENTS

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.

Frequently Asked Questions about browser-relay

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate authenticated browsing with an AI agent using my existing Chrome session?▼

To automate authenticated browsing, Browser Relay connects an AI agent to your active local Chrome session, preserving your login state and cookies for interactions on protected web pages.

How do I extract structured page context from dynamic SPAs for AI agents?▼

Extract structured page context by generating an annotated DOM snapshot that highlights actionable markers like inputs, buttons, and links for dynamic single-page applications.

Can I run in-page JavaScript evaluation directly in the browser tab context?▼

Yes, you can evaluate JavaScript expressions directly in the active tab context to trigger dynamic behavior or perform quick data extraction on the current page.

Does browser automation with AI agents require a separate automation profile?▼

No, this approach uses your existing Chrome profile via a locally running relay bound to 127.0.0.1 and a connected extension, avoiding the friction of separate automation profiles.

How do I perform click, type, and scroll actions on a web page via a local HTTP API?▼

Perform click, type, and scroll actions by sending requests to the local HTTP API, which relays the commands to your connected Chrome tab to execute the interactions.

What are the limitations of using a local relay for browser automation?▼

The local relay requires a running instance bound to 127.0.0.1 and a connected Chrome extension, meaning it operates locally and is not designed for remote or headless server environments.

Related Skills

Explore More Software Engineering Skills→
hetaoBackendhetaoBackend
8

agentforge

Manage AI agent tasks via a local HTTP API and Python CLI.

Community
Advanced
nidhi-subrahnidhi-subrah

browser

Automate browser navigation, form filling, and data extraction using element references.

Community
Advanced
blocknaviblocknavi
1

convex-http-actions

Expose HTTP endpoints for Convex webhooks and external API calls.

Official
Advanced
garrytangarrytan
127.1k

setup-browser-cookies

Import browser cookies into a headless session for authenticated web testing.

Community
Intermediate