skills.rest
BermudaLocals
BermudaLocalsCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

page-agent

Embed a client-side JavaScript GUI agent that drives web interfaces via natural language.

1|1|Updated Apr 26, 2026
Search Tags:#ui#javascript#ai#web#copilot#embed#page-agent
One-click install
npx skills add https://github.com/BermudaLocals/hermes-agent-lite --skill page-agent-bermudalocals
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: page-agent
Source: https://github.com/BermudaLocals/hermes-agent-lite/tree/main/optional-skills/web-development/page-agent
Command: npx skills add https://github.com/BermudaLocals/hermes-agent-lite --skill page-agent-bermudalocals

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Embed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that lets end-users drive the UI with natural language ("click login, fill username as John"). No Python, no headless browser, no extension required. Use this skill when the user is a web developer who wants to add an AI copilot to their SaaS / admin panel / B2B tool, make a legacy web app accessible via natural language, or evaluate page-agent against a local (Ollama) or cloud (Qwen / OpenAI / OpenRouter) LLM. NOT for server-side browser automation — point those users to Hermes' built-in browser tool instead.

Core Features & Use Cases

  • In-page GUI agent written in TypeScript. It lives inside a webpage, reads the DOM as text (no screenshots, no multi-modal LLM), and executes natural-language instructions like "click the login button, then fill username as John" against the current page. Pure client-side — the host site just includes a script and passes an OpenAI-compatible LLM endpoint.
  • Path 1 — CDN/demo, Path 2 — npm install for production, Path 3 — clone the source for hacking on it. This enables quick evaluation, production integration, or contributor workflows.
  • Security & scope: client-side operation with flexible LLM provider options; not intended for server-side browser automation.

Quick Start

Install page-agent in your web app and initialize the panel to drive the UI with natural language.

Frequently Asked Questions about page-agent

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

FAQPage Schema
How do I add an AI copilot to my web application for natural language UI control?▼

Add an AI copilot to your web app by embedding a pure JavaScript in-page GUI agent via a script tag or npm package. The agent reads the DOM as text and executes natural language instructions entirely client-side.

Can I use a local LLM with an in-page GUI agent instead of cloud APIs?▼

Yes, you can use a local LLM with an in-page GUI agent. The client-side component connects to any OpenAI-compatible LLM endpoint, allowing you to evaluate page automation against local models like Ollama or cloud providers.

Does the in-page GUI agent require screenshots or multi-modal LLMs to understand the web interface?▼

No, the in-page GUI agent does not require screenshots or multi-modal LLMs. It operates entirely client-side by reading the DOM as text to understand and interact with the web interface.

What is the best way to drive a SaaS dashboard or legacy web app using natural language?▼

The best way to drive a SaaS dashboard or legacy web app with natural language is using a client-side TypeScript GUI agent. It executes instructions like "click login" directly within the browser without needing Python or a headless browser.

Is a client-side in-page GUI agent suitable for server-side browser automation?▼

No, a client-side in-page GUI agent is not suitable for server-side browser automation. It is designed specifically for client-side operation within web applications to let users instruct the UI with natural language.

How do I embed an AI-driven agent in a web app using a single script tag?▼

Embed an AI-driven agent in a web app by installing the pure JavaScript component via a single script tag or npm package. You then initialize the panel and pass an OpenAI-compatible LLM endpoint to enable natural language UI control.

Related Skills

Explore More Software Engineering Skills→
zeronx798zeronx798

page-agent

Integrate a TypeScript-based GUI agent for natural language DOM manipulation.

Community
Advanced
Rawgrowth-ConsultingRawgrowth-Consulting

page-agent

Embed a TypeScript UI panel that drives DOM interactions via natural language.

Official
Intermediate
RheasilviaRheasilvia

page-agent

Embed a natural-language GUI copilot into web applications to automate DOM-based interactions.

Community
Intermediate
githubgithub
4.9k

gh-agent-task

Create GitHub Copilot-driven agent tasks from natural language via the gh-agent-task CLI extension.

Official
Intermediate