Page Agent: In-Page GUI Agent for Controlling Web Interfaces via Natural Language

Repositoryalibaba/page-agentTool

Alibaba's Page Agent is a TypeScript library that enables natural-language control of web pages directly inside the browser. Loaded as a single JavaScript script, it executes actions through text-based DOM manipulation without requiring headless browsers, Python backends, or screenshots.

Key points

  1. Direct in-page execution: Operates without requiring browser extensions, Python, or headless browser environments.
  2. Text-based DOM manipulation: Functions without screenshots or multimodal vision models, avoiding elevated permissions.
  3. Bring your own LLM: Compatible with mainstream proprietary models as well as locally deployed LLMs.
  4. Optional extension: Offers an optional Chrome extension for additional use cases.

Why it matters

Traditional browser automation frameworks typically require external processes like Playwright or resource-heavy visual recognition pipelines. By embedding the agent logic directly into client-side JavaScript, Page Agent lowers the barrier to adding conversational agent controls to web apps.

Analysis

Targeted at frontend and web developers, Page Agent eliminates server-side browser infrastructure by executing DOM operations directly in the browser context. Bypassing visual multimodal processing keeps inference simpler and token costs lower. With nearly 29,000 GitHub stars, 2,500+ forks, CI integration, an npm package, and a Chrome Web Store listing, the project demonstrates strong traction and a solid open-source foundation.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:Tencent/BrowserSkill

    BrowserSkill: Browser Automation for AI Agents Using Logged-In Sessions

    Tencent has open-sourced BrowserSkill, a tool linking shell-capable AI agents to real Google Chrome or Microsoft Edge instances via a CLI and extension, enabling agents to leverage existing logins without interrupting daily work.

    7kstarsTypeScript

    AI & LLMs· Tool

  • Repository:citrolabs/ego-lite

    ego lite: A Browser Designed for Shared Use Between Humans and AI Agents

    ego lite is an open-source browser built for macOS that allows users to share their active logged-in sessions with AI agents such as Claude Code or Codex. It isolates agent automation tasks into dedicated Spaces, enabling background execution without disrupting the user's open tabs.

    15.1kstarsJavaScript

    AI & LLMs· Tool

  • Repository:Podcast72/showroom-la-finestra-webmcp

    WebMCP: In-Browser Agent Interface Layer via document.modelContext

    The showroom-la-finestra-webmcp repository demonstrates how existing websites can expose structured business knowledge and safe actions directly to AI agents without running a separate MCP server. By using an in-browser layer via `document.modelContext`, the website explains itself rather than relying on DOM scraping.

    1starsJavaScript

    AI & LLMs· Resource

  • Repository:captivus/chrome-agent

    chrome-agent: Direct CDP Control for AI Coding Agents

    chrome-agent is a CLI tool and Python library giving AI coding agents direct browser inspection and interaction via the Chrome DevTools Protocol (CDP). It avoids restrictive abstraction layers and enables concurrent, isolated use by multiple agents and human operators.

    243starsPython

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.