p

page-agent

Page Agent is a JavaScript-based in-page GUI agent that controls web interfaces through natural language.

🇨🇳 DomesticFreeOpen sourceDev开源JavaScript自然语言控制
Platforms: WebBrowser extension
Region
Domestic
Pricing
Free
Open source
Yes
GitHub Stars
★ 18.3k
Source
GitHub
Added
2026-06-04
Last verified
2026-06-04
page-agent

Overview

Page Agent is a JavaScript-based in-page GUI agent that controls web interfaces through natural language. It addresses the need for manual operation of complex web workflows, enabling users to complete intricate tasks with simple text commands. Suitable for SaaS products, ERP systems, and similar scenarios, it can be integrated without rewriting backend systems.

Key features

  • Easy integration, requiring only JavaScript on the page
  • Text-based DOM manipulation
  • Supports custom LLMs
  • Optional Chrome extension for multi-page tasks

Use cases

SaaS AI CopilotIntelligent form fillingAccessibility supportMulti-page agent

Pros

  • No browser extension or Python required
  • No special permissions needed
  • Fast integration

Limitations / notes

  • Requires network connection
  • Free test API has usage limits

Who it's for

DevelopersProduct managersEnterprise usersAccessibility seekers

This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.

FAQ

How can I get started with Page Agent quickly?

Include the script via CDN or install via npm and instantiate a PageAgent object.

Do I need additional permissions?

No special permissions are required—only JavaScript on the page is needed.

Similar agents

Something wrong? Let us know on the About page and we'll fix it.