OSS Alternative - Discover Top Open Source Alternatives to Popular Software

alibaba/page-agent

An in-page JavaScript library enabling natural language control and automation of web interfaces directly within the browser.

Core Features

Easy integration as a pure JavaScript library, requiring no browser extensions or external dependencies.

Performs text-based DOM manipulation, eliminating the need for screenshots or multi-modal LLMs.

Supports integration with various Large Language Models (LLMs) of your choice.

Offers an optional Chrome extension for extending automation capabilities across multiple browser tabs.

Quick Start

npm install page-agent

Detailed Introduction

Page Agent is a powerful JavaScript library designed to bring AI-driven automation directly into web pages. It allows users to control web interfaces using natural language commands, simplifying complex workflows like form filling in ERP/CRM systems or building AI copilots for SaaS products. By operating entirely within the browser and relying on text-based DOM manipulation, it offers lightweight integration without the need for headless browsers or complex backend setups. Its flexibility to integrate with custom LLMs and an optional multi-page Chrome extension make it a versatile tool for enhancing web accessibility and automating browser tasks.