page-agent
A JavaScript GUI agent that controls web interfaces through natural language.
- Type
- MCP
- Transport
- http
- Open source
- Yes
- GitHub Stars
- ★ 19.2k
- Source
- mcp-github
- Repository
- github.com/alibaba/page-agent
Overview
Page Agent is a JavaScript-based in-page GUI agent that allows users to control web interfaces using natural language. It runs directly within the webpage without requiring browser extensions, Python environments, or headless browsers. Page Agent can be integrated into any webpage, providing intelligent form filling and accessibility features. Ideal for developers looking to enhance user experience and automate interactions.
Capabilities
- ▪Natural language control of web elements
- ▪No browser extension required
- ▪Supports multiple LLM models
- ▪Multi-page task support
Use cases
Setup
npm install page-agent
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How can I get started with Page Agent quickly?
You can include the script via CDN or install and initialize it using npm.
Does Page Agent support custom LLM models?
Yes, custom LLM models can be configured.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
antivibe
Transform AI-generated code into deep learning materials to help developers understand the code.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.