P
Page Agent
JavaScript in-page GUI agent. Control web interfaces with natural language.
open-sourcebrowser-web-agents
29.3k
Stars
+2441
Stars/month
59
Commits (90d)
10
Releases (6m)
Star Growth
+7.3k (33.3%)estimated from velocity
Overview
Page Agent is a JavaScript library that adds an AI agent directly into web pages to control interfaces via natural language. It works with mainstream LLMs and offers optional Chrome extension and MCP server features for multi-page tasks.
Deep Analysis
Key Differentiator
Provides in-page JavaScript agent functionality without requiring browser extensions, Python, or headless browsers.
⚡ Capabilities
- • In-page JavaScript agent
- • Text-based DOM manipulation
- • Natural language web control
- • Multi-page task support via extension
🔗 Integrations
Most mainstream LLMsLocally deployed modelsChrome extensionMCP Server (Beta)
✓ Best For
- ✓ Adding AI copilots to SaaS products
- ✓ Smart form filling in web apps
- ✓ Accessibility through natural language commands
✗ Not Ideal For
- ✗ End-user AI applications
- ✗ Non-web-based agent systems
- ✗ Image generation or content creation
⚠ Known Limitations
- ⚠ Browser-based only
- ⚠ Requires JavaScript integration
- ⚠ Text-based DOM manipulation only
Alternatives
B
Browser-Use
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
B
BrowserGPT
Command your browser with GPT
T
Taxy AI
Automate your browser with GPT-4
L
LaVague
Large Action Model framework to develop AI Web Agents
Compare Page Agent
Maintain Page Agent?
Show your live rank in your README, or put Page Agent in front of every visitor to AgentoolRank.