What it does
Page Agent lets a website owner add an AI agent to their own web page with a single script. Visitors or staff can then type an instruction like "click the login button" or describe a long form-filling task, and the agent carries it out on the page.
It reads the page's text structure rather than taking screenshots, so it doesn't need special image-reading AI or browser permissions. It works with most mainstream AI models, including ones you run yourself.
Suggested uses include adding an AI copilot to business software, speeding up repetitive form filling and making web apps usable by voice. An optional Chrome extension handles tasks across several tabs, and a test MCP server lets other AI tools control the browser.
Who it's for
Web developers who want to add an AI assistant to their own site or app.
Can I use it without coding?
Developers only. Adding it to a site needs web development skills. A Chrome extension is also available. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Runs on
- Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Needed. An API key is a password-like code from an online AI service. What's that?
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
- More on staying safe