Plain-AyI
← All projects
Documents & knowledge

PixelRAG

Searches web pages and documents by how they look, using screenshots instead of extracted text.

Research-backedNew this week

What it does

Many AI tools answer questions by pulling text out of web pages. That often loses tables, charts and layout. PixelRAG instead turns pages, PDFs and images into screenshot tiles and searches those images directly.

It comes from university researchers, and its makers say this lets the AI read answers straight off tables and charts. A ready-made index of Wikipedia pages can be searched through a hosted service or in the browser.

It also offers a Claude Code plugin that lets Claude take a screenshot of a web page and read the image, so it sees pages the way a person does.

Who it's for

Developers and researchers building AI search or question-answering over web pages and documents.

Can I use it without coding?

Developers only. It's a Python package and command-line tool. There's also a browser demo to try it. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Web browser
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

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 (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it