Plain-AyI
← All projects
Documents & knowledge

Chandra

An AI model that reads scans and PDFs, including tables, forms and handwriting, and keeps the layout.

New this week

What it does

Chandra is an OCR model. OCR means turning pictures of text, such as scanned pages or PDFs, into text a computer can use. Chandra outputs Markdown, HTML or JSON and keeps track of where things sit on the page.

Its makers say it handles tables, maths, forms with checkboxes and handwriting well, and works in more than 90 languages. It can also pull out images and diagrams and add captions.

You can run it yourself, or use the makers' paid hosted service, which they say is more accurate than the open model.

Who it's for

Developers and researchers who need to turn large numbers of documents into clean, structured text.

Can I use it without coding?

Developers only. It is installed and run with Python commands; there is an optional simple web app for trying it. New to this? Start here.

Can I run it?

Cost
Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
Runs on
Linux, Server, Cloud
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

Try it

  1. Install Chandra with Python's package installer.
  2. Run it on a PDF or image to get structured text, or start its interactive app to 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