Plain-AyI
← All projects
Documents & knowledge

Docling

Converts PDFs, Word files, slides and more into clean text that AI tools can read.

Research-backed

What it does

AI tools work best with clean, well-structured text. Docling takes documents in many formats, including PDF, Word, PowerPoint, Excel, web pages, e-books, emails, images and even audio, and turns them into tidy formats such as Markdown or JSON.

It pays special attention to PDFs. It works out page layout, reading order, tables, formulas and images, and can read text from scanned pages (OCR, optical character recognition).

It can run entirely on your own computer, which its makers point out is useful for sensitive data. It also connects to popular AI frameworks and to AI assistants through MCP, a standard way to plug tools into AI apps.

Who it's for

Developers and data teams preparing documents for AI search, chat or analysis.

Can I use it without coding?

With some setup. Installed with one Python command and run from the command line; deeper use needs Python code. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Windows, Linux
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Install Docling with Python on a Mac, Windows or Linux computer.
  2. Give it a document file or web address, and it creates a clean text version in Markdown.

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.
  • More on staying safe

Where people are talking about it