Docling

by Docling Project (IBM Research)

Converts PDF, DOCX, PPTX and more into Markdown or structured JSON, locally, for AI.

68.7 k stars GitHub MIT FreeOpen sourceLocal

View on GitHub →

What it does

Understands layout: tables, reading order, formulas
VLM mode with the granite_docling model for tough documents
Works offline, ideal for sensitive data

Install it

Requirements: Python 3

Install

pip install docling

Convert a document

docling https://arxiv.org/pdf/2206.01062

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install Docling (https://docling-project.github.io/docling/) on my machine.
1. Check the requirements: Python 3. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install: pip install docling
- Convert a document: docling https://arxiv.org/pdf/2206.01062
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.