# Docling

> MIT local document parser that feeds PDFs and Office files into gen-AI pipelines

**Category:** Python  
**Pricing:** open-source  
**URL:** https://docling.ai  
**GitHub:** https://github.com/docling-project/docling  
**Added:** 2026-09-20

---

## The Hook

Docling turns messy PDFs, Office docs, and more into structured DoclingDocument export (Markdown/JSON/HTML) that agents and RAG stacks can actually use.

## What's Good

MIT (docling-project/docling). Strong PDF understanding (layout, reading order, tables, code, formulas), wide format coverage, local/air-gapped execution, and gen-AI ecosystem integrations. It is the practical document-ingestion primitive when agents must read real enterprise files, not only clean Markdown.

## The Catch

Vs MinerU and plain OCR pipelines: Docling is the broader multi-format DoclingDocument stack with gen-AI export paths — still expect GPU/CPU cost on heavy PDF batches and imperfect table recovery on ugly scans. Local models and extras increase install weight versus a thin Markdown converter.

## Verdict

MIT document AI for agent/RAG ingest. Default when PDFs and Office files must become structured context locally.