# Docling

> Updated 2026-08-25 · type: tool · category: data-scraping · status: active · rev 1

Document-processing toolkit with advanced PDF/DOCX/PPTX/XLSX understanding (tables, complex layouts) and generative-AI integrations — for when simple…

- Open source: yes (MIT)
- Self-hostable: yes
- Pricing model: free
- Best for: Developers and AI practitioners who need to parse diverse document formats and prepare them for generative-AI workflows, including local/air-gapped use.
- Last verified: 2026-09-04

- **Canonical:** https://gtmstacker.com/registry/tool/docling/
- **Source:** [github · docling-project/docling](https://github.com/docling-project/docling)
- **Tags:** data-scraping, document-processing, pdf, rag
- **Repository:** https://github.com/docling-project/docling

## Is Docling open source?

Yes — MIT-licensed.

## How much does Docling cost?

It is free to use.

## Can I self-host Docling?

Yes — it can be self-hosted.


---

Document-processing toolkit with advanced PDF/DOCX/PPTX/XLSX understanding (tables, complex layouts) and generative-AI integrations — for when simple PDF-to-text loses structure.

## Provenance

- MIT verified (65.9k★, active).
- Surfaced via the GTM Stacker X/Twitter signal reports (the "35 marketing repos" list + named drops); license independently WebFetch-verified 2026-09-03.