Updated

Docling

Open-source library that parses PDFs and other document formats into structured data for AI/RAG pipelines.

27 open-source projects declare Docling in their code; no maker's live product we track uses it yet.

Open sourceSelf-hostable

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Docling

What Docling is used for

Document Parsing · Open-source library →Parsing PDFs and office files locally, with layout and table structure kept, at no cost.Trade-off: Runs on your CPU or GPU, and heavy PDFs are slow without a GPU.
Reducto11Unstructured1Carbon1Docling0MarkItDown0Makers' products on each, for document parsing

Docling vs the alternatives makers chose

OptionMakers' productsOpen source
Reducto11 85%No
Carbon1 8%No
Unstructured1 8%Yes
Docling0 0%Yes

For document parsing: how many of the 13 makers' products we know the document parsing of chose each option.

When to use Docling, and when not

Pick Docling if

Something else fits better if

  • You only need the text out of born-digital PDFs, fast and free: pypdf or pdf-parse or PyMuPDF.
  • Your inputs mix PDFs, emails, HTML and office files and you may move to a hosted API later: Unstructured.
  • Scans, dense tables or forms where a parsing error means a wrong answer: Reducto or LlamaParse or Mistral AI.
From each decision's guide, written from what makers' products chose and why.

How Docling itself is built

4 tools, from its own code, website and Product Hunt page.

Who uses it

No maker's live product on record yet, and 27 open-source projects that declare it in their code.

We haven't found a maker's live product that uses Docling yet — only the open-source projects below, which declare it in their code.

docutranslate
docutranslate文档(小说、论文、字幕)翻译工具(支持 pdf/word/excel/json/epub/srt...)Document (Novel, Thesis, Subtitle) T…Document ParsingIn its code · source ↗

Open source: a project that declares Docling as a dependency in its public code — verifiable, but not necessarily a live product.

What its projects tell coding agents

15 of the 24 open-source products built with Docling that were worked on in the last 180 days keep instruction files for coding agents — 63%, against 53% of all the projects we read. AGENTS.md is in 9, CLAUDE.md in 8.

1,144words in the median file
uvthe package manager most named, in 3 of 11 files
73%say how to test a change
Named more in these files than in other projects' — in how many of the 11:
What AGENTS.md files say about other tools →What open-source products tell their coding agents →

Alternatives to Docling

All alternatives by situation →

Questions makers ask about Docling

What are the alternatives to Docling?

For document parsing, the other options makers' products we track chose most are Reducto (11), Carbon (1), Unstructured (1). Open source or self-hostable among them: Unstructured. Each alternative, with the situation it fits, is on the Docling alternatives page.

When should you use Docling?

You want Markdown from many file types with one local tool (document parsing). Layout and tables matter and documents must stay on your own machines (document parsing). Something else fits better if: you only need the text out of born-digital PDFs, fast and free, pick pypdf or pdf-parse or PyMuPDF; your inputs mix PDFs, emails, HTML and office files and you may move to a hosted API later, pick Unstructured.

Is Docling open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Docling?

No llms.txt, official MCP server or CLI found yet.

Who uses Docling?

No maker's live product we track yet; 27 open-source projects declare it in their code. source ↗