Docling

Open-source document conversion library that turns PDFs, Office files and audio into structured data.

Infrastructure by Docling project (LF AI & Data)

IndexedMIT★ 69,507

Install

Pick your client. Read the repository before you give any tool access to your data.

pip install docling

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Docling parses PDF, DOCX, PPTX, XLSX, HTML, images and audio into one document model, and exports to Markdown, HTML, JSON and other formats. It includes advanced PDF understanding for layout, reading order and tables, plus OCR for scanned files. It runs locally and offline, can run as an API server, and integrates with LangChain, LlamaIndex, CrewAI and Haystack.

Use cases: document-processing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: RAG and data · parsing
Self-host: Yesraw.githubusercontent.com
Open source: Yesdocling.ai
Works with: langchain, llamaindex, crewai, haystackraw.githubusercontent.com
Protocols: mcp, restraw.githubusercontent.com

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 69,507
Forks: 5,170
Open issues: 704
Last commit: Oct 23, 2026 (2 days ago)
Last release: Oct 23, 2026 (3 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Packages: pypi docling
License: MIT
Repository: github.com/docling-project/docling
Website: www.docling.ai
Docs: docling-project.github.io/docling/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Docs Website github-graphql

Cite this page

Docling. Agent Mart. https://agentmart.dev/infrastructure/docling (last updated 2026-10-24)