Docling (IBM)

27/100

Open-source (MIT) toolkit parsing docs into Markdown/JSON.

docling-project.github.io

// scorecard · 27/100

verified 1mo ago

methodology →

Agent-readiness14/35

Agent registration (none)0/9

Public API5/5

OpenAPI spec0/9

MCP server9/9

llms.txt0/3

Reliability & performance0/15

Actively maintained—

Production-ready0/4

Updated recently—

Pricing7/13

Itemized public pricing0/6

Free tier / trial4/4

Free-tier generosity3/3

Docs & DX2/12

Docs quality—

Public API2/2

Quickstart / examples0/2

Security & compliance0/12

SOC 20/6

ISO 270010/2

GDPR0/2

Security / trust page0/2

Openness4/10

Open source0/6

Open / un-gated API4/4

Company maturity0/3

Company size—

Years operating—

// rankings · cost per standard workload

#14 in Document Extractionnot comparable

Open-source (MIT) self-host; no hosted API/per-page price. Cost = your compute

github.com/docling-project

// overview

Docling simplifies document processing by parsing diverse formats including advanced PDF understanding and providing seamless integrations with the generative AI ecosystem. It offers a unified DoclingDocument representation, multiple export options like Markdown/HTML/JSON, OCR support, VLM integration, and audio ASR capabilities. The tool supports local execution, various document conversions, chunking, serialization, and plug-and-play integrations with frameworks such as LangChain and LlamaIndex.

// security & compliance

✗ SOC 2✗ ISO 27001✗ GDPR✗ HIPAA

// features

Parsing of multiple document formats (PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, audio, etc.)
Advanced PDF understanding including page layout, reading order, table structure, code, formulas, and image classification
Unified DoclingDocument representation with export to Markdown, HTML, JSON, and XML schemas
Local execution for sensitive data and air-gapped environments
OCR support and integration with Visual Language Models and ASR models
Integrations with LangChain, LlamaIndex, Crew AI, Haystack and MCP server connectivity