Registry › Compare › Docling vs Unstructured

Docling vs Unstructured

Both are Grade A and 1.5 points apart, so choose on what you weigh most. Docling leads on maintenance and adoption; Unstructured leads on supply-chain integrity and transparency.

A Docling 89.5

Get your documents ready for gen AI

docling-project/docling · #30 overall · #1 Research & Data · coverage A (4/5)

Choose Docling if maintenance and adoption matter most.

+1.8Maintenance
+1.6Adoption: 871.6k weekly downloads against 718.6k

A Unstructured 88.0

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows…

Unstructured-IO/unstructured · #48 overall · #3 Research & Data · coverage A (4/5)

Choose Unstructured if supply-chain integrity and transparency matter most.

+2.2Safety / Integrity: 100% of recent commits signed, against 94%
+1.3Transparency: OSSF Scorecard 6.7 against 5.2

Where they differ

18.7

Safety / IntegrityUnstructured +2.2

20.9

12.9

TransparencyUnstructured +1.3

14.2

19.9

MaintenanceDocling +1.8

18.1

19.5

AdoptionDocling +1.6

17.9

+0.5

Runtime calibrationDocling +1.6

-1.1

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of Docling and Unstructured, two Research & Data projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	Doclingdocling-project/docling	UnstructuredUnstructured-IO/unstructured
HVTrust score	89.5	88.0
Evidence grade	A	A
Coverage grade	A	A
Overall rank	#30	#48
Rank in Research & Data	#1	#3
GitHub stars	69.0k	15.6k
Last updated	1d ago	1d ago
Build provenance	Yes	Yes
OSSF Scorecard	5.2 / 10	6.7 / 10
License	MIT	Apache-2.0
Downloads	872k/wk	719k/wk
Trust dimensions (points earned)
Safety / integrity / 25	18.7	20.9
Identity & provenance / 18	18.0	18.0
Transparency / 17	12.9	14.2
Maintenance / 20	19.9	18.1
Adoption / 20	19.5	17.9
Runtime capability surface (full matrix)
MCP server	Implemented	—
External providers	1 — OpenAI	7 — Amazon Bedrock, Google Gemini, OpenAI, …
Requires API keys	No	No
Plugin surface	plugins	—
Provenance drift	Unknown	Match

Open in the live compare tool → Docling profile Unstructured profile More Research & Data →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →