Registry › Compare › Docling vs Feynman

Docling vs Feynman

Docling leads on trust: 89.7/100 (Grade A) against 72.9/100 (Grade B), a 16.8-point gap. Docling leads on supply-chain integrity and transparency, and rests on broader evidence.

A Docling 89.7

Get your documents ready for gen AI

docling-project/docling · #24 overall · #1 Research & Data · coverage A (4/5)

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

+10.1Safety / Integrity: 95% of recent commits signed, against 24%
+4.4Transparency
+4.2Adoption: 828.5k weekly downloads against 19k
A vs BEvidence coverage: 4 of 5 independent signal types, against 3

B Feynman 72.9

The open source AI research agent.

Companion-Inc/feynman · #285 overall · #6 Research & Data · coverage B (3/5)

Feynman doesn't lead on any scored dimension in this pair.

Where they differ

18.8

Safety / IntegrityDocling +10.1

8.7

12.9

TransparencyDocling +4.4

8.5

19.5

AdoptionDocling +4.2

15.3

+0.5

Runtime calibrationFeynman +1.9

+2.4

2 dimensions identical: Identity 18.0 · Maintenance 20.0 · Full evidence table

An independent, evidence-based trust comparison of Docling and Feynman, 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	FeynmanCompanion-Inc/feynman
HVTrust score	89.7	72.9
Evidence grade	A	B
Coverage grade	A	B
Overall rank	#24	#285
Rank in Research & Data	#1	#6
GitHub stars	68.6k	9.9k
Last updated	today	today
Build provenance	Yes	Yes
OSSF Scorecard	5.2 / 10	—
License	MIT	MIT
Downloads	829k/wk	19k/wk
Trust dimensions (points earned)
Safety / integrity / 25	18.8	8.7
Identity & provenance / 18	18.0	18.0
Transparency / 17	12.9	8.5
Maintenance / 20	20.0	20.0
Adoption / 20	19.5	15.3
Runtime capability surface (full matrix)
MCP server	Implemented	Declared
External providers	1 — OpenAI	—
Requires API keys	No	Yes
Plugin surface	plugins	extensions
Provenance drift	Unknown	Match

Open in the live compare tool → Docling profile Feynman 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 →