Registry › Compare › DeerFlow vs Docling

DeerFlow vs Docling

Docling leads on trust: 88.9/100 (Grade A) against 67.2/100 (Grade B), a 21.7-point gap. DeerFlow leads on transparency; Docling leads on provenance and adoption, and rests on broader evidence.

B DeerFlow 67.2

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

bytedance/deer-flow · #443 overall · #8 Research & Data · coverage C (2/5)

Choose DeerFlow if transparency matters most.

+1.2Transparency: OSSF Scorecard 6.5 against 5.0

A Docling 88.9

Get your documents ready for gen AI

docling-project/docling · #47 overall · #3 Research & Data · coverage A (4/5)

Choose Docling if provenance and adoption matter most.

+7.8Adoption
+7.2Identity / Provenance: package provenance attested, against none
+4.9Safety / Integrity: package provenance attested, against none
A vs CEvidence coverage: 4 of 5 independent signal types, against 2

Where they differ

13.1

Safety / IntegrityDocling +4.9

18.0

10.8

Identity / ProvenanceDocling +7.2

18.0

14.0

TransparencyDeerFlow +1.2

12.8

11.8

AdoptionDocling +7.8

19.6

-2.4

Runtime calibrationDocling +3.0

+0.6

1 dimension identical: Maintenance 19.9 · Full evidence table

An independent, evidence-based trust comparison of DeerFlow and Docling, 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	DeerFlowbytedance/deer-flow	Doclingdocling-project/docling
HVTrust score	67.2	88.9
Evidence grade	B	A
Coverage grade	C	A
Overall rank	#443	#47
Rank in Research & Data	#8	#3
GitHub stars	84.9k	70.0k
Last updated	1d ago	1d ago
Build provenance	No	Yes
OSSF Scorecard	6.5 / 10	5.0 / 10
License	MIT	MIT
Downloads	—	904k/wk
Trust dimensions (points earned)
Safety / integrity / 25	13.1	18.0
Identity & provenance / 18	10.8	18.0
Transparency / 17	14.0	12.8
Maintenance / 20	19.9	19.9
Adoption / 20	11.8	19.6
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	6 — E2B, OpenAI, OpenRouter, …	1 — OpenAI
Requires API keys	Yes	No
Plugin surface	extensions	plugins
Provenance drift	—	Unknown

Open in the live compare tool → DeerFlow profile Docling 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 →