Registry › Compare › Crawl4AI vs Feynman

Crawl4AI vs Feynman

Both are Grade B and 2.3 points apart, so choose on what you weigh most. Crawl4AI leads on transparency and adoption, and rests on broader evidence; Feynman leads on provenance and maintenance. Note: Feynman's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

B Crawl4AI 70.6

Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key.

unclecode/crawl4ai · #332 overall · #7 Research & Data · coverage A (4/5)

Choose Crawl4AI if transparency and adoption matter most.

+4.2Transparency
+3.8Adoption: 292.1k 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)

Choose Feynman if provenance and maintenance matter most.

+7.2Identity / Provenance: package provenance attested, against none
+1.6Maintenance: last push today, against 4d ago
+0.8Safety / Integrity: package provenance attested, against none

Where they differ

7.9

Safety / IntegrityFeynman +0.8

8.7

10.8

Identity / ProvenanceFeynman +7.2

18.0

12.7

TransparencyCrawl4AI +4.2

8.5

18.4

MaintenanceFeynman +1.6

20.0

19.1

AdoptionCrawl4AI +3.8

15.3

+1.7

Runtime calibrationFeynman +0.7

+2.4

Full evidence table

An independent, evidence-based trust comparison of Crawl4AI 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	Crawl4AIunclecode/crawl4ai	FeynmanCompanion-Inc/feynman
HVTrust score	70.6	72.9
Evidence grade	B	B
Coverage grade	A	B
Overall rank	#332	#285
Rank in Research & Data	#7	#6
GitHub stars	85.1k	9.9k
Last updated	4d ago	today
Build provenance	No	Yes
OSSF Scorecard	4.9 / 10	—
License	Apache-2.0	MIT
Downloads	292k/wk	19k/wk
Trust dimensions (points earned)
Safety / integrity / 25	7.9	8.7
Identity & provenance / 18	10.8	18.0
Transparency / 17	12.7	8.5
Maintenance / 20	18.4	20.0
Adoption / 20	19.1	15.3
Runtime capability surface (full matrix)
MCP server	—	Declared
External providers	1 — OpenAI	—
Requires API keys	Yes	Yes
Plugin surface	marketplace	extensions
Provenance drift	Match	Match

Open in the live compare tool → Crawl4AI 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 →