Registry › Compare › Feynman vs GPT Researcher

Feynman vs GPT Researcher

Feynman leads on trust: 72.9/100 (Grade B) against 67.9/100 (Grade B), a 5.0-point gap. Feynman leads on provenance and maintenance; GPT Researcher leads on supply-chain integrity and transparency, and rests on broader evidence. Note: Feynman's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

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
+0.9Maintenance: last push today, against 8d ago

B GPT Researcher 67.9

An autonomous agent that conducts deep research on any data using any LLM providers

assafelovic/gpt-researcher · #409 overall · #8 Research & Data · coverage A (4/5)

Choose GPT Researcher if supply-chain integrity and transparency matter most.

+5.3Transparency
+1.4Safety / Integrity: 47% of recent commits signed, against 24%
+0.7Adoption: 30k GitHub stars against 9.9k
A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

8.7

Safety / IntegrityGPT Researcher +1.4

10.1

18.0

Identity / ProvenanceFeynman +7.2

10.8

8.5

TransparencyGPT Researcher +5.3

13.8

20.0

MaintenanceFeynman +0.9

19.1

15.3

AdoptionGPT Researcher +0.7

16.0

+2.4

Runtime calibrationFeynman +4.3

-1.9

Full evidence table

An independent, evidence-based trust comparison of Feynman and GPT Researcher, 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	FeynmanCompanion-Inc/feynman	GPT Researcherassafelovic/gpt-researcher
HVTrust score	72.9	67.9
Evidence grade	B	B
Coverage grade	B	A
Overall rank	#285	#409
Rank in Research & Data	#6	#8
GitHub stars	9.9k	30.0k
Last updated	today	8d ago
Build provenance	Yes	No
OSSF Scorecard	—	6.2 / 10
License	MIT	Apache-2.0
Downloads	19k/wk	8k/wk
Trust dimensions (points earned)
Safety / integrity / 25	8.7	10.1
Identity & provenance / 18	18.0	10.8
Transparency / 17	8.5	13.8
Maintenance / 20	20.0	19.1
Adoption / 20	15.3	16.0
Runtime capability surface (full matrix)
MCP server	Declared	Implemented
External providers	—	5 — Firecrawl, Google Gemini, Multi-provider (LiteLLM), …
Requires API keys	Yes	Yes
Plugin surface	extensions	plugins
Provenance drift	Match	Unknown

Open in the live compare tool → Feynman profile GPT Researcher 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 →