Registry › Compare › Feynman vs WrenAI

Feynman vs WrenAI

WrenAI leads on trust: 85.7/100 (Grade A) against 72.9/100 (Grade B), a 12.8-point gap. Feynman leads on maintenance and adoption; WrenAI leads on supply-chain integrity and transparency.

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 maintenance and adoption matter most.

+2.2Adoption: 19k weekly downloads against 157
+1.6Maintenance

A WrenAI 85.7

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.

Canner/WrenAI · #81 overall · #4 Research & Data · coverage B (3/5)

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

+10.3Safety / Integrity: 90% of recent commits signed, against 24%
+4.8Transparency

Where they differ

8.7

Safety / IntegrityWrenAI +10.3

19.0

8.5

TransparencyWrenAI +4.8

13.3

20.0

MaintenanceFeynman +1.6

18.4

15.3

AdoptionFeynman +2.2

13.1

+2.4

Runtime calibrationWrenAI +1.5

+3.9

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of Feynman and WrenAI, 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	WrenAICanner/WrenAI
HVTrust score	72.9	85.7
Evidence grade	B	A
Coverage grade	B	B
Overall rank	#285	#81
Rank in Research & Data	#6	#4
GitHub stars	9.9k	17.8k
Last updated	today	today
Build provenance	Yes	Yes
OSSF Scorecard	—	5.6 / 10
License	MIT	NOASSERTION
Downloads	19k/wk	157/wk
Trust dimensions (points earned)
Safety / integrity / 25	8.7	19.0
Identity & provenance / 18	18.0	18.0
Transparency / 17	8.5	13.3
Maintenance / 20	20.0	18.4
Adoption / 20	15.3	13.1
Runtime capability surface (full matrix)
MCP server	Declared	Implemented
External providers	—	3 — Amazon Bedrock, Anthropic, Postgres
Requires API keys	Yes	No
Plugin surface	extensions	plugins
Provenance drift	Match	Match

Open in the live compare tool → Feynman profile WrenAI 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 →