Registry › Compare › OpenScience vs WrenAI

OpenScience vs WrenAI

Both are Grade A and 3.5 points apart, so choose on what you weigh most. OpenScience leads on maintenance; WrenAI leads on supply-chain integrity.

A OpenScience 82.4

The open-source AI workbench for scientific research

synthetic-sciences/openscience · #120 overall · #5 Research & Data · coverage B (3/5)

Choose OpenScience if maintenance matters most.

+1.5Maintenance

A WrenAI 85.9

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 · #71 overall · #4 Research & Data · coverage B (3/5)

Choose WrenAI if supply-chain integrity matters most.

+1.7Safety / Integrity: 90% of recent commits signed, against 59%

Where they differ

17.3

Safety / IntegrityWrenAI +1.7

19.0

13.2

TransparencyWrenAI +0.1

13.3

20.0

MaintenanceOpenScience +1.5

18.5

13.6

AdoptionOpenScience +0.3

13.3

+0.3

Runtime calibrationWrenAI +3.5

+3.8

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of OpenScience 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	OpenSciencesynthetic-sciences/openscience	WrenAICanner/WrenAI
HVTrust score	82.4	85.9
Evidence grade	A	A
Coverage grade	B	B
Overall rank	#120	#71
Rank in Research & Data	#5	#4
GitHub stars	3.9k	17.8k
Last updated	today	today
Build provenance	Yes	Yes
OSSF Scorecard	5.5 / 10	5.6 / 10
License	Apache-2.0	NOASSERTION
Downloads	6k/wk	201/wk
Trust dimensions (points earned)
Safety / integrity / 25	17.3	19.0
Identity & provenance / 18	18.0	18.0
Transparency / 17	13.2	13.3
Maintenance / 20	20.0	18.5
Adoption / 20	13.6	13.3
Runtime capability surface (full matrix)
MCP server	Declared	Implemented
External providers	7 — Anthropic, Cohere, DeepSeek, …	3 — Amazon Bedrock, Anthropic, Postgres
Requires API keys	No	No
Plugin surface	plugins	plugins
Provenance drift	Match	Match

Open in the live compare tool → OpenScience 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 →