OpenScience vs WrenAI
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.
WrenAI leads on trust — 86.1/100 (Grade A) vs 78.7/100 (Grade B), a 7.4-point gap. Full breakdown below.
| Signal | OpenSciencesynthetic-sciences/openscience | WrenAICanner/WrenAI |
|---|---|---|
| HVTrust score | 78.7 | 86.1 |
| Evidence grade | B | A |
| Coverage grade | B | B |
| Overall rank | #74 | #41 |
| Rank in Research & Data | #4 | #2 |
| GitHub stars | 3.2k | 17.3k |
| Last updated | 1d ago | 1d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 4.7 / 10 | 5.3 / 10 |
| License | Apache-2.0 | NOASSERTION |
| Downloads | 3k/wk | 162/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 15.9 | 18.9 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 12.5 | 13.0 |
| Maintenance / 20 | 19.9 | 19.4 |
| Adoption / 20 | 13.0 | 13.1 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | Implemented |
| External providers | 7 — Anthropic, Cohere, Google Gemini, … | 3 — Amazon Bedrock, Anthropic, Postgres |
| Requires API keys | Yes | No |
| Plugin surface | plugins | plugins |
| Provenance drift | Match | Match |
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 v4.3 →