An independent, evidence-based trust comparison of Docling 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.
| Signal | Doclingdocling-project/docling | WrenAICanner/WrenAI |
|---|---|---|
| HVTrust score | 86.8 | 86.1 |
| Evidence grade | A | A |
| Coverage grade | A | B |
| Overall rank | #22 | #30 |
| Rank in Research & Data | #1 | #2 |
| GitHub stars | 63.5k | 16.3k |
| Last updated | today | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 4.8 / 10 | 6.1 / 10 |
| License | MIT | NOASSERTION |
| Downloads | 4.1M/wk | 164/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 17.8 | 20.1 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 12.6 | 13.7 |
| Maintenance / 20 | 20.0 | 19.7 |
| Adoption / 20 | 20.0 | 13.1 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Declared |
| External providers | 3 — Amazon Bedrock, OpenAI, Postgres | 3 — Amazon Bedrock, Anthropic, Postgres |
| Requires API keys | No | No |
| Plugin surface | extensions | plugins |
| Provenance drift | Unknown | 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 v4.2 →