Better Harness vs Notebooklm Py
An independent, evidence-based trust comparison of Better Harness and Notebooklm Py, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Better Harness leads on trust — 82.1/100 (Grade A) vs 78.7/100 (Grade B), a 3.4-point gap. Full breakdown below.
| Signal | Better HarnessQoderAI/better-harness | Notebooklm Pyteng-lin/notebooklm-py |
|---|---|---|
| HVTrust score | 82.1 | 78.7 |
| Evidence grade | A | B |
| Coverage grade | B | B |
| Overall rank | #5 | #8 |
| Rank in Agent Skills | #5 | #8 |
| GitHub stars | 2.1k | 19.1k |
| Last updated | 1d ago | today |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 5.4 / 10 | — |
| License | MIT | MIT |
| Downloads | 482/wk | 37k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 15.8 | 10.1 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.1 | 8.5 |
| Maintenance / 20 | 19.9 | 20.0 |
| Adoption / 20 | 11.6 | 16.4 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | 1 — Anthropic | — |
| Requires API keys | No | No |
| Plugin surface | 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 →