Notebooklm Py vs Waza
An independent, evidence-based trust comparison of Notebooklm Py and Waza, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Notebooklm Py leads on trust — 88.8/100 (Grade A) vs 77.6/100 (Grade B), a 11.2-point gap. Full breakdown below.
| Signal | Notebooklm Pyteng-lin/notebooklm-py | Wazatw93/Waza |
|---|---|---|
| HVTrust score | 88.8 | 77.6 |
| Evidence grade | A | B |
| Coverage grade | B | B |
| Overall rank | #4 | #21 |
| Rank in Agent Skills | #4 | #21 |
| GitHub stars | 19.3k | 7.0k |
| Last updated | 1d ago | 1d ago |
| Build provenance | Yes | Yes |
| OSSF Scorecard | 6.3 / 10 | 4.2 / 10 |
| License | MIT | MIT |
| Downloads | 27k/wk | 222/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 16.4 | 13.2 |
| Identity & provenance / 18 | 18.0 | 18.0 |
| Transparency / 17 | 13.9 | 12.1 |
| Maintenance / 20 | 19.9 | 18.2 |
| Adoption / 20 | 16.2 | 12.4 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | — |
| External providers | — | — |
| 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 →