An independent, evidence-based trust comparison of Llama Guard and LLM Guard, two Security & Guardrails projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
| Signal | Llama Guardmeta-llama/PurpleLlama | LLM Guardprotectai/llm-guard |
|---|---|---|
| HVTrust score | 23.2 | 24.2 |
| Evidence grade | D | D |
| Overall rank | #133 | #128 |
| Rank in Security & Guardrails | #3 | #2 |
| GitHub stars | 4.3k | 3.1k |
| Last updated | 4d ago | 202d ago |
| Build provenance | No | No |
| OSSF Scorecard | 5.9 / 10 | 5.9 / 10 |
| License | NOASSERTION | MIT |
| Downloads | — | 56k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 7.4 | 7.4 |
| Identity & provenance / 20 | 10.8 | 10.8 |
| Transparency / 17 | 13.5 | 13.5 |
| Maintenance / 20 | 12.3 | 0.0 |
| Adoption / 20 | 8.7 | 14.7 |
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 v4.0 →