An independent, evidence-based trust comparison of LLM Guard and NeMo Guardrails, 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 | LLM Guardprotectai/llm-guard | NeMo GuardrailsNVIDIA/NeMo-Guardrails |
|---|---|---|
| HVTrust score | 58.2 | 71.2 |
| Evidence grade | C | B |
| Coverage grade | A | A |
| Overall rank | #180 | #77 |
| Rank in Security & Guardrails | #3 | #2 |
| GitHub stars | 3.2k | 6.7k |
| Last updated | 3d ago | 1d ago |
| Build provenance | No | No |
| OSSF Scorecard | 5.6 / 10 | 5.9 / 10 |
| License | MIT | NOASSERTION |
| Downloads | 56k/wk | 79k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 7.0 | 12.4 |
| Identity & provenance / 20 | 10.8 | 10.8 |
| Transparency / 17 | 13.3 | 13.5 |
| Maintenance / 20 | 13.0 | 19.7 |
| Adoption / 20 | 14.7 | 15.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | — |
| External providers | — | 1 — OpenAI |
| Requires API keys | No | No |
| Plugin surface | plugins | plugins |
| Provenance drift | Unknown | Unknown |
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 →