NeMo Guardrails vs open-kritt
NeMo Guardrails leads on trust: 71.9/100 (Grade B) against 57.7/100 (Grade C), a 14.2-point gap. NeMo Guardrails leads on adoption and supply-chain integrity, and rests on broader evidence; open-kritt leads on maintenance.
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Choose NeMo Guardrails if adoption and supply-chain integrity matter most.
- +7.9Adoption: 7.2k GitHub stars against 2.2k
- +5.4Safety / Integrity: 100% of recent commits signed, against 51%
- +1.9Transparency: OSSF Scorecard 7.1 against 4.8
- A vs CEvidence coverage: 4 of 5 independent signal types, against 2
Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.
Choose open-kritt if maintenance matters most.
- +1.0Maintenance: last push today, against 2d ago
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of NeMo Guardrails and open-kritt, two Security & Guardrails projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | NeMo GuardrailsNVIDIA/NeMo-Guardrails | open-krittKritt-ai/open-kritt |
|---|---|---|
| HVTrust score | 71.9 | 57.7 |
| Evidence grade | B | C |
| Coverage grade | A | C |
| Overall rank | #290 | #704 |
| Rank in Security & Guardrails | #5 | #8 |
| GitHub stars | 7.2k | 2.2k |
| Last updated | 2d ago | today |
| Build provenance | No | No |
| OSSF Scorecard | 7.1 / 10 | 4.8 / 10 |
| License | NOASSERTION | AGPL-3.0 |
| Downloads | 90k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 13.9 | 8.5 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 14.5 | 12.6 |
| Maintenance / 20 | 16.8 | 17.8 |
| Adoption / 20 | 15.9 | 8.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | — |
| External providers | 1 — OpenAI | — |
| Requires API keys | No | No |
| Plugin surface | — | — |
| Provenance drift | 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 v4.3 →