NeMo Guardrails vs PentAGI
NeMo Guardrails leads on trust: 89.3/100 (Grade A) against 53.8/100 (Grade C), a 35.5-point gap. NeMo Guardrails leads on supply-chain integrity and maintenance, and rests on broader evidence.
NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.
Choose NeMo Guardrails if supply-chain integrity and maintenance matter most.
- +9.6Safety / Integrity: 100% of recent commits signed, against 99%
- +8.3Maintenance: last push 3d ago, against 9d ago
- +7.2Identity / Provenance: package provenance attested, against none
- +5.1Adoption
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
PentAGI doesn't lead on any scored dimension in this pair.
Where they differ
An independent, evidence-based trust comparison of NeMo Guardrails and PentAGI, 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 | PentAGIvxcontrol/pentagi |
|---|---|---|
| HVTrust score | 89.3 | 53.8 |
| Evidence grade | A | C |
| Coverage grade | A | C |
| Overall rank | #42 | #898 |
| Rank in Security & Guardrails | #3 | #18 |
| GitHub stars | 7.5k | 34.8k |
| Last updated | 3d ago | 9d ago |
| Build provenance | Yes | No |
| OSSF Scorecard | 7.1 / 10 | 5.5 / 10 |
| License | NOASSERTION | MIT |
| Downloads | 101k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 21.4 | 11.8 |
| Identity & provenance / 18 | 18.0 | 10.8 |
| Transparency / 17 | 14.5 | 13.2 |
| Maintenance / 20 | 19.7 | 11.4 |
| Adoption / 20 | 16.0 | 10.9 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | — |
| External providers | 1 — OpenAI | 9 — Anthropic, DeepSeek, Firecrawl, … |
| Requires API keys | No | Yes |
| Plugin surface | plugins | plugins |
| 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 v4.4 →