Guardrails AI vs PentAGI
An independent, evidence-based trust comparison of Guardrails AI 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.
Guardrails AI leads on trust — 82.6/100 (Grade A) vs 62.5/100 (Grade C), a 20.1-point gap. Full breakdown below.
| Signal | Guardrails AIguardrails-ai/guardrails | PentAGIvxcontrol/pentagi |
|---|---|---|
| HVTrust score | 82.6 | 62.5 |
| Evidence grade | A | C |
| Coverage grade | A | C |
| Overall rank | #51 | #184 |
| Rank in Security & Guardrails | #1 | #5 |
| GitHub stars | 7.3k | 21.6k |
| Last updated | today | today |
| Build provenance | Yes | No |
| OSSF Scorecard | 6.0 / 10 | 5.7 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | 41k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 20.0 | 12.1 |
| Identity & provenance / 18 | 18.0 | 10.8 |
| Transparency / 17 | 13.6 | 13.3 |
| Maintenance / 20 | 17.4 | 20.0 |
| Adoption / 20 | 15.4 | 10.4 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | 2 — Anthropic, OpenAI | 7 — Amazon Bedrock, Anthropic, Google Gemini, … |
| Requires API keys | Yes | Yes |
| Plugin surface | — | extensions |
| 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 v4.2 →