HOL Guard vs open-kritt
HOL Guard leads on trust: 91.3/100 (Grade A) against 54.5/100 (Grade C), a 36.8-point gap. HOL Guard leads on supply-chain integrity and provenance, and rests on broader evidence.
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Choose HOL Guard if supply-chain integrity and provenance matter most.
- +14.2Safety / Integrity: 100% of recent commits signed, against 59%
- +7.2Identity / Provenance: package provenance attested, against none
- +6.5Maintenance: last push today, against 6d ago
- +4.2Adoption
Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.
open-kritt doesn't lead on any scored dimension in this pair.
Where they differ
An independent, evidence-based trust comparison of HOL Guard 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 | HOL Guardhashgraph-online/hol-guard | open-krittKritt-ai/open-kritt |
|---|---|---|
| HVTrust score | 91.3 | 54.5 |
| Evidence grade | A | C |
| Coverage grade | B | C |
| Overall rank | #18 | #874 |
| Rank in Security & Guardrails | #2 | #16 |
| GitHub stars | 1.1k | 2.4k |
| Last updated | today | 6d ago |
| Build provenance | Yes | No |
| OSSF Scorecard | 8.8 / 10 | 5.1 / 10 |
| License | Apache-2.0 | AGPL-3.0 |
| Downloads | 5k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 23.5 | 9.3 |
| Identity & provenance / 18 | 18.0 | 10.8 |
| Transparency / 17 | 16.0 | 12.8 |
| Maintenance / 20 | 20.0 | 13.5 |
| Adoption / 20 | 12.3 | 8.1 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | — |
| External providers | 3 — Anthropic, Google Gemini, Multi-provider (LiteLLM) | — |
| Requires API keys | No | No |
| Plugin surface | extensions | — |
| Provenance drift | Match | — |
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 →