Registry › Compare › HOL Guard vs NeMo Guardrails

HOL Guard vs NeMo Guardrails

HOL Guard leads on trust: 92.2/100 (Grade A) against 71.9/100 (Grade B), a 20.3-point gap. HOL Guard leads on supply-chain integrity and provenance; NeMo Guardrails leads on adoption and rests on broader evidence. Note: HOL Guard's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.

A HOL Guard 92.2

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

hashgraph-online/hol-guard · #7 overall · #1 Security & Guardrails · coverage B (3/5)

Choose HOL Guard if supply-chain integrity and provenance matter most.

+10.5Safety / Integrity: OSSF Scorecard 9.6 against 7.1
+7.2Identity / Provenance: package provenance attested, against none
+3.2Maintenance: last push today, against 1d ago
+2.2Transparency: OSSF Scorecard 9.6 against 7.1

B NeMo Guardrails 71.9

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

NVIDIA/NeMo-Guardrails · #293 overall · #5 Security & Guardrails · coverage A (4/5)

Choose NeMo Guardrails if adoption matters most.

+3.8Adoption: 93.6k weekly downloads against 9.1k
A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

24.4

Safety / IntegrityHOL Guard +10.5

13.9

18.0

Identity / ProvenanceHOL Guard +7.2

10.8

16.7

TransparencyHOL Guard +2.2

14.5

20.0

MaintenanceHOL Guard +3.2

16.8

12.1

AdoptionNeMo Guardrails +3.8

15.9

+1.0

Runtime calibrationHOL Guard +1.0

+0.0

Full evidence table

An independent, evidence-based trust comparison of HOL 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.

Full evidence

Signal	HOL Guardhashgraph-online/hol-guard	NeMo GuardrailsNVIDIA/NeMo-Guardrails
HVTrust score	92.2	71.9
Evidence grade	A	B
Coverage grade	B	A
Overall rank	#7	#293
Rank in Security & Guardrails	#1	#5
GitHub stars	683	7.2k
Last updated	today	1d ago
Build provenance	Yes	No
OSSF Scorecard	9.6 / 10	7.1 / 10
License	Apache-2.0	NOASSERTION
Downloads	9k/wk	94k/wk
Trust dimensions (points earned)
Safety / integrity / 25	24.4	13.9
Identity & provenance / 18	18.0	10.8
Transparency / 17	16.7	14.5
Maintenance / 20	20.0	16.8
Adoption / 20	12.1	15.9
Runtime capability surface (full matrix)
MCP server	Implemented	—
External providers	3 — Anthropic, Google Gemini, Multi-provider (LiteLLM)	1 — OpenAI
Requires API keys	No	No
Plugin surface	extensions	—
Provenance drift	Match	Unknown

Open in the live compare tool → HOL Guard profile NeMo Guardrails profile More Security & Guardrails →

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 →