Registry › Compare › Guardrails AI vs PentAGI

Guardrails AI vs PentAGI

Guardrails AI leads on trust: 75.1/100 (Grade B) against 53.8/100 (Grade C), a 21.3-point gap. Guardrails AI leads on supply-chain integrity and provenance, and rests on broader evidence.

B Guardrails AI 75.1

Adding guardrails to large language models.

guardrails-ai/guardrails · #277 overall · #6 Security & Guardrails · coverage A (4/5)

Choose Guardrails AI if supply-chain integrity and provenance matter most.

  • +7.4Safety / Integrity: 100% of recent commits signed, against 99%
  • +7.2Identity / Provenance: package provenance attested, against none
  • +4.2Adoption
  • A vs CEvidence coverage: 4 of 5 independent signal types, against 2
C PentAGI 53.8

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

vxcontrol/pentagi · #898 overall · #18 Security & Guardrails · coverage C (2/5)

PentAGI doesn't lead on any scored dimension in this pair.

Where they differ

19.2
Safety / IntegrityGuardrails AI +7.4
11.8
18.0
Identity / ProvenanceGuardrails AI +7.2
10.8
13.1
TransparencyPentAGI +0.1
13.2
11.7
MaintenanceGuardrails AI +0.3
11.4
15.1
AdoptionGuardrails AI +4.2
10.9
-2.0
Runtime calibrationGuardrails AI +2.3
-4.3

Full evidence table

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.

Full evidence

Signal Guardrails AIguardrails-ai/guardrails PentAGIvxcontrol/pentagi
HVTrust score 75.1 53.8
Evidence grade B C
Coverage grade A C
Overall rank #277 #898
Rank in Security & Guardrails #6 #18
GitHub stars 7.6k 34.8k
Last updated 4d ago 9d ago
Build provenance Yes No
OSSF Scorecard 5.4 / 10 5.5 / 10
License Apache-2.0 MIT
Downloads 22k/wk —
Trust dimensions (points earned)
Safety / integrity / 25 19.2 11.8
Identity & provenance / 18 18.0 10.8
Transparency / 17 13.1 13.2
Maintenance / 20 11.7 11.4
Adoption / 20 15.1 10.9
Runtime capability surface (full matrix)
MCP server — —
External providers 3 — Anthropic, Multi-provider (LiteLLM), OpenAI 9 — Anthropic, DeepSeek, Firecrawl, …
Requires API keys Yes Yes
Plugin surface — plugins
Provenance drift Unknown —
Open in the live compare tool → Guardrails AI profile PentAGI 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 →