Registry › Compare › DvalinCode vs PentAGI

DvalinCode vs PentAGI

DvalinCode leads on trust: 83.7/100 (Grade A) against 54.9/100 (Grade C), a 28.8-point gap. DvalinCode leads on supply-chain integrity and provenance, and rests on broader evidence; PentAGI leads on adoption.

A DvalinCode 83.7

Independent security verification for code written by humans and AI agents. Scan, repair, then prove it — Dvalin runs your project's own checks and issues a Verified Fix Record anyone can re-derive offline. Local-first, policy-bound, MIT.

arthurpanhku/dvalincode · #121 overall · #4 Security & Guardrails · coverage B (3/5)

Choose DvalinCode if supply-chain integrity and provenance matter most.

  • +8.0Safety / Integrity: OSSF Scorecard 6.7 against 5.5
  • +7.2Identity / Provenance: package provenance attested, against none
  • +6.6Maintenance
  • +1.0Transparency: OSSF Scorecard 6.7 against 5.5
C PentAGI 54.9

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

vxcontrol/pentagi · #862 overall · #17 Security & Guardrails · coverage C (2/5)

Choose PentAGI if adoption matters most.

  • +2.5Adoption: 34.2k GitHub stars against 121

Where they differ

19.8
Safety / IntegrityDvalinCode +8.0
11.8
18.0
Identity / ProvenanceDvalinCode +7.2
10.8
14.2
TransparencyDvalinCode +1.0
13.2
19.1
MaintenanceDvalinCode +6.6
12.5
8.4
AdoptionPentAGI +2.5
10.9
+4.2
Runtime calibrationDvalinCode +8.5
-4.3

Full evidence table

An independent, evidence-based trust comparison of DvalinCode 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 DvalinCodearthurpanhku/dvalincode PentAGIvxcontrol/pentagi
HVTrust score 83.7 54.9
Evidence grade A C
Coverage grade B C
Overall rank #121 #862
Rank in Security & Guardrails #4 #17
GitHub stars 121 34.2k
Last updated 2d ago 2d ago
Build provenance Yes No
OSSF Scorecard 6.7 / 10 5.5 / 10
License MIT MIT
Downloads 331/wk —
Trust dimensions (points earned)
Safety / integrity / 25 19.8 11.8
Identity & provenance / 18 18.0 10.8
Transparency / 17 14.2 13.2
Maintenance / 20 19.1 12.5
Adoption / 20 8.4 10.9
Runtime capability surface (full matrix)
MCP server Implemented —
External providers 2 — Anthropic, Tavily 9 — Anthropic, DeepSeek, Firecrawl, …
Requires API keys Yes Yes
Plugin surface plugins plugins
Provenance drift Match —
Open in the live compare tool → DvalinCode 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 →