Deepsec vs PentAGI
Deepsec leads on trust: 60.7/100 (Grade C) against 53.8/100 (Grade C), a 6.9-point gap. Deepsec leads on maintenance; PentAGI leads on supply-chain integrity and adoption.
Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents
Choose Deepsec if maintenance matters most.
- +5.3Maintenance: last push 2d ago, against 9d ago
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Choose PentAGI if supply-chain integrity and adoption matter most.
- +1.5Adoption: 34.8k GitHub stars against 8.5k
- +0.7Safety / Integrity: OSSF Scorecard 5.5 against 4.9
- +0.5Transparency: OSSF Scorecard 5.5 against 4.9
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Deepsec 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 | Deepsecvercel-labs/deepsec | PentAGIvxcontrol/pentagi |
|---|---|---|
| HVTrust score | 60.7 | 53.8 |
| Evidence grade | C | C |
| Coverage grade | C | C |
| Overall rank | #682 | #898 |
| Rank in Security & Guardrails | #10 | #18 |
| GitHub stars | 8.5k | 34.8k |
| Last updated | 2d ago | 9d ago |
| Build provenance | No | No |
| OSSF Scorecard | 4.9 / 10 | 5.5 / 10 |
| License | Apache-2.0 | MIT |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.1 | 11.8 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.7 | 13.2 |
| Maintenance / 20 | 16.7 | 11.4 |
| Adoption / 20 | 9.4 | 10.9 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | — |
| External providers | — | 9 — Anthropic, DeepSeek, Firecrawl, … |
| Requires API keys | No | Yes |
| Plugin surface | — | plugins |
| Provenance drift | — | — |
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 →