PentAGI vs PentestAgent
Both are Grade C and 0.4 points apart, so choose on what you weigh most. PentAGI leads on supply-chain integrity and adoption; PentestAgent leads on transparency.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Choose PentAGI if supply-chain integrity and adoption matter most.
- +2.5Adoption: 33.4k GitHub stars against 3.2k
- +1.7Safety / Integrity: 99% of recent commits signed, against 47%
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
Choose PentestAgent if transparency matters most.
- +0.6Transparency: OSSF Scorecard 6.2 against 5.5
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of PentAGI and PentestAgent, 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 | PentAGIvxcontrol/pentagi | PentestAgentGH05TCREW/pentestagent |
|---|---|---|
| HVTrust score | 55.9 | 55.5 |
| Evidence grade | C | C |
| Coverage grade | C | C |
| Overall rank | #824 | #834 |
| Rank in Security & Guardrails | #14 | #15 |
| GitHub stars | 33.4k | 3.2k |
| Last updated | 14d ago | 3d ago |
| Build provenance | No | No |
| OSSF Scorecard | 5.5 / 10 | 6.2 / 10 |
| License | MIT | MIT |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.8 | 10.1 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.2 | 13.8 |
| Maintenance / 20 | 13.5 | 13.2 |
| Adoption / 20 | 10.9 | 8.4 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | 9 — Anthropic, DeepSeek, Firecrawl, … | 4 — Anthropic, Multi-provider (LiteLLM), OpenAI, … |
| Requires API keys | Yes | 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 →