PentAGI vs REA
REA leads on trust: 93.7/100 (Grade A) against 53.8/100 (Grade C), a 39.9-point gap. REA leads on maintenance and adoption, and rests on broader evidence.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
PentAGI doesn't lead on any scored dimension in this pair.
Reverse engineer anything with agents, from app behavior down to native binaries.
Choose REA if maintenance and adoption matter most.
- +9.1Adoption: 473.4k GitHub stars against 34.8k
- +8.6Maintenance: last push today, against 9d ago
- +8.0Safety / Integrity: OSSF Scorecard 6.6 against 5.5
- +7.2Identity / Provenance: package provenance attested, against none
Where they differ
An independent, evidence-based trust comparison of PentAGI and REA, 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 | REAmorluto/rea |
|---|---|---|
| HVTrust score | 53.8 | 93.7 |
| Evidence grade | C | A |
| Coverage grade | C | B |
| Overall rank | #898 | #4 |
| Rank in Security & Guardrails | #18 | #1 |
| GitHub stars | 34.8k | 473.4k |
| Last updated | 9d ago | today |
| Build provenance | No | Yes |
| OSSF Scorecard | 5.5 / 10 | 6.6 / 10 |
| License | MIT | MIT |
| Downloads | — | 377k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.8 | 19.8 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 13.2 | 14.1 |
| Maintenance / 20 | 11.4 | 20.0 |
| Adoption / 20 | 10.9 | 20.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | 9 — Anthropic, DeepSeek, Firecrawl, … | 1 — Anthropic |
| Requires API keys | Yes | No |
| Plugin surface | plugins | plugins |
| Provenance drift | — | Match |
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 →