An independent, evidence-based trust comparison of Agency Agents and CAMEL, two Multi-Agent Systems projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
| Signal | Agency Agentsmsitarzewski/agency-agents | CAMELcamel-ai/camel |
|---|---|---|
| HVTrust score | 65.9 | 69.7 |
| Evidence grade | B | B |
| Overall rank | #121 | #89 |
| Rank in Multi-Agent Systems | #3 | #2 |
| GitHub stars | 120.8k | 17.3k |
| Last updated | today | 2d ago |
| Build provenance | No | No |
| OSSF Scorecard | 4.9 / 10 | 6.8 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | — | 15k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.0 | 11.3 |
| Identity & provenance / 20 | 10.8 | 10.8 |
| Transparency / 17 | 12.7 | 14.3 |
| Maintenance / 20 | 19.2 | 17.6 |
| Adoption / 20 | 12.2 | 15.7 |
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 v3.2 →