Agency Swarm vs CAMEL
An independent, evidence-based trust comparison of Agency Swarm 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.
CAMEL leads on trust — 68.6/100 (Grade B) vs 65.0/100 (Grade B), a 3.6-point gap. Full breakdown below.
| Signal | Agency SwarmVRSEN/agency-swarm | CAMELcamel-ai/camel |
|---|---|---|
| HVTrust score | 65.0 | 68.6 |
| Evidence grade | B | B |
| Coverage grade | A | A |
| Overall rank | #232 | #166 |
| Rank in Multi-Agent Systems | #4 | #3 |
| GitHub stars | 4.5k | 17.6k |
| Last updated | 2d ago | 4d ago |
| Build provenance | No | No |
| OSSF Scorecard | 4.4 / 10 | 6.8 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | 11k/wk | 18k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 7.2 | 11.4 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.2 | 14.3 |
| Maintenance / 20 | 17.1 | 17.1 |
| Adoption / 20 | 14.2 | 15.9 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Declared |
| External providers | 2 — Multi-provider (LiteLLM), OpenAI | 14 — Amazon Bedrock, Anthropic, Cohere, … |
| Requires API keys | Yes | Yes |
| Plugin surface | marketplace | — |
| Provenance drift | Match | 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 v4.3 →