agent-swarm vs CAMEL
An independent, evidence-based trust comparison of agent-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 — 67.3/100 (Grade B) vs 63.9/100 (Grade C), a 3.4-point gap. Full breakdown below.
| Signal | agent-swarmdesplega-ai/agent-swarm | CAMELcamel-ai/camel |
|---|---|---|
| HVTrust score | 63.9 | 67.3 |
| Evidence grade | C | B |
| Coverage grade | C | A |
| Overall rank | #328 | #247 |
| Rank in Multi-Agent Systems | #7 | #3 |
| GitHub stars | 734 | 17.7k |
| Last updated | today | 1d ago |
| Build provenance | No | No |
| OSSF Scorecard | 6.3 / 10 | 6.8 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | — | 9k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 12.6 | 11.4 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.9 | 14.3 |
| Maintenance / 20 | 20.0 | 16.2 |
| Adoption / 20 | 6.9 | 15.5 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Declared |
| External providers | 3 — Anthropic, E2B, OpenAI | 14 — Amazon Bedrock, Anthropic, Cohere, … |
| Requires API keys | Yes | Yes |
| Plugin surface | 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 v4.3 →