Agency Swarm vs Swarms
Both are Grade B and 4.9 points apart, so choose on what you weigh most. Agency Swarm rests on broader evidence; Swarms leads on supply-chain integrity and transparency. Note: Swarms's evidence coverage is thinner (coverage B vs A) — its score rests on fewer independent signal types.
Reliable Multi-Agent Orchestration Framework
Choose Agency Swarm if breadth of evidence matters most.
- A vs BEvidence coverage: 4 of 5 independent signal types, against 3
The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai
Choose Swarms if supply-chain integrity and transparency matter most.
- +3.3Safety / Integrity: 100% of recent commits signed, against 69%
- +1.2Transparency: OSSF Scorecard 6.0 against 4.6
- +0.8Adoption: 1.6k weekly downloads against 801
- +0.6Maintenance: last push today, against 1d ago
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Agency Swarm and Swarms, 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.
Full evidence
| Signal | Agency SwarmVRSEN/agency-swarm | Swarmskyegomez/swarms |
|---|---|---|
| HVTrust score | 68.0 | 72.9 |
| Evidence grade | B | B |
| Coverage grade | A | B |
| Overall rank | #404 | #285 |
| Rank in Multi-Agent Systems | #5 | #3 |
| GitHub stars | 4.6k | 7.2k |
| Last updated | 1d ago | today |
| Build provenance | No | No |
| OSSF Scorecard | 4.6 / 10 | 6.0 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | 801/wk | 2k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 9.2 | 12.5 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.4 | 13.6 |
| Maintenance / 20 | 19.4 | 20.0 |
| Adoption / 20 | 12.7 | 13.5 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 2 — Multi-provider (LiteLLM), OpenAI | 4 — Anthropic, Groq, Multi-provider (LiteLLM), … |
| Requires API keys | Yes | Yes |
| Plugin surface | marketplace | 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 v4.4 →