Agency Swarm vs agent-swarm
Both are Grade B and 2.6 points apart, so choose on what you weigh most. Agency Swarm leads on adoption and rests on broader evidence; agent-swarm leads on supply-chain integrity and transparency.
Reliable Multi-Agent Orchestration Framework
Choose Agency Swarm if adoption matters most.
- +5.6Adoption: 4.6k GitHub stars against 878
- A vs CEvidence coverage: 4 of 5 independent signal types, against 2
Your Company Agentic Operating System
Choose agent-swarm if supply-chain integrity and transparency matter most.
- +4.1Safety / Integrity: 100% of recent commits signed, against 70%
- +1.8Transparency: OSSF Scorecard 6.6 against 4.5
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Agency Swarm and agent-swarm, 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 | agent-swarmdesplega-ai/agent-swarm |
|---|---|---|
| HVTrust score | 68.0 | 65.4 |
| Evidence grade | B | B |
| Coverage grade | A | C |
| Overall rank | #407 | #484 |
| Rank in Multi-Agent Systems | #5 | #8 |
| GitHub stars | 4.6k | 878 |
| Last updated | 1d ago | today |
| Build provenance | No | No |
| OSSF Scorecard | 4.5 / 10 | 6.6 / 10 |
| License | MIT | MIT |
| Downloads | 817/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 9.1 | 13.2 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.3 | 14.1 |
| Maintenance / 20 | 19.6 | 20.0 |
| Adoption / 20 | 12.7 | 7.1 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 2 — Multi-provider (LiteLLM), OpenAI | 4 — Anthropic, E2B, Google Gemini, … |
| Requires API keys | Yes | No |
| Plugin surface | marketplace | 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 →