Registry › Compare › Agency Swarm vs Ruflo

Agency Swarm vs Ruflo

Both are Grade B and 1.4 points apart, so choose on what you weigh most. Agency Swarm leads on adoption and rests on broader evidence; Ruflo leads on supply-chain integrity and maintenance. Note: Ruflo's evidence coverage is thinner (coverage C vs A) — its score rests on fewer independent signal types.

B Agency Swarm 65.7

Reliable Multi-Agent Orchestration Framework

VRSEN/agency-swarm · #491 overall · #9 Multi-Agent Systems · coverage A (4/5)

Choose Agency Swarm if adoption matters most.

+0.9Adoption
A vs CEvidence coverage: 4 of 5 independent signal types, against 2

B Ruflo 67.1

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

ruvnet/ruflo · #451 overall · #5 Multi-Agent Systems · coverage C (2/5)

Choose Ruflo if supply-chain integrity and maintenance matter most.

+2.5Maintenance
+2.0Safety / Integrity: 98% of recent commits signed, against 67%

Where they differ

9.0

Safety / IntegrityRuflo +2.0

11.0

12.3

TransparencyRuflo +0.4

12.7

17.4

MaintenanceRuflo +2.5

19.9

12.7

AdoptionAgency Swarm +0.9

11.8

+3.5

Runtime calibrationAgency Swarm +2.6

+0.9

1 dimension identical: Identity 10.8 · Full evidence table

An independent, evidence-based trust comparison of Agency Swarm and Ruflo, 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	Rufloruvnet/ruflo
HVTrust score	65.7	67.1
Evidence grade	B	B
Coverage grade	A	C
Overall rank	#491	#451
Rank in Multi-Agent Systems	#9	#5
GitHub stars	4.6k	80.7k
Last updated	1d ago	1d ago
Build provenance	No	No
OSSF Scorecard	4.5 / 10	4.9 / 10
License	MIT	MIT
Downloads	861/wk	—
Trust dimensions (points earned)
Safety / integrity / 25	9.0	11.0
Identity & provenance / 18	10.8	10.8
Transparency / 17	12.3	12.7
Maintenance / 20	17.4	19.9
Adoption / 20	12.7	11.8
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	2 — Multi-provider (LiteLLM), OpenAI	2 — Anthropic, Supabase
Requires API keys	Yes	No
Plugin surface	marketplace	plugins
Provenance drift	Match	—

Open in the live compare tool → Agency Swarm profile Ruflo profile More Multi-Agent Systems →

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 →