Registry › Compare › Leon vs Qwen Audio Agent

Leon vs Qwen Audio Agent

Qwen Audio Agent leads on trust: 86.1/100 (Grade A) against 59.7/100 (Grade C), a 26.4-point gap. Qwen Audio Agent leads on supply-chain integrity and provenance, and rests on broader evidence.

C Leon 59.7

🧠 Leon is your open-source personal assistant.

leon-ai/leon · #663 overall · #6 Voice & Conversational · coverage C (2/5)

Leon doesn't lead on any scored dimension in this pair.

A Qwen Audio Agent 86.1

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

QwenAudio/qwen-audio-agent · #73 overall · #2 Voice & Conversational · coverage B (3/5)

Choose Qwen Audio Agent if supply-chain integrity and provenance matter most.

+10.0Safety / Integrity: 92% of recent commits signed, against 67%
+7.2Identity / Provenance: package provenance attested, against none
+1.3Adoption
+0.9Transparency: OSSF Scorecard 5.5 against 4.5

Where they differ

9.0

Safety / IntegrityQwen Audio Agent +10.0

19.0

10.8

Identity / ProvenanceQwen Audio Agent +7.2

18.0

12.3

TransparencyQwen Audio Agent +0.9

13.2

20.0

MaintenanceLeon +0.1

19.9

10.2

AdoptionQwen Audio Agent +1.3

11.5

-2.6

Runtime calibrationQwen Audio Agent +7.1

+4.5

Full evidence table

An independent, evidence-based trust comparison of Leon and Qwen Audio Agent, two Voice & Conversational projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	Leonleon-ai/leon	Qwen Audio AgentQwenAudio/qwen-audio-agent
HVTrust score	59.7	86.1
Evidence grade	C	A
Coverage grade	C	B
Overall rank	#663	#73
Rank in Voice & Conversational	#6	#2
GitHub stars	17.6k	2.9k
Last updated	today	1d ago
Build provenance	No	Yes
OSSF Scorecard	4.5 / 10	5.5 / 10
License	MIT	Apache-2.0
Downloads	—	247/wk
Trust dimensions (points earned)
Safety / integrity / 25	9.0	19.0
Identity & provenance / 18	10.8	18.0
Transparency / 17	12.3	13.2
Maintenance / 20	20.0	19.9
Adoption / 20	10.2	11.5
Runtime capability surface (full matrix)
MCP server	—	Implemented
External providers	5 — Anthropic, DeepSeek, Groq, …	—
Requires API keys	No	Yes
Plugin surface	plugins	—
Provenance drift	—	Match

Open in the live compare tool → Leon profile Qwen Audio Agent profile More Voice & Conversational →

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 →