Registry › Compare › Leon vs LiveKit Agents

Leon vs LiveKit Agents

LiveKit Agents leads on trust: 92.0/100 (Grade A) against 62.4/100 (Grade C), a 29.6-point gap. LiveKit Agents leads on supply-chain integrity and adoption, and rests on broader evidence.

C Leon 62.4

🧠 Leon is your open-source personal assistant.

leon-ai/leon · #635 overall · #5 Voice & Conversational · coverage C (2/5)

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

A framework for building realtime voice AI agents 🤖🎙️📹

livekit/agents · #14 overall · #1 Voice & Conversational · coverage B (3/5)

Choose LiveKit Agents if supply-chain integrity and adoption matter most.

  • +9.4Safety / Integrity: 100% of recent commits signed, against 92%
  • +8.0Adoption
  • +7.2Identity / Provenance: package provenance attested, against none
  • +1.0Transparency: OSSF Scorecard 6.4 against 5.2

Where they differ

11.1
Safety / IntegrityLiveKit Agents +9.4
20.5
10.8
Identity / ProvenanceLiveKit Agents +7.2
18.0
12.9
TransparencyLiveKit Agents +1.0
13.9
20.0
MaintenanceLeon +0.1
19.9
10.2
AdoptionLiveKit Agents +8.0
18.2
-2.6
Runtime calibrationLiveKit Agents +4.1
+1.5

Full evidence table

An independent, evidence-based trust comparison of Leon and LiveKit Agents, 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 LiveKit Agentslivekit/agents
HVTrust score 62.4 92.0
Evidence grade C A
Coverage grade C B
Overall rank #635 #14
Rank in Voice & Conversational #5 #1
GitHub stars 17.7k 15.3k
Last updated today 1d ago
Build provenance No Yes
OSSF Scorecard 5.2 / 10 6.4 / 10
License MIT Apache-2.0
Downloads — 1.3M/wk
Trust dimensions (points earned)
Safety / integrity / 25 11.1 20.5
Identity & provenance / 18 10.8 18.0
Transparency / 17 12.9 13.9
Maintenance / 20 20.0 19.9
Adoption / 20 10.2 18.2
Runtime capability surface (full matrix)
MCP server Declared Implemented
External providers 5 — Anthropic, DeepSeek, Groq, … 1 — OpenAI
Requires API keys No Yes
Plugin surface plugins plugins
Provenance drift — Match
Open in the live compare tool → Leon profile LiveKit Agents 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 →