Registry › Compare › Bolna vs Leon

Bolna vs Leon

Both are Grade C and 4.8 points apart, so choose on what you weigh most. Bolna leads on supply-chain integrity; Leon leads on maintenance and adoption.

C Bolna 57.6

Conversational voice AI agents

bolna-ai/bolna · #781 overall · #8 Voice & Conversational · coverage C (2/5)

Choose Bolna if supply-chain integrity matters most.

  • +0.8Safety / Integrity: 100% of recent commits signed, against 92%
C Leon 62.4

🧠 Leon is your open-source personal assistant.

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

Choose Leon if maintenance and adoption matter most.

  • +3.2Adoption: 17.7k GitHub stars against 831
  • +1.5Maintenance: last push today, against 3d ago

Where they differ

11.9
Safety / IntegrityBolna +0.8
11.1
13.2
TransparencyBolna +0.3
12.9
18.5
MaintenanceLeon +1.5
20.0
7.0
AdoptionLeon +3.2
10.2
-3.8
Runtime calibrationLeon +1.2
-2.6

1 dimension identical: Identity 10.8 · Full evidence table

An independent, evidence-based trust comparison of Bolna and Leon, 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 Bolnabolna-ai/bolna Leonleon-ai/leon
HVTrust score 57.6 62.4
Evidence grade C C
Coverage grade C C
Overall rank #781 #635
Rank in Voice & Conversational #8 #5
GitHub stars 831 17.7k
Last updated 3d ago today
Build provenance No No
OSSF Scorecard 5.5 / 10 5.2 / 10
License MIT MIT
Downloads — —
Trust dimensions (points earned)
Safety / integrity / 25 11.9 11.1
Identity & provenance / 18 10.8 10.8
Transparency / 17 13.2 12.9
Maintenance / 20 18.5 20.0
Adoption / 20 7.0 10.2
Runtime capability surface (full matrix)
MCP server — Declared
External providers 6 — ElevenLabs, Google Gemini, Groq, … 5 — Anthropic, DeepSeek, Groq, …
Requires API keys Yes No
Plugin surface — plugins
Provenance drift — —
Open in the live compare tool → Bolna profile Leon 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 →