Leon vs TEN Framework
Both are Grade C and 4.5 points apart, so choose on what you weigh most. Leon leads on supply-chain integrity and maintenance.
🧠 Leon is your open-source personal assistant.
Choose Leon if supply-chain integrity and maintenance matter most.
- +2.9Maintenance: last push today, against 2d ago
- +1.1Safety / Integrity: OSSF Scorecard 5.2 against 4.0
- +1.0Transparency: OSSF Scorecard 5.2 against 4.0
- +0.5Adoption: 17.7k GitHub stars against 11.2k
Open-source framework for conversational voice AI agents
TEN Framework doesn't lead on any scored dimension in this pair.
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of Leon and TEN Framework, 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 | TEN FrameworkTEN-framework/ten-framework |
|---|---|---|
| HVTrust score | 62.4 | 57.9 |
| Evidence grade | C | C |
| Coverage grade | C | C |
| Overall rank | #635 | #771 |
| Rank in Voice & Conversational | #5 | #7 |
| GitHub stars | 17.7k | 11.2k |
| Last updated | today | 2d ago |
| Build provenance | No | No |
| OSSF Scorecard | 5.2 / 10 | 4.0 / 10 |
| License | MIT | NOASSERTION |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.1 | 10.0 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.9 | 11.9 |
| Maintenance / 20 | 20.0 | 17.1 |
| Adoption / 20 | 10.2 | 9.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | — |
| External providers | 5 — Anthropic, DeepSeek, Groq, … | 1 — OpenAI |
| Requires API keys | No | Yes |
| Plugin surface | plugins | extensions |
| Provenance drift | — | — |
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 →