Leon vs Pipecat
Pipecat leads on trust: 87.5/100 (Grade A) against 62.4/100 (Grade C), a 25.1-point gap. Pipecat leads on supply-chain integrity and adoption, and rests on broader evidence.
🧠 Leon is your open-source personal assistant.
Leon doesn't lead on any scored dimension in this pair.
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
Choose Pipecat if supply-chain integrity and adoption matter most.
- +7.4Adoption
- +7.3Safety / Integrity: OSSF Scorecard 7.5 against 5.2
- +7.2Identity / Provenance: package provenance attested, against none
- +2.0Transparency: OSSF Scorecard 7.5 against 5.2
Where they differ
1 dimension identical: Maintenance 20.0 · Full evidence table
An independent, evidence-based trust comparison of Leon and Pipecat, 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 | Pipecatpipecat-ai/pipecat |
|---|---|---|
| HVTrust score | 62.4 | 87.5 |
| Evidence grade | C | A |
| Coverage grade | C | A |
| Overall rank | #635 | #68 |
| Rank in Voice & Conversational | #5 | #2 |
| GitHub stars | 17.7k | 17.4k |
| Last updated | today | today |
| Build provenance | No | Yes |
| OSSF Scorecard | 5.2 / 10 | 7.5 / 10 |
| License | MIT | BSD-2-Clause |
| Downloads | — | 389k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.1 | 18.4 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 12.9 | 14.9 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 10.2 | 17.6 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | — |
| External providers | 5 — Anthropic, DeepSeek, Groq, … | 7 — Anthropic, Google Gemini, Groq, … |
| Requires API keys | No | No |
| Plugin surface | plugins | plugins |
| Provenance drift | — | Match |
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 →