An independent, evidence-based trust comparison of Jan and LocalAI, two LLM Gateways & Infra projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
| Signal | Janjanhq/jan | LocalAImudler/LocalAI |
|---|---|---|
| HVTrust score | 65.6 | 33.4 |
| Evidence grade | B | D |
| Overall rank | #79 | #139 |
| Rank in LLM Gateways & Infra | #2 | #3 |
| GitHub stars | 43.4k | 47.3k |
| Last updated | 2d ago | 1d ago |
| Build provenance | No | No |
| OSSF Scorecard | 5.9 / 10 | — |
| License | NOASSERTION | MIT |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 12.3 | 5.0 |
| Identity & provenance / 20 | 10.8 | 10.8 |
| Transparency / 17 | 13.5 | 8.5 |
| Maintenance / 20 | 19.6 | 19.9 |
| Adoption / 20 | 11.1 | 11.2 |
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 v4.0 →