An independent, evidence-based trust comparison of LocalAI and vLLM, 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 | LocalAImudler/LocalAI | vLLMvllm-project/vllm |
|---|---|---|
| HVTrust score | 33.4 | 100.0 |
| Evidence grade | D | A |
| Overall rank | #139 | #2 |
| Rank in LLM Gateways & Infra | #3 | #1 |
| GitHub stars | 47.3k | 85.4k |
| Last updated | 1d ago | today |
| Build provenance | No | No |
| OSSF Scorecard | — | 6.7 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | — | 1.2M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 5.0 | 13.4 |
| Identity & provenance / 20 | 10.8 | 10.8 |
| Transparency / 17 | 8.5 | 14.2 |
| Maintenance / 20 | 19.9 | 20.0 |
| Adoption / 20 | 11.2 | 19.9 |
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 →