Jan vs vLLM
An independent, evidence-based trust comparison of Jan 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.
vLLM leads on trust — 81.8/100 (Grade A) vs 64.6/100 (Grade C), a 17.2-point gap. Full breakdown below.
| Signal | Janjanhq/jan | vLLMvllm-project/vllm |
|---|---|---|
| HVTrust score | 64.6 | 81.8 |
| Evidence grade | C | A |
| Coverage grade | B | A |
| Overall rank | #232 | #61 |
| Rank in LLM Gateways & Infra | #7 | #3 |
| GitHub stars | 44.0k | 89.4k |
| Last updated | today | today |
| Build provenance | No | No |
| OSSF Scorecard | 5.8 / 10 | 6.7 / 10 |
| License | NOASSERTION | Apache-2.0 |
| Downloads | — | 1.2M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 12.2 | 13.4 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.4 | 14.2 |
| Maintenance / 20 | 18.7 | 20.0 |
| Adoption / 20 | 11.1 | 20.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | Declared |
| External providers | 3 — Anthropic, OpenAI, xAI Grok | — |
| Requires API keys | No | No |
| Plugin surface | extensions | extensions |
| 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 v4.3 →