Jan vs vLLM
vLLM leads on trust: 80.7/100 (Grade A) against 64.3/100 (Grade C), a 16.4-point gap. vLLM leads on supply-chain integrity and adoption, and rests on broader evidence.
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
Jan doesn't lead on any scored dimension in this pair.
A high-throughput and memory-efficient inference and serving engine for LLMs
Choose vLLM if supply-chain integrity and adoption matter most.
- +8.5Adoption: 97.1k GitHub stars against 45.8k
- +2.1Safety / Integrity: OSSF Scorecard 6.3 against 4.6
- +1.5Transparency: OSSF Scorecard 6.3 against 4.6
- A vs BEvidence coverage: 4 of 5 independent signal types, against 3
Where they differ
2 dimensions identical: Identity 10.8 · Maintenance 20.0 · Full evidence table
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.
Full evidence
| Signal | Janjanhq/jan | vLLMvllm-project/vllm |
|---|---|---|
| HVTrust score | 64.3 | 80.7 |
| Evidence grade | C | A |
| Coverage grade | B | A |
| Overall rank | #573 | #175 |
| Rank in LLM Gateways & Infra | #7 | #4 |
| GitHub stars | 45.8k | 97.1k |
| Last updated | today | today |
| Build provenance | No | No |
| OSSF Scorecard | 4.6 / 10 | 6.3 / 10 |
| License | NOASSERTION | Apache-2.0 |
| Downloads | — | 582k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 10.8 | 12.9 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.4 | 13.9 |
| Maintenance / 20 | 20.0 | 20.0 |
| Adoption / 20 | 11.2 | 19.7 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | Declared |
| External providers | — | — |
| 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 v4.4 →