Instructor vs vLLM
An independent, evidence-based trust comparison of Instructor 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 — 81.4/100 (Grade A) vs 66.9/100 (Grade B), a 14.5-point gap. Full breakdown below.
| Signal | Instructor567-labs/instructor | vLLMvllm-project/vllm |
|---|---|---|
| HVTrust score | 66.9 | 81.4 |
| Evidence grade | B | A |
| Coverage grade | A | A |
| Overall rank | #155 | #67 |
| Rank in LLM Gateways & Infra | #4 | #1 |
| GitHub stars | 13.9k | 92.3k |
| Last updated | 3d ago | today |
| Build provenance | No | No |
| OSSF Scorecard | 5.6 / 10 | 6.8 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | 1.9M/wk | 409k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 8.8 | 13.5 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.3 | 14.3 |
| Maintenance / 20 | 19.0 | 20.0 |
| Adoption / 20 | 18.3 | 19.4 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Declared |
| External providers | 11 — Amazon Bedrock, Anthropic, Cohere, … | — |
| Requires API keys | No | No |
| Plugin surface | — | extensions |
| Provenance drift | Unknown | 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 →