Jan vs LiteLLM
An independent, evidence-based trust comparison of Jan and LiteLLM, 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.
LiteLLM leads on trust — 76.8/100 (Grade B) vs 63.9/100 (Grade C), a 12.9-point gap. Full breakdown below.
| Signal | Janjanhq/jan | LiteLLMBerriAI/litellm |
|---|---|---|
| HVTrust score | 63.9 | 76.8 |
| Evidence grade | C | B |
| Coverage grade | B | A |
| Overall rank | #261 | #83 |
| Rank in LLM Gateways & Infra | #7 | #4 |
| GitHub stars | 44.1k | 56.8k |
| Last updated | today | today |
| Build provenance | No | No |
| OSSF Scorecard | 5.8 / 10 | 5.8 / 10 |
| License | NOASSERTION | NOASSERTION |
| Downloads | — | 174.0M/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 12.2 | 10.7 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.4 | 13.4 |
| Maintenance / 20 | 18.0 | 20.0 |
| Adoption / 20 | 11.1 | 20.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Declared | Implemented |
| External providers | 3 — Anthropic, OpenAI, xAI Grok | 6 — Amazon Bedrock, Anthropic, Google Gemini, … |
| Requires API keys | No | Yes |
| Plugin surface | extensions | plugins |
| 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 →