Registry › Compare › Jan vs vLLM

Jan vs vLLM

vLLM leads on trust: 80.8/100 (Grade A) against 66.6/100 (Grade B), a 14.2-point gap. vLLM leads on adoption and supply-chain integrity, and rests on broader evidence.

B Jan 66.6

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

janhq/jan · #426 overall · #6 LLM Gateways & Infra · coverage B (3/5)

Jan doesn't lead on any scored dimension in this pair.

A vLLM 80.8

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-project/vllm · #136 overall · #2 LLM Gateways & Infra · coverage A (4/5)

Choose vLLM if adoption and supply-chain integrity matter most.

+8.3Adoption: 93.1k GitHub stars against 44.8k
+1.1Safety / Integrity: OSSF Scorecard 6.5 against 5.6
+0.7Transparency: OSSF Scorecard 6.5 against 5.6
A vs BEvidence coverage: 4 of 5 independent signal types, against 3

Where they differ

12.0

Safety / IntegrityvLLM +1.1

13.1

13.3

TransparencyvLLM +0.7

14.0

19.9

MaintenancevLLM +0.1

20.0

11.2

AdoptionvLLM +8.3

19.5

-0.6

Runtime calibrationvLLM +4.0

+3.4

1 dimension identical: Identity 10.8 · 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	66.6	80.8
Evidence grade	B	A
Coverage grade	B	A
Overall rank	#426	#136
Rank in LLM Gateways & Infra	#6	#2
GitHub stars	44.8k	93.1k
Last updated	1d ago	today
Build provenance	No	No
OSSF Scorecard	5.6 / 10	6.5 / 10
License	NOASSERTION	Apache-2.0
Downloads	—	498k/wk
Trust dimensions (points earned)
Safety / integrity / 25	12.0	13.1
Identity & provenance / 18	10.8	10.8
Transparency / 17	13.3	14.0
Maintenance / 20	19.9	20.0
Adoption / 20	11.2	19.5
Runtime capability surface (full matrix)
MCP server	Declared	Declared
External providers	—	—
Requires API keys	No	No
Plugin surface	extensions	extensions
Provenance drift	—	Match

Open in the live compare tool → Jan profile vLLM profile More LLM Gateways & Infra →

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 →