index / patrice-blp/jev-llm-orchestration
jev-llm-orchestration
TypeScript reference architecture for decision-first LLM orchestration with JEV. Structured decisions guide explicit application control flow, reserving LLM calls for reasoning and generation. Includes runnable examples, behavioral tests, and evaluations of routing quality and estimated token savings.
Learning?RoutingListedTypeScript
Repository
Stars1
LanguageTypeScript
LicenseMIT
Created2026-10-07
Last pushed2026-10-07
Officialno
Judgment
Genuine Jev project0.73
gate 0.5
Uses Jev at runtime0.49
Is a meta list0.04
Is a reimplementation0.15
Quality scales
Substance2.15 / 3
gate 0.5
Docs2.61 / 3
Novelty1.58 / 3
Composite score0.71
Category distribution
Jev's confidence in this category is below 0.5, so the category is shown with a question mark. It is not a listing condition: this entry's status was decided by genuine and substance alone.
Learning0.48
Agent and Dev Tooling0.41
Integrations0.06
Applications0.04
SDKs and Clients0.01
Other0.00
Games and Simulation0.00
Research and Evals0.00
Assigned categoryLearning (uncertain)
Category probability0.48
Category confidence0.41
PatternRouting
Pattern confidence1.00
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev in:name,description,readme created:2026-10-07
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-10-08 12:47 UTC