let-jev-speak
suidouble
TypeSafe's `/v1/systemone` endpoint classifies text — it returns a `choice`, a `score`, or a probability. It does not generate prose. This library makes it generate prose anyway: every word of the answer is a separate `choice` question over a vocabulary, and the loop feeds its own output back in as the prefix.
- License
- MIT
- GitHub Stars
- 2
- Source reviewed
- —
Where Jev makes a decision
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
What this project offers
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Review scope
Based on repository metadata and README with rule-based classification; pending human review, with no independent runtime or performance verification.
Sources and implementation
Related projects
jev-got
phureewat29 · Creative Tools
A Game of Thrones text-adventure demo where a language model writes the story and Jev labels the scene.
jevthoven
cocktailpeanut · Creative Tools
Turns a music prompt into editable multitrack MIDI by asking Jev to choose instruments, harmony, and bar patterns.
ui-generator-instinct-jev
joevidev · Creative Tools
Turns UI descriptions into selections from existing shadcn/ui components, fields and styles.
jev-music-theory-1
adammichaelwood · Creative Tools
Explores Jev on harmony exercises and music-theory questions, alongside a piano demo driven by chord choices.