Local alternative
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Details →★ 21,612
luce
Luce: a recipe for calibrated decision models — a sentence about your task in, a small model that answers typed questions with honest probabilities out (init → synth → train → eval → serve)
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- Apache-2.0
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-20
- GitHub stars
- 7
- Evidence checked
- 2026-09-24T08:40:10.508Z
- Metadata checked
- 2026-09-24T08:40:10.508Z
- Check status
- current
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
Three question types, same as TypeSafe's Jev interface: **Choice** (one of N options), **Score** (an ordered scale), **Noul** (a statement is true or false).
Evidence commit: ec584762a01c9117ca5d30845f98cb663a8fd60f
Discovered through: typesafe-field-guide.
How we review →