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.
jevcheck
Behavioral contracts for TypeSafe Jev — pin production expectations, eval model upgrades, catch flips and confidence regressions.
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-19
- GitHub stars
- 1
- 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.
The repo’s `jev-1.13` / `jev-1.14` strings are **unverified example pin labels** used by fixtures. A documented TypeSafe version pin (2026-09-19 model list) is `jev-1.13.0`. Floating aliases `jev-latest` and `jev-preview` are rejected unless you pass `--allow-unpinned`. With that opt-in, a response whose `model` is the concrete resolved ID (for example `jev-1.13.0`) is accepted; the eval report prints that resolved model. Concrete pins still require exact identity.
Evidence commit: f6db69924fe7461bce0b015fb97250582ceb2e58
Discovered through: github-search.
How we review →