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
jev-curate
High-throughput synthetic and pretraining dataset sifter for TypeSafe Jev. Rust streaming core, Parquet and JSONL I/O, typed Choice/Score/Noul judgments, speculative fan-out, 24.0 rows/sec measured.
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Rust
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-18
- GitHub stars
- 48
- 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.
Keywords: typesafe ai, type safe ai, jev, api.typesafe.ai, jev-1.13.0, jev-latest, system one, choice, score, noul, dataset curation, synthetic data filtering, pretraining datasets, post-training, fine-tuning, rlcd, reasoning models, parquet, arrow, polars, pyarrow, pyo3, rust, jsonl, llm evaluation, speculative fan-out
Evidence commit: a188d720bdd2ad6120f10824af41da77f95419c8
Discovered through: awesome-jev.
How we review →