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
llm-prompt-techniques-on-jev
Chain-of-thought and self-refinement for TypeSafe's Jev: feed its typed answers back as state and ask again. Benchmarks vs TypeSafe's own cookbook numbers.
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
- 2
- 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.
One model (`typesafe-ai/jev` = jev-1.13, September 2026), every technique on every item, all runs through `dspy.Evaluate` with the scripts in [`benchmarks/`]. Full tables per benchmark are in [`results/`].
Evidence commit: 73a631eb52f2ca11bf1305df25c7e13ee0253b82
Discovered through: github-search.
How we review →