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-clinic-triage-eval
Early evaluation of TypeSafe's Jev on clinic call triage: 98.6% accurate when confident, 116k decisions per dollar
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-21
- GitHub stars
- 0
- 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.
At launch TypeSafe's own API was waitlisted, but Jev is served by Vercel AI Gateway as `typesafe-ai/jev`. It is not on OpenRouter. The gateway's format differs from TypeSafe's documentation in ways that are not documented anywhere. These differences were checked against both APIs on 2026-09-20:
Evidence commit: d65e6bf310515b31207ed194f727c6c8a53c2c86
Discovered through: github-search.
How we review →