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
agent-workflow-benchmark-results
results from iterative benchmark runs
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Python
- License
- Apache-2.0
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-22
- 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.
The qualification evidence records three successes for each study: BM3 had one task-class disagreement under shadow disposition and semantic-risk uncertainty fallback in all three phases; BM4 and BM5 matched deterministic route recommendations in all three phases. BM4 also contains separate advisory TypeSafe source-review experiments; these do not affect its benchmark score or eligibility. No benchmark presently demonstrates that Jev/TypeSafe improves product quality or reduces execution cost.
Evidence commit: 241a2980a75ae8e344d26c2a40e496cc8c889f7b
Discovered through: github-search.
How we review →