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-evals
Deterministic evaluation harness for LLM agents, with a calibrated judge (Jev) that can act as a CI gate.
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- TypeScript
- License
- MIT
- 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.
This library makes those checks first-class. For the judgments that genuinely need semantics — *is this reply on-brand, did it actually answer the question* — it asks [Jev], TypeSafe AI's System One model ([typesafe.ai]): instead of writing text, it returns a typed decision — a choice, a score, or a yes/no as a **calibrated probability** — in ~400 ms. `0.91` compares against a threshold. A paragraph does not.
Evidence commit: a703251f7a7a14c9212d357b00b72c8e52e12266
Discovered through: github-search.
How we review →