jevper

Repository description

The repository describes its purpose as: Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients: probabilities and confidence instead of prose

Source evidence

The daily check found an explicit Jev / TypeSafe AI connection in the original README and implementation files at the same commit.

The [Jev](https://docs.typesafe.ai) interface — `state` in, typed `questions` (`noul`, `choice`, `score`) out, answers carrying probabilities and confidence — on top of any OpenAI-compatible model.

Automatically source-checked: public repository, pinned README, and implementation files. Not run, benchmarked or security-audited.

How automated checks and editorial selection work