logan-markewich/jeff

Supersimple way to serve LLMs as a Jev-like endpoint

Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

Turn any open model into a classifier/jev endpoint

A local, API-compatible replacement for Jev, TypeSafe's System One model

Super fast Jev like server in JS, model agnostic, working with any OpenAI compatible endpoint

Bulk classification and decision inference on one GPU: the content is read once, every question about it is scored in the same pass. OpenAI-compatible, Apache 2.0

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.