RISC-jeV

离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev

A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.

A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.

Turn any open model into a classifier/jev endpoint

The same decisions, on CPU. System One model that can run on your Personal Computer.

turn any llama-server into a jev system one endpoint

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)

Agent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable script

A WebGL demo where you play the card game Speed against a CPU whose brain is TypeSafe AI's Jev. The whole point of the app is to measure and show Jev's decision speed and decision accuracy in real time.