Jev Local LLM

An open-source platform for creating, distributing, and running sovereign EU-compliant LLMs: one Rust binary with OpenAI- and Ollama-compatible APIs, decisions answered as probabilities in milliseconds, and an audit trail designed for the EU AI Act.

A small Python sample that uses OpenThai-SystemOne to recommend which of Windows, macOS, Linux Desktop, Android and iOS/iPadOS best fits a user's needs. A generic decision() helper builds one Noul question per option and sorts the match scores.

Open reimplementation of the Jev decision-model idea: masked-logit softmax turns any small local LLM or OpenAI-compatible API into a type-safe decision engine with raw probabilities. Also ships a WeChat/QQ/Telegram crush radar with a verdict and next-move advice.

Fire-evacuation simulation where every occupant gets a Jev-style typed decision engine: a local Ternary Bonsai 2 27B, Qwen3.5-4B or the TypeSafe Jev API reads choice probabilities, while movement runs on validated social-force physics.

A lightweight Python engine that mimics Jev's structured decisions on local LLMs via Ollama, vLLM or llama.cpp: choice, score and noul questions come back as JSON with probabilities and confidence, plus an OpenAI-compatible gateway.