jev-model

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

Deep research tool for local knowledge base.

A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.

Calibration-aware reinforcement learning for adaptive decision systems

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it tells you. Deterministic-first, tool-agnostic.

Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.

A simplified functionality reproduction of Jev-style decisions with Gemma 4. Native multi-modal ability, finetuning free, runs locally on your machine.

Code and data for evaluating Jev, a System One model, on scientific decisions and how its choices affect downstream results.

An open-source, small and fast Jev-style model for structured text and vision decisions.

Windows port of Laya typed-decision AI (ONNX Runtime + DirectML) — Core ML/Apple Neural Engine alternative with first-class Arabic support. No text generation, no hallucination, runs on any DX12 GPU.

an Information-Geometric Analysis Toolkit for any System-one (Jev, Jevlike) agent systems

Jebadiah, an open System One decision model: trainer, data builders, evals and every run record

decision-first data cleaning system powered by Jev

LISA: Leak, Injection & Simplicity Auditor. GitHub Action that uses TypeSafe Jev (a system one model) to flag secrets, security vulnerabilities, and unneeded complexity in pull requests

No yap, only fax. bruv a CLI tool that runs Jev, Simple Jev and other supported open models to turn your data into a clear yes, choice, or score.

When Jev meets LLM — Transparent proxy that makes AI coding agents 3× faster and 80% cheaper. Cut response times from 2.4s to 890ms with Line J architecture.

Jev-trading is a desktop application that combines the ultra-fast neural network model Jev (by TypeSafe AI) with an intuitive visual interface. We've created a platform where the power of algorithmic trading is accessible without writing a single line of code, messing with Python scripts, or configuring servers in the terminal.

Clanker frustration insights, powered by on-device Laya decision model.

Security requirements analysis with JEV, LangChain Deep Agent review via LLM, and deterministic Python reporting

Reproducible Laya-CoreML vs Jev benchmark for zero-shot intent classification on Banking77, ArBanking77, and CLINC150. Includes paired accuracy and per-dataset results.