typed-decisions

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.

🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

Jev demos, projects, SDKs and skills, with source links and a curated X gallery.

Typed decisions with TypeSafe's Jev, the first System One model

Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels integration, and runnable examples with documented OS, SDK and model requirements.

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

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

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

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

An instrumented 2048 web lab where every move is a Jev (TypeSafe AI System One) Choice, with no heuristic fallback | 用 Jev 决策模型驱动每一步的 2048 网页实验台，概率、置信度、延迟与成本全部摊开可见，且刻意不做启发式兜底

Jev-style typed decisions from Qwen3.5-2B logits — one forward pass, zero decoding, zero fine-tuning.

Fast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay

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.

Open-source projects that provably call Jev, TypeSafe AI's System One model. Every entry links to the line of code that proves it. Refreshed daily.

Curated catalog of System One / Decision Models — contributions for modelsystem.one

Drop-in /v1/systemone proxy that shadows Jev with local decision models (Kev, Laya) and reports whether you can swap