system-one-model

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

200+ plug-and-play Jev recipes: small, calibrated AI decisions that route, grade, gate, compare, and label text for agents, RAG, support, code review, and music. Import from JavaScript or TypeScript, or call the CLI with JSON from any language.

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwright/CDP, MCP-friendly.

⚡ Foq — the FREE, local, open-source alternative to Jev. Typed System 1 decisions in ~25 ms — no waitlist, no cloud, no per-token cost. foq.fr

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

Blazing-Fast Token-Efficient Intrusion Detection System (IDS) based on TypeSafe's Jev.

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

decision-first data cleaning system powered by Jev

An evidence-graded deep dive into Jev (TypeSafe AI's System One model): interface, verification, reproduction comparison, and field guide. Bilingual (EN/中文), with runnable probe tools.

Open-source System One decision model built on Qwen3.5. Lumen leverages mixture-of-LoRA adapters, conformal prediction, and block-causal attention to deliver highly calibrated, multi-format decisions (discrete, ordinal, binary) optimized with focal PSR loss.

Hands-on research lab for TypeSafe's Jev (System One model): reproducible benchmarks of Noul/Choice/Score primitives, confidence gating, fan-out latency, agent control — plus a living audit of the Jev ecosystem.

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

A crawler-maintained directory of projects built on Jev, TypeSafe AI's System One model. Daily GitHub + npm sweep, human-merged.

A coding agent CLI where Jev (TypeSafe System One) or Laya decide what to do next and a configurable LLM does the work.

system one model serving engine

Jev(TypeSafe AI System One Model) 스터디 — 타입화된 결정·RLCD·confidence-gated routing을 한국어 노트와 TypeScript 목업으로 정리

logits to multiple-choice questions for Qwen3.8-27B

Local, open-source computer use on macOS: Laya (open System One model) decides every step over the Accessibility tree. No screenshots, no cloud, no coordinates — a local Jev alternative.

Prototype of Jev-powered Root Cause Analysis for events