Can I really drop this in where my Jev client already calls?

Yes for the wire shape: point an existing Jev client at the local /v1/systemone endpoint and the state-plus-questions contract carries over, though model behavior and tuning still differ.

What is the offline story for air-gapped or intranet use?

Install the npm package and fetch the cached model once; inference needs no Python, PyTorch, API keys, or cloud calls, with native binaries on Node and Bun.

When should I embed it versus running the HTTP service?

Use it in-process for zero network overhead, or launch the CLI service with host, port, backend, and optional bearer auth; the browser path needs hosted model and WASM assets.

What is the catch with running decisions in the browser?

Seconds per question instead of milliseconds, roughly an order of magnitude slower than native in the repo notes; keep the browser build for demos and run native where latency matters.

What happens on the first run, and how big is the model?

The right engine for your machine installs automatically, and the model, about 324 MB, is fetched once on first use and cached. After that inference needs no Python, PyTorch, API keys or cloud calls.

Does Laya System-One support long inputs?

maxLen defaults to 2,048 tokens and can be raised to 8,192 for long documents through the Laya.load options. The model answers in English, Portuguese, Spanish, German, French, Chinese, Japanese and more than 100 languages out of the box.

How does the HTTP service handle auth and errors?

Pass --api-key or set LAYA_API_KEY to require a Bearer token on /v1/systemone; without it the endpoint is open. A configured but missing or wrong header returns 401, invalid JSON or missing state and questions returns 422, and a body over 4 MB returns 413.

CommunityJev Models & Reimplementations

Laya System One

Zero-dependency Node package wrapping the Laya decision model for offline typed answers, usable as a CLI service, in-process library, or browser build.

See highlights

Open github.com

Stars: 4
Language: JavaScript
License: APACHE-2.0
Published by: Community
Author: italoalmeida0
Last verified: Oct 2026

italoalmeida0/laya-system-one

User repository on GitHub

View on GitHub

Self-contained, ultra-fast System 1 decision engine with WebGPU/WASM acceleration, 100% wire-compatible with TypeSafe Jev (/v1/systemone).

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Runs entirely on your machine. No Python, no PyTorch, no API keys, no cloud calls at inference time. One npm install and it works. 🔒 100% Offline: Nothing leaves your machine. Ideal for corporate intranets, edge servers and privacy-sensitive workflows. ⚡ Fast: 40 ms per question on a warm engine, measured on every platform we ship for. 🔄 TypeSafe Jev Compatible: Drop-in POST /v1/systemone. Point an existing Jev client at it and it just works.

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Classification

Used inJev for Software & DevTools

Languages: JavaScript

Highlights

Answers choice, score, and noul questions offline with calibrated probabilities, confidence, and decisions.
Ships as a CLI HTTP service, an in-process predict API, and an embeddable server for existing apps.
Supports Node, Bun, and browser WASM builds with zero npm dependencies and one install.
Covers bearer auth, token budgets, threading, health checks, and structured error codes.

Watch out

The model weights belong to the upstream Laya project and download on first use; browser WASM runs far slower than native. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

scheda.js

ES6 rewrite of scheda.js for SystemOne-inspired timetable grids, drawing courses on canvas with configurable ids, colors, themes, and PNG export.

Jev Models & Reimplementations#community#github

Community

rrsilaya/scheda.jsJavaScript

djev-spark

221

A Docker Compose image that serves DiffusionGemma 26B-A4B on a DGX Spark behind Jev's systemone endpoint, adding seven not-yet-upstream vLLM perf branches and dependency-keyed multi-stage question reads.

Jev Models & Reimplementations#community#jevbest

Community

mmastrac/djev-sparkHTML

system-one-foundation-models

Native Swift 6 package that evaluates @Generable structs and enums through System One decision models in 15-150 ms, with on-device Laya, self-hosted laya-serve, and TypeSafe Jev cloud backends.

Jev Models & Reimplementations#community#github

Community

peterfriese/system-one-foundation-modelsSwift

gut

Python helper that turns judgment calls into one-liners like likely, classify and rate, defaulting to Jev while also running on local or OpenAI-compatible backends.

Jev Models & Reimplementations#community#github

Community

Kungie/gutPython

kev-onnx

Self-hosted CPU-only server that speaks the /v1/systemone wire format for the KEV decision model, packaged as one container with ONNX Runtime and a health check.

Jev Models & Reimplementations#community#github

Community

aleskxyz/kev-onnxPython

laya-jev-compatible-server

Laya multilingual server exposing POST /v1/systemone and GET /v1/models for noul, choice and score questions, usable with the official TypeSafe SDK.

Jev Models & Reimplementations#community#github

Community

exfly/laya-jev-compatible-serverPython

From the Jev guides

Original write-ups on what this entry is for.

Multimodal Decision Models: What Clef and d1 Change

Oct 12, 2026

Jev takes text only; Clef-omni adds image, audio, and video input and Liquid d1 adds images, each keeping the same typed-answer shape. Where that matters, where it does not, and the costs the vendors underplay.

Jev Models & Reimplementations#multimodal#open-models#decision-model

Read article

The Decision-Model Price War

Oct 11, 2026

One model in September, a dozen by October. Clef, Liquid d1, Perplexity, and OpenAI all ship the same typed-answer shape now. How to read the rival benchmarks and pick on your own task.

Jev Models & Reimplementations#decision-model#benchmarks#pricing

Read article

What Is Actually on Hugging Face

Oct 8, 2026

Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.

Jev Models & Reimplementations#open-models#hugging-face#local

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai