User repository on GitHub
Local System One-compatible decision server for Laya backends
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Systemone Workbench
A local workbench for System One-style models on Apple Silicon Macs: it serves Laya through MLX or Core ML behind a Jev-compatible /v1/systemone endpoint, proxies other Jev-compatible servers like Jeff and Kev, recommends models and evaluates them on Japanese data.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- katya4oyu
- Last verified
- Oct 2026
Works forJev for Evaluation
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceRuns locally
Highlights
- Serves Laya via MLX or Core ML behind a Jev-compatible /v1/systemone endpoint, which the README says the official SDKs can use as-is.
- Proxies other Jev-compatible servers such as Jeff and Kev by model name, and can register fine-tuned checkpoints.
- A /v1/recommend endpoint takes a task description and answers which model to use; a Japanese evaluation suite under eval/ja/ compares Jev, Laya, Jeff and Kev.
- Requires an Apple Silicon Mac; the README states the project is independent of TypeSafe Jev and ships no Jev weights.
- Formerly named jev-systemone-local, with old command and env var names still accepted; Python with uv and FastAPI, MIT, 0 stars.
Watch out
README reviewed 2026-10-17; it is written in Japanese and the captured excerpt cuts off during the startup and iPhone section, so exact commands, port, API shapes and usage screenshots are not available in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A local workbench for System One-style decision models on Apple Silicon Macs: it serves Laya behind a Jev-compatible endpoint, proxies other Jev-compatible servers, recommends models and evaluates them.
It exposes Laya on a Jev-compatible /v1/systemone endpoint so the official SDKs can call it directly. The README says it includes no Jev weights and is an independent project unrelated to TypeSafe Jev.
Laya via MLX, Core ML and ONNX, implemented in that order, with laya-mlx first. The README insists unsupported backends are managed by their real implementation names and not treated as supported.
Forward requests to other Jev-compatible servers like Jeff and Kev by model name, recommend a model from a task description through /v1/recommend, evaluate models on Japanese data and run Laya fine-tuning.
An Apple Silicon Mac: the README's operation target is Apple Silicon and the backends are built on MLX and Core ML. No cloud or Linux option is described in the captured text.
No. The README states it is an independent project with no connection to Jev itself and no Jev weights; it was formerly named jev-systemone-local, and the old command and environment variable names still work.
Python for the server, uv for dependency and environment management, and FastAPI for the HTTP API; the README says the API structure follows the earlier laya-serve implementation. The repo is MIT-licensed with 0 stars.
More Jev resources like this
A proof-of-concept HTTP service for constrained decisions with a local MLX model: send text or JSON plus typed choice, score, or noul questions and it returns probabilities over the answers you declared — no generated text, no parsed model JSON.
Jev Tools & CLIs#community#github#python
Community
snellingio/system-onePython
snellingio/system-onePythonA small proof-of-concept app that runs local Laya and external System One-family APIs in one judgment UI: it executes typed questions against a state and compares choice probabilities, yes/no probabilities and ordinal scores across providers.
Jev Demos & Experiments#community#github#python
Community
keispace/systemonePython
keispace/systemonePythonA local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict — with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonA local, non-autoregressive security guardrail suite powered by Convai Innovations' Laya model, returning typed decision probabilities for security inspection. It positions itself against Jev on latency and against generative LLMs on hallucination risk.
Jev Tools & CLIs#community#github#security
A 32M-parameter typed-decision model plus a Chrome extension that runs entirely on-device with WebGPU/WASM and Moonshine speech recognition. Its local server speaks POST /v1/systemone, so existing Jev clients work by changing the base URL; a benchmark table claims zero option-order flips.
Jev Tools & CLIs#community#github#chrome-extension
Community
MeharPro/GenClassPython
MeharPro/GenClassPythonA technical knowledge assistant that runs adaptive RAG over 11 technical books (2,810 chunks) with hybrid dense and BM25 search, reciprocal rank fusion and a JEV System-1 decision engine over a local vector database.
Jev Tools & CLIs#community#github#rag
Community
rudra-p11/techbook-ragHTML
rudra-p11/techbook-ragHTMLFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.