mizorewww/laya-mlx

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

Language modelsPython#apple-silicon#inference#machine-learning#mlx#modernbert

6.0 Early signal Magnitude out of 10. Star growth looks organic. Data as of September 20, 2026.

Open on Seismograph Open on GitHub

About the project

Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.

Useful for

Run local routing of support tickets to departments without cloud APIs
Score a statement against a rubric using the score type and get an expected value
Run the offline laya-snake demo on Apple Silicon to check inference latency

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

0 stars so far today, about 102 expected by the end of the day.
The spike has held for 2 days in a row — not a one-off blip.
The repository is 1 day old and already has 162 stars.
Top new repositories this week: #86.
About 80 forks a day — people are taking the code.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 162
Stars in a day: 102
Forks: 5
Issues and pull requests: 0
Watchers: 0
Language: Python
License: Apache-2.0
Created: September 19, 2026
Last push: September 19, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 20, 2026Top new repositories this week: #86

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/mizorewww/laya-mlx.svg?lang=en)](https://gitnova.dev/en/r/mizorewww/laya-mlx)

Similar projects

7.3
TianyuCodings/NanoJev
A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).

Early signalLanguage modelsPython+340 stars in a day
7.0
githubnext/localjev
A local TypeScript/Bun HTTP service implementing a Jev-compatible POST /v1/systemone API on top of an OpenAI-compatible Chat Completions endpoint (DiffusionGemma via oMLX). It acts as a bridge for typed decisions…

Early signalLanguage modelsTypeScript+270 stars in a day
7.0
higgsfield-ai/higgsfield
Fault-tolerant GPU orchestration and ML framework for distributed training of models with billions to trillions of parameters, including LLMs. Manages node access, experiment queueing, and GitHub Actions integration.

BreakoutLanguage modelsJupyter Notebook+234 stars in a day
6.9
bespokelabsai/nimble
Nimble is a model and training recipe for fast typed decisions over text: given a flat schema of enum and boolean fields, it picks an answer and returns probabilities for each option. It targets routing, condition…

Early signalLanguage modelsPython+285 stars in a day
6.8
docling-project/docling
Docling is a document parsing library for many formats (PDF, DOCX, PPTX, XLSX, HTML, EPUB, audio, video) with advanced PDF understanding: page layout, tables, formulas, OCR. It prepares structured data for generative…

BreakoutLanguage modelsPython+293 stars in a day
6.4
TheoLeeCJ/SemIf
An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.

PeakingLanguage modelsPython+207 stars in a day