Repos made with Laya

One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback

Atari-inspired lunar lander with Laya on Apple MLX, compact inference, supervised training, and a VanillaJS demo.

leanest diffs your PR against main, asks one semantic judgment per e2e spec, and runs only the tests it can

Laya4j is a pure-Java 17+ SDK that ports the Laya System 1 decision framework — originally a Python research project — into a production-grade, deployable inference library running entirely on Apache 2.0 multilingual checkpoints via ONNX Runtime and HuggingFace Hub.

A from-scratch, dependency-free Zig CPU runtime for the Laya System-1 decision model: tokenizer + mmBERT-base encoder + decision head in one binary, no Python/torch/BLAS. Work in progress, see README.

Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Native Laya inference for macOS with MLX Swift

一着 · Laya-MLX 五子棋

Serve the Laya decision engine from a macOS menu bar app with an OpenAI-compatible endpoint for n8n

A public test of the Laya typed-decision model on a home energy system.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Decision models (Laya, Kev) in any web page: a zero-dependency Rust engine compiled to WebAssembly, with WebGPU kernels. One import, no server.

Job search in Denmark: aggregates vacancies from jobnet.dk and jobindex.dk, filters them against a profile, ranks matches with the Laya decision model, and outputs terminal tables plus a Markdown report.

Jev vs fine-tuned Laya: reproducible workflow benchmarks, chat moderation, and published OpenAI/Mistral comparisons.

実務判断ベンチマークJP：同一40問によるJevとLayaの計測・設問と回答例・静的比較レポート

Self-hosted console to compare System One decision models (Jev, Von, Laya) against each other using VirusTotal API data.

Can an at-home model match Jev? TypeSafe Jev vs self-hosted Laya on Moroccan Darija sentiment, with reproducible zero-shot evaluation.

Live message tone checker: see tone, formality and fight risk as you type. Powered by Laya, a non-generative decision model.

Zero-shot benchmark of TypeSafe Jev 1.13 (decision model) vs open-weight non-generative models PrismNLI-0.4B and Laya: frozen protocol, raw predictions, calibration, latency, report

60 zero-shot information-extraction & classification systems (57 benchmarked) across 32 families — extractor encoders, zero-shot classifiers, cross-encoder rerankers, typed-decision engines — local, Ollaya-served & hosted (OpenRouter, Cloudflare, TypeSafe); measured…