Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
-
Updated
Sep 19, 2026 - Python
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.
An open-source toolbox that takes a game all the way "from idea → built → live" — Unity/Godot/Cocos/Laya clients + one .NET server. | 开源游戏全流程工具箱:Unity/Godot/Cocos/Laya 客户端 + .NET 服务器,从想法到上线一站搞定。
laya3.x引擎 + nodejs 开发的网络麻将,省去了大量复杂配置,极其适合上手
基于Typescript的渐进式通用游戏前端开发框架
A website, two games, a benchmark and an agent skill for Laya, the open-source decision model. Runs on your machine.
Jev-powered search infrastructure for AI agents: zero API keys, MCP-ready, LLM-context aware, with local neural evidence verification.
Dohnuts builds small multimodal models for direct decisions. -> System One model
Gesture support for LayaAir engine(Laya 手势库).
离线可用的本地类型化决策:4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev
World 1-1 cleared with unmodified Laya on DGX Spark. Model-driven jumping, replay-verified frames, and every decision recorded.
To associate your repository with the laya topic, visit your repo's landing page and select "manage topics."