laya-mlx plays Snake at 60 decisions per second on an M3 Max
介绍比Jev快50倍，在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇！
Project: laya-mlx→The Laya project directory
Everything the world is building on Laya.
Laya turns any text into typed decisions in milliseconds, on your own machine. Here is what it does, and 952 projects people built with it.
real run · laya-mlx
Input text
“Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan.”
laya-mlx · 146 input tokens · 0 output tokens
Which team should handle this ticket?
choice✓ billing98%
technical1%
sales1%
How urgent is this?
scorenot urgent4%
soon15%
✓ blocking81%
Does the customer threaten to cancel or leave?
yes / no✓ yes84%
no16%
Decided in 30.7 ms · 3 typed answers · one forward pass
Real outputs from Laya, not a mock-up. Run it yourself →
- Projects
- 952
- New this week
- 952
- Platforms
- 18
Seen on X this month
All demos →
Local Laya beats Jev at Tetris on a MacBook Air
Local Laya moggs Jev at @grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally ->
Jev decision layer routes tasks and recovers from tool failures
jev + opus 5.5... i simply can't comprehend why everyone isn't building this yet. in my workflow, this cut costs and time by ~80%. i think it's one of the best ways to use it. → pick relevant project notes before loading the context → route suitable tasks to a faster worker → choose a recovery path when a tool fails → run focused checks before the full test suite opus handles the hard reasoning. jev picks from options the harness prepares and validates. i explain how to build the decision layer in the article below:
Laya plays Tetris locally with decisions in about 27 milliseconds
This is NOT Jev. Open source. Runs on your laptop. Decides in ~27 ms, about 200× faster than waiting on a hosted LLM. Here it is playing Tetris by itself 👇
laya-coreml runs 99.5% of operations on ANE at 3.7 ms per decision
Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms per decision on an M5 Pro. Release: Models:
Project: FluidUse→A step-by-step Jev build guide with code and architecture
everything you need to start building with jev, in one article. code, architecture, diagrams... everything you need to follow the build and make it your own.
Directory
+ Submit yours
laya-mcp
NVentimiglia
An MCP server exposes Laya decision capabilities as tools for agent workflows
5·GitHub repo
vgi-laya
lmangani
Runs local Laya inference in DuckDB to filter, classify, and score rows
5·GitHub repo
laya-onnx
MstyAI
Runs Laya decision models locally with ONNX Runtime through a Go library and CLI
5·GitHub repo
laya-jev-compatible-server
exfly
Serves Laya through a TypeSafe Jev-compatible HTTP API
5·GitHub repo
laya-plays-smb3
cv
Demonstrates Laya controlling Super Mario Bros. 3 with recorded, replay-verified decisions
5·GitHub repo
laya-go
neko233-com
Provides a Go server and agent integrations for structured Laya decisions
5·GitHub repo
omp-laya-judge
F0Rextasy
Adds a local Laya-powered decision judge and MCP server for oh-my-pi
5·GitHub repo
headroom
llm-learner
A local-first Codex plugin estimates prompt load using Laya scoring
5·GitHub repo
jev-tests
schacon
Compares Laya, Jev, Kev, and Claude in three macOS typed-decision demos
5·GitHub repo
laya-fast
DJLougen
Runs Laya typed decisions on Apple Silicon with MLX and optional Core ML execution
5·GitHub repo
deqio
ILuce
Serves multiple typed-decision models, including Laya, through a local API and browser UI
5·GitHub repo
reflexbench
brida-ai
Benchmarks Laya and other typed-decision engines across quality, calibration, robustness, and latency
5·GitHub repo
A
laya-multilingual-coreml
aac6fef
Exports multilingual Laya as a portable Core ML bundle for Apple devices
343·HF model
L
laya-jev-benchmark
Luni
Benchmarks Laya against Jev and other models on phishing detection and calibration
4·HF dataset
L
Laya-Multilingual-LiteRT
litert-community
Runs multilingual Laya on Android GPUs using LiteRT
197·HF model
M
laya-multilingual-onnx
mizchi
Exports multilingual Laya to ONNX for native and browser WebGPU inference
4·HF model
C
MacJev-322M-4K-Laya
chaoliangUNSW
Fine-tunes Laya for long-context local Mac agents and compares it with the base model
4·HF model
laya.cpp
shpati
Ports the Laya model to C and C++ for CPU inference on Linux and Windows
4·GitHub repo
laymbda
HQarroum
Runs the Laya decision model as a CPU-only AWS Lambda function with SnapStart
4·GitHub repo
laya-candle
b0xtch
Runs Laya safetensors natively in Rust with Candle and CPU, Metal, or CUDA backends
4·GitHub repo
pastewhat-ranker-v1
mizorewww
Distills a candidate-aware clipboard ranker into Laya multilingual for local inference
4·GitHub repo
laya-zig
li-ming1
Runs the Laya decision model on CPU with a dependency-free Zig runtime
4·GitHub repo
jev-laya-benchmark
harrymunro
Benchmarks local MLX Laya against TypeSafe's hosted Jev on synthetic decision tasks
4·GitHub repo
sysone-bench
instax-dutta
Compares Laya and Jev on identical inputs across multiple decision benchmarks
4·GitHub repo