The Laya project directory
Laya turns any text into typed decisions in milliseconds, on your own machine. Here is what it does, and 2330 projects people built with it.
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?
choiceHow urgent is this?
scoreDoes the customer threaten to cancel or leave?
yes / noDecided in 30.7 ms · 3 typed answers · one forward pass
Real outputs from Laya, not a mock-up. Run it yourself →
Seen on X this month
All demos →
Local Laya beat @OpenAI's decision API 🕷 Four decision models raced down a web page ripping out links that name a spider and Laya running locally on an M5 Max took 34 ms a link so it checked 3x more than the cloud models Run decision models locally ->
QVAC SDK 0.22 is out, and it adds Laya, a model that makes decisions instead of writing text. We added: - Laya support: answers the questions you define, each with a probability - CUDA support: for LLM, embedding and VLA models. - MiniMax-H3 image to video: start a clip from your own picture - MOSS-SoundEffect v2: create sound effects on device - Model fit checks: broader model coverage, improved estimates for model combinations, and opt-in load refusal before model loading begins - Parallel tool calls: agents run several tools in one turn Learn more in the thread below. Complete release doc here: Star ⭐️ for updates.
Local vs cloud at Tetris. • Jev (cloud): 316ms per decision, buried alive, game over • Laya (local, open-weights): 43ms per decision, running clean on a 16GB MacBook Air 11x faster and it didn't even need the cloud to get there.
Laya can help protect your website from agentic attack jailbreaking. Imagine a swarm of agents attacking your website, and in under 33 ms, it all gets blocked. Also, before the agent is allowed to call a tool (send email, query a database, execute code, etc.), Laya can answer: “Is this action consistent with the original user request and safe under the current policy?” Low confidence or a clear “no” triggers a human review or hard block. All on your browser with the 421 M model on edge!!!
Project: laya→
Pi v1.1.0 is out! Highlights: - Program status reporting via OSC 7501: terminals and agent dashboards see whether Pi is working, blocked on a dialog or login, done, or failed. PI_PROGRAM_STATUS=1|0 overrides detection. - Claude Haiku 5.5 (anthropic/claude-haiku-5-5) added, with adaptive thinking up to xhigh/max effort and prompt caching on Bedrock. - --tools now accepts +name/-name to adjust the default selection instead of replacing it, e.g. pi -t +codemode,-write. - GPT-6 Luna available as a Decisions API classifier; native llama.cpp models (Julia-1, Laya, Kev, lev, OpenJev) served by llama.cpp 0.6.0+ run as classifiers through /v1/systemone. Complete details in thread ↓
苹果芯片本地自动化迎来新突破：开源项目 FluidUse 实现了完全基于端侧运行的“Computer Use”。 它摒弃了昂贵且高延迟的云端多模态大模型方案，通过 macOS 原生的 Accessibility API（辅助功能接口）直接抓取运行中 Mac 应用或浏览器页面的表单上下文，由 Apple 芯片的 Neural Engine（ANE）或 GPU 运行超轻量端侧模型判定填入内容，再直接驱动系统完成键入与交互。 核心特性与性能亮点： • 极致速度与能效：运行 706K 参数的表单模型 CUA-S1-FORMS 时，在 Neural Engine 上的单次决策延迟仅约 1 毫秒（0.9ms）；搭配 322M 的 laya 模型，单次前向传播直接输出选择与评分概率，无需逐字生成 token， short 决策耗时仅约 3.7ms。 • 全面的端侧模型矩阵：支持 GLiNER 2.5、Kev-0.8B、Clef-vision（端侧视觉决策）、Decision 2.0/3.0 以及用于意图分类与 PII 隐私脱敏的 Vela 2.0。除了自动填表，还适配了 Tetris、2048 等交互演示。 • 100% 数据隐私安全：计算完全在本地设备完成，零数据出机，非常适合财务报销、内部审批、客户凭证录入等敏感场景。 • 清晰的安全边界：专注把字段匹配到已有数据画像，不盲目生成长篇自由文本，且默认不自动触发最终 Submit 提交，兼顾自动化与人工复核。 对于探索端侧 AI Agent、Swift + Core ML 落地以及隐私优先型工作流自动化的开发者，这个项目提供了一套极佳的工程实践范式。 项目链接：
Project: FluidUse→
colibri
JustVugg
Runs large open models locally in pure C, including Laya for typed decisions
laya
NandhaKishorM
Runs multilingual typed-decision models and provides routing, serving, and integration options
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya
convaiinnovations
A multilingual-ready System 1 model that returns calibrated typed decisions over text in one pass
laya-coreml
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine
laya
receptron
Runs Laya typed-decision models from Node.js and TypeScript through ONNX Runtime
laya-multilingual
convaiinnovations
A multilingual System 1 model that returns calibrated typed decisions over text in one pass
typesafe-mcp
itsmostafa
Connects AI agents to typed-decision models through an MCP server
laya-demo
convaiinnovations
A Gradio demo for Laya typed decisions, multilingual routing, moderation, and RAG filtering
openJev-verdict-2.0
Heman10x-NGU
Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya
quackd
rokbenko
A Python CLI coordinates robots using LLMs, vision-language-action models, and decision models
laya-ultrafast
ipenywis
Runs a browser automation agent using local Laya decisions through MLX
mu
qybaihe
Provides a coding agent with a judgment kernel that can use Laya as its local judge
laya-typed-decisions
convaiinnovations
A Laya model fine-tuned for agent traces, customer service, invoices, and security incidents
FluidUse
FluidInference
Automates form filling on Apple devices with on-device models, including Laya through Core ML
jev-cookbook
datawhalechina
Teaches Jev and demonstrates fine-tuning and serving the open-source Laya model
laya-playground
wdobry
A local website combines Laya model demos, games, a benchmark, and an agent skill
keel
codejunkie99
A macOS coding workspace uses local Laya or hosted Jev to select task routes
laya-mlx
aac6fef
An MLX FP16 conversion of Laya for native inference on Apple silicon
laya-vs-jev
virajbhartiya
A side-by-side T-Rex game compares local Laya and hosted Jev decision models
laya.cpp
lkarlslund
A native C++ runtime runs Laya typed-decision models across GPU and Apple backends
jevals
openlayer-ai
Agent evaluation and guardrail tools run with local Laya, Kev, or hosted Jev
system-one-foundation-models
peterfriese
Bridges Laya and Jev System One decision models into Apple’s Foundation Models framework
chat-seek-vscode
fstandhartinger
A VS Code extension searches chat archives and uses Laya to rerank matches
