Laya for agents

Agents make many small decisions: which tool to call, whether an input is safe, which element to click. Laya answers each one as a typed probability in one forward pass, locally, so an agent can branch on a number instead of parsing prose from an LLM.

606 projects

G

@alisio/plugin-laya

gustavogutierrez

An Alisio plugin that runs local Laya models for select, boolean and ordinal decisions

0·npm package
K

calvino-laya

kevago

Banking customer-service decision engine with Laya multilingual as the System 1 classifier

0·HF Space

laya-layer

bsisduck

Enforces policy, budgets, and local semantic checks for agent applications

0·GitHub repo

aubin

Emrevrg

Provides calibrated decision models, computer-use tools, and a Laya/Jev-compatible API

0·GitHub repo

laya-agent

leoantony72

Routes Windows desktop and browser-control commands with a Laya Choice model

0·GitHub repo

laya-decision-skill

xyzln

A dependency-free skill implements the Laya System 1 decision protocol

0·GitHub repo

laya-agent-gateway

JohnGF

A local Laya gateway routes prompts and session modes for AI coding agents

0·GitHub repo

laya-mcp-server

AIAI-Laboratory

A self-hosted Laya decision service exposes MCP and REST APIs for AI agents

0·GitHub repo

jev-laya-decisionmodel

zhaojie911272507

A runnable Python tutorial teaches Jev and Laya decision models and their use in agent systems

0·GitHub repo

crypto-paper-trader

saikrishnachatare-spec

Simulates cryptocurrency trades using Laya signals and public Coinbase market data

0·GitHub repo

hybrid-decision-agent

musaugurlu

Tests a Laya-first agent architecture that routes requests to Gemini Flash and benchmarks its performance

0·GitHub repo

jev_flappy_bird

iamdgarcia

Controls Flappy Bird by using Laya ONNX inference to choose whether to flap

0·GitHub repo

c3-service

kiliankaena85-byte

A lead-generation and stair-estimation service combines Laya System 1, Gemini, computer vision, and Telegram

0·GitHub repo
V

trace-sec

vk.amogh

Security checks for coding agents with SecureBERT and a fine-tuned Laya ONNX router

0·npm package

laya-cli-skills

MIt9

Provides reusable agent skills that run local typed decisions through laya-cli

0·GitHub repo

pybullet-yolo-laya-sorter

cf2018

Uses Laya to direct a simulated robot arm sorting colored cups

0·GitHub repo

flyagent

JamesKevinJones

Combines a Drosophila circuit simulation with an asynchronous typed-decision layer that can use Laya

0·GitHub repo

juggernaut

prayingperceptions

Provides a single-goal agent template using laya-mlx for local typed decisions on Apple Silicon

0·GitHub repo
L

laya-superfast

LazyHuman

Serves Laya decisions through an MCP bridge and browser automation relay

0·HF Space

video-to-screenplay-laya

vamshicreates

Adds Laya-based transcript triage to a video-to-screenplay workflow

0·GitHub repo

pi-laya-auto-classifier

finngreig

Adds a Laya-powered local classification gate for tool calls in the Pi coding agent

0·GitHub repo

reflexarc

lumenform

A Python desktop pet uses optional Laya decisions to nudge its behavior

0·GitHub repo

system-one-demo

dinh144

A research demo compares Laya, Kev, and small language models for agent-memory decisions

0·GitHub repo

gmail-auto-cleanup

nani-stack

A Python tool triages Gmail using either local Laya or hosted Jev decisions

0·GitHub repo

MCP servers

The core package includes an optional MCP stdio server with laya_predict, laya_route, laya_preset and laya_status tools:

pip install "laya[mcp]"
laya-mcp-server
{
  "mcpServers": {
    "laya": {
      "command": "laya-mcp-server",
      "env": { "LAYA_DEVICE": "cpu" }
    }
  }
}

Other options:

  • laya-mcp (NVentimiglia): pip install laya-mcp, with guardrail, routing, PR-diff and moderation tools.
  • ollaya: claude mcp add ollaya -- ollaya mcp.
  • typesafe-mcp: built for Jev, and can point at a local Laya server through TYPESAFE_BASE_URL.

Browser automation

  • laya-browser-agent: Playwright/CDP browser decisions with Laya, speaking TypeSafe's /v1/systemone dialect. It also publishes a fine-tuned browser checkpoint.
  • laya-ultrafast: a port of browser-use/jev-ultrafast that runs Laya through laya-mlx (Apple Silicon only).
  • The core repository documents a browser-agent fine-tune on one 16 GB GPU. Element top-1 accuracy went from 0.10 zero-shot to 0.66, and task success from 0% to 62%.

Agent frameworks and evals

  • system1-agents: prebuilt browser-use, computer-use, robotics and game agents on Jev, Laya or Cua-S1.
  • jevals: agent evals and guardrails as typed decisions (pip install jevals), with Laya as a local option.
  • FluidUse: on-device computer use on macOS, with Laya over Core ML.

Caveats

laya-ultrafast states it plainly: Laya answers narrow questions well (which field is the destination, whether two dates match) but does not reliably answer "what should the browser do next?". Those projects combine narrow Laya questions with rules. The zero-shot numbers above also show that fine-tuning is where most of the gain comes from.

Hosted option

An agent that runs in the cloud may not have a GPU or a Mac next to it. layahost serves Laya, and Cloudflare's open Clef models, over the Jev-compatible /v1/systemone. It has an MCP server for agents, an n8n community node (n8n-nodes-layahost) and a prompt_injection template for screening web pages, emails and tool output before an agent reads them. layahost is run by the makers of laya.tools.

More ways to use Laya