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

near_agi

yassinebkr

Evaluates and post-trains Laya as a local transition predictor for agent planning

0·GitHub repo

Coding_Decision_Agent

SampleBias

A training harness fine-tunes Laya to grade code changes, tool calls, agent traces and routing decisions

0·GitHub repo

routewise-support-agent

sami-rk

Routes customer-support messages with local Laya decisions and handles replies, tools, and knowledge retrieval

0·GitHub repo

laya-browser-guard

pateti-hub

A privacy-first browser extension analyzes website security using optional local Laya ONNX decisions

0·GitHub repo

laya-decision-benchmark

Zerolxgic

Evaluates the Laya decision model under decomposition, distribution shift, and live agent-system inputs

0·GitHub repo

laya-linear-assigner

DamengRandom

Assigns unassigned Linear tickets to engineers using the local Laya decision model

0·GitHub repo

codepilot

GorbunovS

Indexes code and provides MCP search tools with Laya-powered reranking

0·GitHub repo

RLP

senghan1992

Uses Laya to triage coding requests and route work to parallel agents

0·GitHub repo

laya-mcp

kennedyshead

Serves local Laya routing decisions to coding agents through an MCP server

0·GitHub repo

FinLaya

reck98

Uses a local Laya model to generate simulated NIFTY options trading decisions from live market data

0·GitHub repo

laya-cua

anchorbrowser

Drives browser tasks by using Laya for typed action decisions and a writer for free text

0·GitHub repo

Laya_try

kameusagiyahoo

Tests Laya in browsers and on iPhone, including ONNX inference and a runnable Google ADK workflow

0·GitHub repo

laya-mcp

RobcPeng

Provides an MCP server, agent tool-call guards, and fine-tuning pipelines for the Laya decision model

0·GitHub repo

test-laya

tom-scott-dev

Runs a 2D town game where NPC behavior is driven by local Laya decisions

0·GitHub repo

laya-warden

Gjusev

Combines Laya decisions and deterministic rules to supervise agent tool calls

0·GitHub repo

laya_kev_Agent

MinhTriTM

Coordinates coding agents using Laya and Kev decision engines

0·GitHub repo

laya-voice-browser

mo-tunn

Controls Chromium by voice using a local Laya model and Playwright

0·GitHub repo

laya-plays-porklike

AlexandroBG

Uses Laya decisions to guide an observed-only agent through the Porklike roguelike

0·GitHub repo

hermes-laya-router

rengaryang

Routes Hermes Agent model tiers and provides per-turn model selection using Laya

0·GitHub repo

notchvoice

Starlord-999

A hands-free Mac voice assistant that uses Laya-MLX for on-device decisions

0·GitHub repo

podcast-editor

vamshicreates

A multi-camera podcast editing skill that uses Laya to select camera angles

0·GitHub repo

recon3d-cross-cell-deg

hpend2373

Packages a Recon3D analysis skill with Jev and Laya API clients for optional review ordering

0·GitHub repo

jev-touhou

NatBrian

Uses local Laya and Mica decision models to control the Taisei game in real time

0·GitHub repo

LayaGameSuggest

SukandVM

Uses Laya to classify game specifications and Ollama to explain recommendations

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