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

laya-mlx-server

tankerwng2

Serves laya-mlx over HTTP using the Jev protocol and exposes an MCP interface

0·GitHub repo

laya-workflow

oliveagle

Ports a workflow engine to Rust and includes an inference crate that serves the Laya model

0·GitHub repo

Miya

snowman6-git

Korean-first Minecraft agent driven by a fine-tuned Laya decision model

0·GitHub repo

layapilot

sanjeevranjaniitb

Simulates autonomous driving with Laya making real-time typed decisions

0·GitHub repo

layafill

danioh04

Fills job applications automatically through a Chromium browser extension

0·GitHub repo

laya-desktop

mategog

A desktop workbench runs Laya decisions offline, calibrates questions, and serves an API and MCP

0·GitHub repo

laya-guardrails

javimp2003

Spanish-language guardrails use a self-hosted typed-decision model to check agent inputs, tool calls, and outputs

0·GitHub repo

laya-guard

dockndevai

A local risk guard combines deterministic rules with Laya decisions to confirm or block dangerous commands

0·GitHub repo

codex-sidebar-laya

vit-cerny

A Codex browser planner uses local Laya to select safe next actions

0·GitHub repo

laya-ollama-demo

pyardley

Routes support tickets with Laya and uses Ollama to draft replies when needed

0·GitHub repo

laya-browser-mcp

bala2006

Adds local Laya-driven browser automation tools and an Autopilot loop to Playwright MCP

0·GitHub repo

Laya-jev-mcp

ronisaguey-ux

Provides an MCP server that scores candidate actions with local Laya or hosted Jev

0·GitHub repo

herdr-laya-router

candidosales

Routes coding tasks to AI agents using a local Laya classifier

0·GitHub repo

sayso

AshutoshKY

Uses on-device Laya to select Mac apps and system actions from voice commands

0·GitHub repo

evidence-gate

AnotherMeatsack

A local workbench for evidence review, task routing, MCP tools, and reproducible Laya evaluations

0·GitHub repo

dsh-decision-layer

xbzbing

A structured decision plugin for DeepSeek Harness with configurable Jev-compatible backends

0·GitHub repo

neo-vs-morpheus

hakkisagdic

An Ultima Online duel bot driven by local Laya or cloud Jev decision models

0·GitHub repo

EmailDetective

kaicao

Classifies messages as phishing or legitimate with Laya in an Agno agent served locally

0·GitHub repo

vibecheck-jev

mgd34msu

Tracks coding-agent work in SQLite and verifies reports with a configurable judgment model

0·GitHub repo

jev-hearthstone

ChienIKao

Automates Hearthstone play using local Laya decisions and Android emulator controls

0·GitHub repo

laya-plugin

Andrei-cloud

Provides an offline Laya decision plugin for coding agents through MCP and native integrations

0·GitHub repo

laya-orchestrator

emanuelediluzio

Combines Laya decisions with code-generation models to orchestrate autonomous software development

0·GitHub repo

yanng-laya-skill

xiaoyanng

Teaches coding agents to make local typed decisions with Laya and use confidence gates

0·GitHub repo

fast-laya-compaction

kartikeyaagr

Trims stale Claude Code tool output using local Laya classification 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