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

J

janderscience-skills

janderson1719

Provides a corporate agentic workforce of specialized skills with a Jev/Laya decision engine

0·npm package

laya-jev-ultrafast

leisc

A browser agent that uses Laya for typed action and element selection, with Jev as an optional backend

0·GitHub repo

anima3

hulryung-uo

Uses a System One decision brain with Qwen log-probabilities and Laya triage for a game client

0·GitHub repo

XERON

PIXELZX0

Fine-tunes Laya decision models for multilingual classification, scoring, routing, and browser actions

0·GitHub repo

laya-mcp

EbiPenMan

Serves a persistent local Laya model through an MCP Streamable HTTP server

0·GitHub repo

laya-deploy

Pidbid

Deploys Laya as a local judgment backend for omp with an HTTP bridge, MCP tools, and installation scripts

0·GitHub repo

laya-assist-proxy

dwyschka

A local Home Assistant bridge that classifies voice commands with Laya and routes uncertain requests to an LLM

0·GitHub repo

laya-plays-Pokemon

masmoriya

A local model agent plays Pokémon using Laya decisions and Qwen vision

0·GitHub repo

laya_comp_use

InterestingBrainPoops

A Windows screen agent uses Laya to choose UI actions from text-described controls

0·GitHub repo

Laya-GuardRails-Harness

morre95

A Python harness evaluates coding-agent actions with Laya typed decisions and policy rules

0·GitHub repo

classify-goblin

Sharkelot

A local typed-decision service offers Laya alongside rules, DistilBERT, and Qwen backends

0·GitHub repo

laya-jev

kiuckhuang

Adds a local Laya decision endpoint and conformance tests to a Jev browser-agent fork

0·GitHub repo

layacore-mcp

PerryLink

Planned MCP server for exposing Laya typed decisions to agent harnesses

0·GitHub repo

laya-hermes

pavlealeksic

Adds Laya decision tools, routing hints, and output filtering to the Hermes Agent

0·GitHub repo

laya-local

vit-cerny

Runs a browser agent using local Laya decisions or TypeSafe's hosted Jev backend

0·GitHub repo

laya-mcp

devthinker-ai

Serves Laya typed decisions over MCP and HTTP on Apple Silicon using MLX

0·GitHub repo

laya-api

mlnima

Serves Laya Multilingual through a local Python HTTP API and MCP service

0·GitHub repo

laya-mcp

jerepaira

Exposes local Laya typed decisions as tools for MCP clients

0·GitHub repo

laya-deployment

80233456

Deploys Laya locally and tests its typed decisions and LLM integration

0·GitHub repo

laya-codex-triage

kanottonp

Evaluates local Laya recommendations for model tier and reasoning effort in Codex

0·GitHub repo

dsh-laya-router

ricardochen1996

Routes agent requests using a local Laya-MLX typed-decision model

0·GitHub repo

laya-mcp-npm

PerryLink

Launches a Python MCP server that exposes Laya typed decisions to Node.js clients

0·GitHub repo

laya-claude-plugin

noorforeverone

Provides a Claude Code plugin with local Laya decision tools and an MCP server

0·GitHub repo

jev-skill-laya

applex250

Adapts Jev skills to use a local Laya decision API as their sole backend

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