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-plugin

theo-odore

Routes coding-agent tasks to models based on task type and complexity

0·GitHub repo

laya-desktop-agent

royaldynamo128-gif

Runs a local voice desktop agent with Convai Laya as a decision-routing component

0·GitHub repo

c-elegans-valencia

mateusbsmg

Simulates C. elegans brains and compares connectome behavior with Laya-guided actions evolved by a genetic algorithm

0·GitHub repo

llama-mcp-router

u9401066

Routes requests to relevant MCP tools using Laya and BM25 selectors before forwarding them to llama-server

0·GitHub repo

beebots

kazakhan

Runs Coinbase spot-trading agents with recorded model decisions and hourly Laya-based self-review

0·GitHub repo

dsh-laya-go-decision

Ling0727-ai

Registers a Laya Go decision server as tools in DeepSeek Harness

0·GitHub repo
S

gz-laya-pilot

somedayyoung

Provides a TypeScript browser-testing runtime that uses Laya decisions for exploration and replay

0·npm package

laya_Nav

rvlab-univ

Adapts InternNav's DualNav System 1 decision component to use Laya

0·GitHub repo

laya-browser

vikrambalaaj

Uses Laya with Playwright to select browser elements for goal-directed actions

0·GitHub repo

jev-laya-dsh

alexdoandev

Adds a local Laya decision layer for routing prompts and gating risky agent actions

0·GitHub repo

intent-router-laya

anujgupta9860

Routes queries to worker agents using self-hosted Laya, with optional training and review

0·GitHub repo

litellm-gemini-laya-router

derrickqin

Uses a local Laya model to route coding-agent requests to Gemini models on Vertex AI

0·GitHub repo

AgentSmith

nsh1999

Standalone demos explore local Laya inference, typed decisions, and LLM agent workflows

0·GitHub repo

reflex

priyansh19

A decision gateway combines Laya or Jev decisions with LLM escalation and human guardrails

0·GitHub repo

ai-frontend-guide-kit

urben88

Provides a reusable UI catalog and guided workflow with optional local Laya ranking

0·GitHub repo
L

laya-browser-mcp

LazyHuman

An MCP server for controlling a Playwright browser with Laya decision models

0·HF Space

laya-mcp

kaysermagnus

Exposes Laya typed decisions as MCP tools for agents, reranking, relevance gating and model routing

0·GitHub repo

laya-trader

zakanysa

Tests Laya-driven trading strategies on an on-chain order book and evaluates their real costs

0·GitHub repo

mcts_laya

kthfan

MCTS self-improvement experiments that use Laya as the policy and value network

0·GitHub repo

laya-sec-agent

bsisduck

Governs agent requests and tool execution with policy checks and optional local Laya signals

0·GitHub repo

convents

skorotkiewicz

Coordinates LLM proposals and critiques, then uses Laya to select and synthesize a final response

0·GitHub repo

jev-router-mcp

humayunkabir

An MCP server routes questions to tools through a Jev-compatible decision engine, including Laya

0·GitHub repo

FastFence

llama-lovers

A local policy gateway uses Laya and other models to assess agent inputs and outputs

0·GitHub repo

laya-setup

LeonardoBrum0907

Runs Laya locally as a perception layer for the Ultron system

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