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

opencode-memory

pedroteste00000008-stack

Adds long-term memory to OpenCode using Laya decisions, embeddings, reranking, and a local vector store

0·GitHub repo

omp-marketplace

F0Rextasy

Lists a local System-1 judge plugin for the oh-my-pi marketplace

0·GitHub repo

agent-kits

leonezhu

Provides Python integration kits for Laya decision workflows and WorkClaw agent utilities

0·GitHub repo

Jev-agent

To3akaRin

Suggests clipboard entries based on the focused field using local Laya inference or the Jev API

0·GitHub repo

morph-desktop

Locaryn

Controls Windows applications and desktop input with rapid decisions from Laya

0·GitHub repo

semantic-browser

koriym

Navigates hypermedia applications by selecting server-declared links using Laya-MLX

0·GitHub repo

LayaBOT

tomikan1208-code

Uses Laya decisions to control a Minecraft combat bot through Mineflayer

0·GitHub repo

LayaMCP

GeneGulanesJr

Exposes Laya decision tools to MCP clients through an HTTP server

0·GitHub repo

layaagent

rotsl

Routes tasks through Laya classification and deterministic mediation to local or API-based coding agents

0·GitHub repo

laya-mcp

WayneCommand

Wraps the Laya decision model in an MCP server and REST API for agent integrations

0·GitHub repo

laya-mcp

YerikZ

Exposes Laya decision presets as MCP tools for coding agents

0·GitHub repo

pi-laya

K0stIa

Adds typed-decision tools and session controls to Pi using a Laya-compatible service

0·GitHub repo

laya-agent

ahmadfreijeh

A support-action agent combines a Python Laya prediction service with a Node.js customer-facing server

0·GitHub repo

laya-ai

vincent1986

Adds local Laya predictions to agent workflows for intent classification and tool routing

0·GitHub repo

laya-server

r2d-ai

Serves Laya's multilingual checkpoint through CUDA-backed REST and MCP interfaces

0·GitHub repo

laya-memory

ganeshdipdumbare

A local Laya classifier selects relevant durable memories for coding agents across sessions

0·GitHub repo

laya-adblock

Samuel-Ku

Uses a local MLX Laya model to identify and remove likely ads from web pages

0·GitHub repo

laya-agents

lesterppo

Integrates local Laya typed-decision tools into Hermes Agent and Muse for classification and routing

0·GitHub repo

Laya_TESTSUITE

sirwari

Provides Laya tests, demos, routing examples, and MLX setup guidance

0·GitHub repo

laya-skills

wearshoes

Provides agent skills for the Wearglass-hosted Laya typed-decision API

0·GitHub repo

laya-doom-agent

Jaiswal-Siddhant

Uses Laya-MLX to choose actions for an autonomous DOOM agent

0·GitHub repo

laya-robot-arm

ramb5144

Uses structured Laya decisions to control a simulated pick-and-place robot arm

0·GitHub repo

laya-agent-kit

Maxwell00000086

Local Laya decision tools integrate with coding agents and ChatGPT through MCP

0·GitHub repo

laya-mlx-advisor

esse

Uses a resident Laya-MLX model to adapt reasoning effort in Codex CLI and Claude Code

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