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-router-skill

wangmiaozero

Adds local Laya decision routing to coding agents through skills and MCP

3·GitHub repo

auto-mode-for-paseo

obetomuniz

Routes Paseo messages to personas using TypeSafe Jev or a local Laya model

3·GitHub repo

laya-cli

MIt9

A CLI runs Laya typed decisions with batch, routing, and resident-daemon modes

3·GitHub repo

oh-my-laya

leo1394

Installs local Laya tools for classification, scoring, and routing in coding agents

3·GitHub repo

decidealot

psyb0t

Serves local Laya and Von decision models through TypeSafe-compatible HTTP and MCP APIs

3·GitHub repo

laya-ocr-guard

okrath

Adds fast Laya triage to a dual-gate code impact and regression guard

3·GitHub repo

laya-thalamus

lcbkmm

Middleware uses Laya for agent tool routing with confidence-based LLM fallback and evaluation

3·GitHub repo

shed

IAmUnbounded

Provides remote access to desktop coding-agent sessions with local Laya-based routing

3·GitHub repo
N

laya-home-fine-tune-en

nohaah

Fine-tunes Laya to map English smart-home commands to device actions for an offline assistant

2·HF model

jeffrey

thomasbrueggemann

A coding-agent CLI uses Jev or Laya to choose tools while a configurable LLM executes them

2·GitHub repo

laya-needle

50bbx

Finds semantically relevant webpage passages with a locally running Laya model

2·GitHub repo

Rimworld autopilot

Georgy-hook

A local RimWorld colony autopilot uses Laya to choose and issue in-game orders

2·GitHub repo

gutcheck

janmejai2002

Runs calibrated Jev- and Laya-style decisions on local NPUs or GPUs with agent tool leasing

2·GitHub repo

pi-pignon

siiick

A Pi coding-agent extension routes prompts by difficulty using local Laya or hosted Jev

2·GitHub repo

openpave-jev

cnrai

Provides typed-decision commands for PAVE and Claude with local Laya and hosted Jev providers

2·GitHub repo

Routapse

pooyaphoenix

Routes prompts to models or specialist agents using Laya or Jev classification

2·GitHub repo
A

laya-toolguard-mlx

a3harva

Fine-tunes Laya in MLX to assess coding-agent tool calls for safety risks

110·HF model
A

laya-guard-multilingual

Ayaannnnnnn

Fine-tunes Laya to classify coding-agent shell commands and tool calls as allow, review, or block

38·HF model
B

laya-multilingual-calculator-router

Borcherding

A multilingual Laya model routes agent steps by predicting whether they need calculation

18·HF model
I

laya-desktop-v1

ikaanakkok

Fine-tunes Laya for desktop computer-use decisions based on Ubuntu accessibility trees

11·HF model
T

laya-for-clara

TheWiderLensInitiative

A Laya fine-tune routes assistant messages and selects the level of agent effort

8·HF model
J

laya-agentguard

Jojoarumugam

A Laya fine-tune classifies tool calls for destructive risk and third-party content for prompt injection

7·HF model
A

atmem-laya-formation-model-v1

atmem

Provides a finite-choice Laya model for AtMem memory-formation decisions

6·HF model
F

laya-kannaka-supersession

flaukowski

A Laya fine-tune for detecting when newer statements supersede earlier memory facts

1·HF model

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