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
voice-assistant-laya
Joshua265
A prototype Wayland voice assistant uses an ONNX Laya model to decide desktop actions
laya-chat-release
LAGcomcom
A Windows chat assistant uses Laya to assess conversations and rank drafted reply suggestions
app-intents-laya-study
junshanxu
Studies macOS App Intents and CLI agents with and without a local Laya next-action gate
hermes-laya-arbiter-integration
osviel91
Connects Hermes Agent to Laya/Arbiter decision tools through MCP
TALK---A-Decision-Making-Model-Leveraging-Laya-and-Jev-
navzar81-dev
Provides a voice-first decision app combining Laya with cloud LLM research and document grounding
canvastty-plugin-assistant
BIackFIame
Adds a CanvasTTY assistant for command review, task triage, and orchestration advice
fast-brain-deep-brain
thunderhill
Demonstrates local Laya and Claude collaboration for inbox triage, escalation, and coding guardrails
offline-ai-mobile
frederico-kluser
Provides an offline prompt-testing app with local Laya decisions and MiniCPM text generation
jev-clean
chengyixu
A macOS cleanup tool that uses Laya-MLX to investigate System Data and propose files for review
CodeAgentLab
YeChenglin8888
A lightweight Python coding-agent system that integrates Jev and Laya for browser and application tasks
s1cap
Jaffe2718
Uses System-1 decision models to manage agent context recall and rank candidate plans
laya-langchain-examples
nkon123
Provides offline LangChain and LangGraph examples for using Laya to classify, route, and guard text
agent-sample
shiborgi
Classifies message subjects using interchangeable Typer, A2A, LangGraph, DeepAgents, and Laya implementations
LayaGamer
psurge1
Provides harnesses and a web dashboard for playing games with Laya decision agents
laya-lab
InfiniteXyy
A playground demonstrates Laya-powered routing, browser tests, and semantic log filtering
laya-pro
mareknardella-lgtm
A hybrid AI platform combines local Laya decisions with generative models and workflow orchestration
laya-seo
emmanuelnurit
Provides SEO and GEO audits through a Jev-based CLI and MCP, with a local Laya scoring bridge
jev-laya-trader
PrateekReddy116
Compares Jev and Laya decision engines in a paper-trading sandbox
laya-agentic-triage
PrashantMali07
A LangGraph incident-triage system uses Laya for typed classification and routing
laya-claude-code
anshc022
A Claude Code plugin runs Laya locally for prompt checks, task hints, and typed decisions
eval_laya_mcp
Ayanshefeek
A Python package and MCP server use Laya to judge agent and RAG outputs
ai-agents-and-laya-system-meld
ManasviAtGitHub
Uses Laya for perception and speaker selection in a multi-agent MELD conversation system
playwright-cli-laya-bakeoff
NerdishShah
Evaluates local Laya in a Playwright CLI workflow for adding a product to a Shopify cart
hybrid-pg-laya-poc
JadELHAJJ-prog
Routes a refund-support agent with Laya and calls local Qwen when generation or tool use is needed
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/systemonedialect. 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