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
agent-decision-firewall
chinna250801
Gates AI agent actions with a local Laya decision model and fail-closed rules
reckon
Quietcatalpa
Organizes and reviews Windows files offline using rules and the local Laya decision model
RayCodes_LayaAI
47thtechcorner
A browser-based Pong game uses Laya to control an AI opponent's paddle
laya-studio-node
ajayjha1
Provides a Node.js and TypeScript toolkit for Laya classification, routing, CLI, and MCP use
katai
Shiawaseu
A browser automation agent uses fine-tuned Laya models to select actions and target elements
laya-browser
Benny93
Uses a local Laya model to resolve plain-English selectors in browser automation
adecider
Agents365-ai
Provides typed decision tools for coding agents with pluggable local Laya, Jev, and OpenAI-compatible backends
laya-voice-browser
AkshayKulkarni1904
Controls Chromium-based browsers by voice using local Laya decisions on Windows
omarchy-agent
pranav6266
Runs an offline Linux voice assistant that uses Laya to route user requests
ghosthand
ameerhmz
A local macOS voice and computer-use agent uses Laya for typed decisions
jev-search
AnthonyDavidAdams
A Python library and CLI run decision-driven search with Jev or a local Laya backend
pi-laya-skill-router
ericmjl
Routes pi coding-agent requests to relevant skills using a local Laya model
system1-jev-laya-agent
harshavarma02
Runs a speedcubing agent that uses Laya and Jev to assess cube states and choose moves
layaMOE
vishalmysore
Routes Laya requests to domain-specific expert heads, with a browser demo using ONNX Runtime Web
omnia-mcp
Omniaeye
Exposes Jev and local Laya typed decisions to agents through the Model Context Protocol
laya-agent
inboxxobni
Runs Laya typed decisions locally on Apple Silicon and provides an HTTP server and agent integrations
laya-compactor
Gjusev
Compacts RAG context by scoring and removing less relevant retrieved documents with Laya
laya-skill
StevenLi-phoenix
A Claude Code skill runs, fine-tunes, evaluates, and exports Laya typed-decision models
POK-Agent
Acekorneya
Provides a Windows computer-use agent with JEV or local Laya as its fast action model
Claude-laya
HardikCoder45
A Claude Code plugin uses Laya to select models, skills, agents, and plugins for each prompt
hermes-laya
agusbyna
A Hermes Agent plugin uses Laya for local triage, classification, routing, and risk flags
google-adk-laya-router
derrickqin
A Google ADK example routes requests among Gemini tiers using Laya and evaluates routing results
laya-graph-harness
FMsongX2
Integrates a trained Laya model with Cognee and Neo4j for evidence-backed graph selection
edge-decision-laya-system1-demo
skdwriting
Demonstrates low-latency edge decisions using the Laya System 1 model and safety guardrails
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