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
smart-request-router
Leito2
A Python request router uses Laya for routine decisions and escalates hard cases to a LangGraph agent
ThinkingChooseModel
fplity
A Windows assistant uses local Laya to rank fixed reply templates from WeChat conversation text
omarchy-laya-workspace
nblanchard-intact
Uses a local Laya decision server to choose and launch apps in Omarchy workspaces
omarchy-laya-attention
nblanchard-intact
Uses a local Laya server to triage agent and desktop notifications in Omarchy
pi-knowledge-triage-compactor
sebastianosrt
Compacts Pi agent knowledge and retrieves archived sessions using a local Laya classifier
TypeSafe-Agent
Abhii-04
LangGraph agent that uses laya.Router to route between chat, Gmail, web and local tools
laya-demo
foxnukem
Runs a Tower Bloxx browser agent that uses Laya to decide when to drop blocks
pi-laya-firewall
r1cc4rd0m4zz4
Adds local Laya-powered policy checks and taint tracking to the Pi Coding Agent
Let-Laya-Decide
desodre
Compares screenshot and UI-hierarchy context for Laya-driven Duolingo lesson automation
rogue
dea6cat
Compares answers from AI harnesses and ranks them using Laya
decision-lite
cckyros
Provides a Jev-compatible MCP decision server with pluggable local and hosted model backends
paint-laya-cua
hoony3000
Uses an optional Laya decision API to guide line drawing in Microsoft Paint
Layagame
BrajamohanDas-afk
Runs an autonomous Pac-Man game in which the local Laya model chooses strategic moves
laya-compaction
bussolabs
A Claude Code plugin that uses Laya decisions to compact context by dropping or truncating tool history
laya_auto
diff-name-diffc
A live-web agent benchmark and fine-tuning workflow for Laya browser decisions
laya-router
ozbayenes123-ops
Stdio MCP server exposing Laya multilingual predictions as a tool
unsloth-laya
smithysw7
A Python bridge calls the local Laya decision model through Unsloth Studio’s Decision API
PaymentOps_JEV
ayush-jain-09
Uses Laya for payment-operation routing and gating while an LLM generates user-facing responses
22-minds
Satya141
Runs a football simulation where each player uses Laya to choose actions during play
mcp-router
Amantux
Routes MCP tools using a pluggable decision engine with Laya as its default local model
laya-coding-decisions
emiliano-go
Trains Laya as a coding-agent judge to score requirement coverage and patch risk
laya-browser-demo
LazyHuman
Runs Laya to predict browser actions from page snapshots and exposes an MCP-compatible endpoint
laya
junaidariie
Classifies and routes support tickets with Laya before generating responses
laya-nethack
Leeleit
Adds Laya risk judgments to a NetHack bot and studies learning from human games
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