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
Unitree_Low-Level_Balance
DeRuiChen258
Combines Unitree G1 balance control, skill scheduling, and structured LayA decisions in MuJoCo
LayaResolve
jasgigli
Routes and triages problems with the Laya decision model family
floorcall
yashraz23
Provides a fine-tuned and calibrated Laya decision layer for voice-agent tasks
pi-laya-bridge
DrGekoz
Adds a local Laya-backed typed-decision tool to the Pi agent
laya-agent
clarois
Uses local Laya decisions to choose and execute actions in Ragnarok Offline
laya-android
Byun11
Fine-tunes Laya into a typed-decision policy for Android GUI action selection
DSH-Laya-Tool-Router
residenthiago2011
Uses Laya typed decisions to reveal relevant DSH tools on demand
life-decision-system
NankoMi
Provides an agent skill for life decisions with an integrated Laya scoring and fine-tuning pipeline
reverie
r3c0nc1l3r
Runs browser tests from Markdown specifications using local Laya or hosted Jev decisions
neo4j-laya-exploration
Satyaprakash27
Routes LangGraph agents using Laya decisions informed by Neo4j episodic memory
OpsOne
prannesshkva
Automates cloud operations and cost remediation using LangGraph, FastAPI, and Laya decisions
dsh-laya-mcp
Alexander390370
Connects the local Laya decision model to DeepSeek Harness through an MCP server
Cuse
muneebkhan08
A macOS cursor agent uses on-device UI grounding and a local Laya model to operate apps
replacing-ReAct-Hardcoded-Agent
tharunreddym-ai-dev
A Telegram assistant uses Laya decision gates to manage memory, web search, and retries
jetson-browser-assistant
zibochen6
Uses local Laya and Qwen models to operate a browser and edit a whiteboard on Jetson
@ursuciprian/reflex
ursuciprian
Gates coding-agent commands and scans content for prompt injection using local rules, Jev, or Laya
decisionlint-mcp
nolindnaidoo
Provides MCP tools to lint and repair questions sent to Jev or Luna decision models
decisionlint
nolindnaidoo
Lints Jev and Luna decision-model questions in CI, editors, and an MCP server
pi-laya-guardrails
izolight
A Pi extension sends prompts and tool calls to a local Laya guardrail server
opencode-jev-compaction
jlegends
Two OpenCode plugins prune stale tool calls and optionally refine decisions with local Laya
pi-laya-model-router
izolight
Routes Pi sessions to mapped models using task classifications from a local Laya server
reflex-hooks-oss
lia210350
A Node provider runs the Laya decision model locally through ONNX for reflex-hooks
laya-homelab-decisions
daviestechlabs
A synthetic dataset supports training and calibration for a Laya homelab routing experiment
laya-browser-suite-c
cklxx
Provides held-out real-site tasks for evaluating a browser agent
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