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
obsidian-classify
adra2n
Classifies Obsidian notes and assesses their long-term value with a local Laya model
browser-agent-laya-fast
samdem-ai
Uses Laya and NuExtract to power a browser agent for automated tasks
jev-kev-laya-selfhost
suarify
Provides a Dockerized, self-hosted HTTP API for Laya typed decisions with agent-skill documentation
synapse
Hduc
Tạo hệ thống ra quyết định và tự động hóa bằng Laya, kết hợp quy tắc, phê duyệt và phân giải giao diện động
laya-zeroshot-agent-guard-eval
Zephyr4772
An evaluation measures zero-shot Laya checkpoints as guards between agent steps
quarkus-langchain4j-jev-laya
kdubois
Integrates Jev and self-hosted Laya decision backends into a Quarkus LangChain4j agent
MacJev-322M-4K-Laya
lawrence3699
Provides a fine-tuned Laya-derived decision model for local Mac agents
Reflex
dimpu47
Routes infrastructure alerts using Jev or local Laya decision model APIs
jev-deliberation-judge
SammySN-car
Plans a multi-agent deliberation judge using Laya jurors and vote, weight, or veto aggregation
Mark-LIII
shettysaaproductions
Provides a cross-platform desktop voice assistant with a local Laya decision model and multi-agent system
ohmylaya
QuBiit0
Installs laya.cpp and exposes local Laya decisions to coding agents through MCP and an agent skill
jgent
Sube-py
Routes on-demand tool access in Pi using Jev or a local Laya model
Wayfinder
manish-9245
Serves Laya decisions through an HTTP gateway with policies, a web console and an MCP server
model-router
gbaeke
Routes prompts to inexpensive or powerful language models using Laya complexity decisions
jev-agent-risk-gate
jayeshvpatil
Compares Jev, Claude, fine-tuned Qwen, and open Laya in experiments on agent shell-command risk gates
fly-brain-agent
shenjie002
Drives a browser-based fruit-fly simulation with Laya decisions and spiking-neuron dynamics
ClearanceAI
PSivaMallikarjun
Automates QA planning and test workflows with Laya confidence scoring and human approval checkpoints
Laya
samyakb32-sys
Routes requests to prompt-configured task sub-agents using the Laya model on CPU
layaAgent
vishalmysore
Runs a browser-based agent that uses Laya for routine decisions and WebLLM when needed
LayaService
wj1313677
Serves the Laya decision model through a local REST API using MLX on Apple Silicon
laya-murdle
reycardo
Parses Murdle puzzles with Laya and solves their clues using a constraint solver
try-laya
lin52025iq
Provides a Laya-first agent runtime with browser and Android control integrations
laya-scraper
qxZap
Uses Laya to find publication pages and extract publication details with a browser-capable crawler
laya-integration
SanjaySathish
Routes Claude Code tasks to Claude tiers using a locally served Laya decision 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/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