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
laya-as-judge
rbrus
Uses Laya-MLX to evaluate models and agents with typed-decision judgments
laya-ultrafast
xuancuongdoo
A Python browser agent uses local Laya decisions to select actions from indexed page elements
MacJev-322M-4K-Laya-GGUF
chaoliangUNSW
Provides GGUF encoder files and a runtime for running MacJev with llama.cpp
MacJev-322M-4K-Laya-MLX
chaoliangUNSW
Runs the MacJev decision model natively on Apple silicon with an MLX runtime
dsh-laya
PerryLink
A Cordis plugin exposes Laya typed decisions as tools for DeepSeek Harness
layaForWorkflows
vishalmysore
Runs browser-based Laya decisions to automate branching workflows
laya-go
neko233-com
Provides a Go server and agent integrations for structured Laya decisions
omp-laya-judge
F0Rextasy
Adds a local Laya-powered decision judge and MCP server for oh-my-pi
headroom
llm-learner
A local-first Codex plugin estimates prompt load using Laya scoring
laya-codex
pilotspace
Ranks repository code for Claude Code using the Laya re-ranker, hooks, and an MCP server
laya-plays-google-snake
Makankn
Controls the real Google Snake game using Laya decisions and visual tracking
laya-mcp
NVentimiglia
An MCP server exposes Laya decision capabilities as tools for agent workflows
home-assistant-laya
allenporter
Runs Laya as a local conversation agent for Home Assistant Assist
laya-mlx-voice-browser
aryanbhujade
Uses a local Laya-MLX model to turn spoken commands into browser actions on Mac
mjbrain
jinlio
Fine-tunes Laya into a real-time recommendation system for Japanese riichi mahjong
jev-as-quant
jiayylu
Combines Laya and Jev with Claude in a quantitative research stack and evaluates trading experiments
fast-laya-compaction
ShinyDataTech
Uses local Laya decisions to compact agent context and provides filters, caching, and an MCP server
system-one-router
mmornati
A Go gateway routes prompts to language models using Jev or a locally running Laya decision model
fast-browser
hamza-sahin
Automates Brave browser workflows through MCP using Jev or optional local Laya inference
laya-browser-v32b
ichenney
Fine-tunes a Laya-based decision model for browser-agent navigation and page-state judgments
kevin
gauravsaini
Runs a browser automation agent that uses Laya-ONNX to rank candidate actions
laya-mcp
wsargent
Runs local Laya inference on Apple Silicon and exposes typed-decision tools through an MCP server
elixir-jev
fbettag
Provides Elixir typed judgments backed by hosted Jev or a persistent local Laya model
laya-mcp
rdutra
An MCP server exposes local Laya-CoreML decisions through persistent decision tools
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