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-robot
NIRUN-Weerawit
Uses Laya typed decisions to control a simulated robot arm through a LIBERO harness
playwright-laya-healer
sahil9256
Uses a local Laya/Jev decision model to repair and verify broken Playwright locators
laya-computer-use
adityachauhan0
Provides a macOS MCP server that uses Laya MLX to choose computer-use actions
JobHunt
priyansha016
A LinkedIn job-search toolkit uses Laya for profile matching and connection management
DecisionService
nightwalker404
Selects agent profiles and capabilities from prompts using Laya and CRL data
Laya
muhammadbilalcp
Provides a multilingual, non-autoregressive decision engine with Python, server, and integration packages
Laya-
muhammadbilalcp
Provides a multilingual, non-autoregressive decision engine with Python, server, and integration packages
LayaSDLC
Ajinkya-Furange-Patil
Routes bounded engineering decisions through the Laya model in an OpenCode workflow
Customer-HelpDesk
Abhii-04
Builds a customer helpdesk using Laya and LangGraph
laya-usecase
ompdas
Demonstrates Laya for ticket triage, policy-aware automation, and evaluation grading
laya-web-agent
0Xw3ak
Adapts Laya for constrained web-action decisions with browser execution and evaluation
hermes-router-model-laya
hakuzero4
Routes Hermes conversations among configured models using a Jev-compatible Laya decision service
local-ai-agent
DanielGodriNeto
Uses a local Laya classifier to choose presets in a voice-controlled desktop agent
laya
jetmiyoung
Provides a multilingual typed-decision engine with Python and integrations for serving and agent frameworks
laya_explore
akshayaasd
Uses Laya to route queries among agents and tools in multi-agent and RAG workflows
ai-os-decision-layer
amariwan
Runs deterministic-first local decisions with optional Laya and other advisory model backends
dsh-system1
GitHub Actions
Provides typed System One decisions for DeepSeek Harness plugins with Jev, Laya and Clef providers
dk-tech-lead-scanner
pthaodotcom
Scans Facebook group posts and uses Laya for classification, Qwen for comments, and Chrome automation for posting
laya-deploy
stevenke1981
Deploys Laya locally with an HTTP decisions API and MCP computer-use support
laya_tutorial
amire2000
Teaches Laya-based robot decision-making through small Python labs
laya-self-train-prime
archaeus-ai
Fine-tunes, calibrates, evaluates, and serves Laya decision models through a CLI and Claude Code skill
architecture-review-plugin
Ujjansh05
Provides an MCP tool for evidence-backed messaging architecture reviews using the base Laya model
laya-heart
r5x8ksva-del
A local desktop copilot uses Laya to interpret couple chats and Gemma to draft reply suggestions
LayaEval
VinayChaudhari1996
Evaluates agent and RAG workflows with neural metrics powered by the Laya MCP Server
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