Routing with Laya
A router runs before every request, so its own latency and cost land on the critical path. Laya answers a routing question in one forward pass with no generated tokens, which makes it a natural fit for choosing an LLM tier, a support queue or a tool.
342 projects
jeff-laya-routing-study
tiw
Compares Jeff and Laya for sub-agent routing using a stacking model and confidence cascade
jev-lens
xi029
A local workbench uses Laya, Jev, or Ollama to inspect RAG evidence decisions and replay policies
reflex
priyansh19
A decision gateway combines Laya or Jev decisions with LLM escalation and human guardrails
ai-frontend-guide-kit
urben88
Provides a reusable UI catalog and guided workflow with optional local Laya ranking
laya-mcp
kaysermagnus
Exposes Laya typed decisions as MCP tools for agents, reranking, relevance gating and model routing
jev-router-mcp
humayunkabir
An MCP server routes questions to tools through a Jev-compatible decision engine, including Laya
n8n-nodes-ollaya
cogniwork-fr
An n8n node that routes workflow items using typed decisions from Ollaya or TypeSafe AI
calvino-laya
kevago
Banking customer-service decision engine with Laya multilingual as the System 1 classifier
laya
mes1234
Provides a Python implementation of the multilingual Laya typed-decision model
laya-seo
tomwugdgz
Audits websites for SEO using a local Laya model as a gate before escalating uncertain judgments to Jev
laya-banking77
hari-hashing
Evaluates Laya decision-model classification and routing on the Banking77 intent dataset
laya-agent-gateway
JohnGF
A local Laya gateway routes prompts and session modes for AI coding agents
SmartCart-Laya
sanjanabhat846
A Flask-backed dashboard uses Laya to evaluate e-commerce promotions, order urgency, and manual-review decisions
hybrid-decision-agent
musaugurlu
Tests a Laya-first agent architecture that routes requests to Gemini Flash and benchmarks its performance
kronos-laya-engine
sdfafe
Combines Kronos forecasts with Laya decisions to produce crypto trading signals
laya-decision-models
YunfanKang
Demonstrates and fine-tunes Laya for routing and tool selection in I-GUIDE AI
RightDesk-Laya
Supankan
Evaluates support-request routing workflows with a local Laya inference adapter and baseline comparisons
decision-model-benchmarks
asopitech-publishing
Benchmarks decision models including Laya and Jev on Japanese routing and support classification tasks
jev-laya-model-use-cases
shridhar-galande
Jupyter notebooks demonstrate Jev and Laya for classification, routing, security checks, and business workflows
smart-request-router
Leito2
A Python request router uses Laya for routine decisions and escalates hard cases to a LangGraph agent
TypeSafe-Agent
Abhii-04
LangGraph agent that uses laya.Router to route between chat, Gmail, web and local tools
laya-router
boss2236
Suggests intended terminal commands and apps using edit distance and the Laya decision model
laya-support-ticket-triage
jilanikashif375
Demonstrates Laya-based classification, routing, and scoring of customer-support messages
NLP-Support
decooding
Classifies and routes support tickets with Laya and escalates complex cases to Gemini
Built-in router preset
The core package ships a question set for small-versus-frontier model routing:
import laya
agent = laya.load("convaiinnovations/laya")
routing = agent.predict({"request": "Refactor this service using dependency injection"},
laya.router_questions())
For LangGraph there is a conditional-edge router with a confidence fallback:
from laya.integrations.langchain import LayaRouter
router = LayaRouter(
criteria={"billing": "invoices, charges", "tech": "bugs, outages"},
confidence_threshold=0.80,
fallback="human_agent",
)
workflow.add_conditional_edges("triage", router)
Note that laya.Router is a different thing: it picks which Laya checkpoint answers, based on script and language.
Measured: Laya vs a reasoning model
laya_router put Laya and GPT-5 nano behind one endpoint and tested 180 labelled requests. Both scored 0.600 route accuracy, at 184 ms p50 for Laya and 6,415 ms for GPT-5 nano. The README also found that rewording the tier descriptions moved accuracy by 21 points.
git clone https://github.com/glukicov/laya_router && cd laya_router
uv sync --all-extras
uv run laya-router serve --backend laya
Projects
- system-one-router: an OpenAI- and Anthropic-compatible Go gateway where Laya or Jev answers topic, complexity, risk and private-data questions, then picks the cheapest adequate model.
- pi-pignon: a pi coding-agent extension that picks a model tier per prompt from a local
laya-serve(about 75 ms on Apple Silicon, per its README) or Jev. - laya-mcp (NVentimiglia): a
route_taskMCP tool for light vs frontier routing.
Caveats
In laya_router, Laya got 97% of small requests right but only 7 of 56 medium ones, so check each tier separately, not just overall accuracy. Write tier descriptions with concrete examples, and send low-confidence answers to a fallback.
Hosted option
layahost runs Laya behind the Jev-compatible /v1/systemone, plus /v1/decide templates for routing, support_intent and priority. Its decision flows chain questions in a visual editor (spam check, then intent, then team) and run the whole flow in one request, asking and billing only the questions on the path taken. Low-confidence answers can take their own branch to a person. layahost is run by the makers of laya.tools.
More ways to use Laya