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
LayaMail
Theani7
Prioritizes email locally by applying typed Laya decisions to messages
layarank
akashmitra
Filters and reranks search results locally using Laya neural routers
MedLaya
0xcemkurt
Adapts the Laya decision engine for clinical triage, routing, urgency scoring, and red-flag detection
laya-experiments
RafaelJaime
Spanish notebooks evaluate Laya decision behavior, diagnostics, message routing, and product recommendation
laya-jev-homeautomation
CoryHawkless
A home-automation command router and benchmark harness exercises Laya
laya-ollama-demo
pyardley
Routes support tickets with Laya and uses Ollama to draft replies when needed
herdr-laya-router
candidosales
Routes coding tasks to AI agents using a local Laya classifier
toolhint
pedrocr83
A local Laya classifier ranks skills, connectors, and tools for coding prompts
evidence-gate
AnotherMeatsack
A local workbench for evidence review, task routing, MCP tools, and reproducible Laya evaluations
dsh-decision-layer
xbzbing
A structured decision plugin for DeepSeek Harness with configurable Jev-compatible backends
Tiyakaloud
herveyyy
A Python server uses Laya and ModernBERT for support triage, classification, scoring, and routing
laya-server
criguex
A local Jev-compatible server runs Laya and can cascade uncertain decisions to Jev
laya-trial
ngdghfdc
Tests Laya as a choice and confidence router for exam-processing pipelines
laya-router
Kaytm93
Routes requests to OpenAI-compatible models using local decisions from Laya
laya-plugin
Andrei-cloud
Provides an offline Laya decision plugin for coding agents through MCP and native integrations
laya-orchestrator
emanuelediluzio
Combines Laya decisions with code-generation models to orchestrate autonomous software development
laya-gateway
amanjoshi2002
Uses Laya to classify prompt safety and route prompts to suitable models
laya-fast-router
pramitsaha123
Demonstrates using Laya to route customer-support requests by department, urgency, and cancellation risk
laya-opencode-router
Wauuuuuu
A macOS OpenCode plugin routes tasks using local Laya classification and optional MLX models
s1cap
Jaffe2718
Uses System-1 decision models to manage agent context recall and rank candidate plans
laya-langchain-examples
nkon123
Provides offline LangChain and LangGraph examples for using Laya to classify, route, and guard text
laya-demo
gen24AI
Demonstrates Laya decision workflows for routing, triage, guardrails, RAG filtering, and moderation
laya-demo
Slothwolf
Demonstrates typed decisions, multilingual routing, triage, guardrails, RAG filtering, and moderation with Laya
laya-router
suradisworkspace
Routes Claude Code turns between model tiers using a local Laya classifier
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