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
Intelligent-Email-Routing-at-Local-Speed-Using-Laya
hasif154
Uses Laya to route emails with typed decisions and a checkpoint-selecting router
KVev
AdudodlaVarish
Serves cached long-document chat and uses Laya for offline routing experiments
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
sparky-reflex
Applied-AI-Solutions-hub
Routes desktop app messages locally with the Laya decision model through a Windows service
leanroute
kdandu001-arch
Provides a Laya-powered decision SDK and gateway for blocking attacks and routing LLM requests
laya
HydriaOne
Serves Laya routing predictions in Docker and includes an offline scenario inspector
Laya
samyakb32-sys
Routes requests to prompt-configured task sub-agents using the Laya model on CPU
Laya-Firehose
AdityaRawat00189
Ingests incoming data, classifies it with Laya, and routes items by urgency
laya-integration
SanjaySathish
Routes Claude Code tasks to Claude tiers using a locally served Laya decision model
laya-ecosystem
MiguelFAraujo
Provides utilities for supervision, context compaction, search, and UI decisions using Laya and Jev
laya---jev
rosdebbu
Farm and market co-pilot agent that routes vernacular farmer queries with a local Laya router
laya-studio
felix-homelab
Wraps Laya in a web panel for schema authoring, evaluation, automation, and calibration monitoring
Laya_wrapper
ugelucero
Wraps Laya checkpoints in a command-line tool and FastAPI service for request routing
laya-call-router
riefer02
Demonstrates fine-tuned Laya decisions in an inspectable dealership call-routing workflow
laya-code-router
SupremeDreamZ
Routes Claude Code and Codex turns using a local Laya model
pi-laya-router
codenamekt
Routes Pi coding-agent prompts to mapped models using a local Laya intent classifier
laya-v2-agent-routing
mdad-elec
Fine-tunes a Laya System-One router to select the price tier for each agent turn
intents
ezeike
Documents and sketches decision-model patterns for routing user input to application actions
synthetic-ehr-decision-evals
MadCodeTX
Benchmarks decision models on synthetic EHR administrative-routing tasks
handoff
kingd2925-beep
A local router learns from chat history to direct requests to cheaper or stronger models
nexus-decisor-laya
janiojandson
A JavaScript Nexus decision component built around the Laya System 1 model
laya-idjvsuen
muhfalihr
Fine-tuned Laya models for classification and decisions across Indonesian, Javanese, Sundanese, and English
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