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
openai-decisions-vs-jev-vs-laya
mateusfonsek
Benchmarks OpenAI Decisions, Jev, and Laya on Portuguese-language decision tasks
decide-gateway
thinx-pro
Routes typed decision requests to Jev, Laya, or language-model backends with confidence escalation and red-team testing
decision-lite
cckyros
Provides a Jev-compatible MCP decision server with pluggable local and hosted model backends
@reasoning-router/classifiers
robertn702
Provides reasoning-effort classifiers for Jev, Clef, and Laya through HTTP
laya-spike
naraaruna6302
Provides a multilingual typed-decision model with Python, serving, MCP, and ONNX options
helpdesk-fatec
VitorFranca089
Classifies college IT help-desk tickets with Laya and routes them by department and priority
laya-router
ozbayenes123-ops
Stdio MCP server exposing Laya multilingual predictions as a tool
laya-router
bussolabs
A Claude Code and Codex plugin that routes each turn to a model tier using Laya decisions
unsloth-laya
smithysw7
A Python bridge calls the local Laya decision model through Unsloth Studio’s Decision API
laya-coding-harness
MysterTech
Local advisor that uses laya-mlx to suggest model, effort or planning for Claude Code and Codex
laya-workiq-routing
hieunhums
A fine-tuned Laya model routes Microsoft 365 workplace questions to Work IQ sources
jev-laya-kev-winnow-qwen-comparison
srvkataria
Compares Qwen, Jev, Laya, and Kev on support-ticket routing
PaymentOps_JEV
ayush-jain-09
Uses Laya for payment-operation routing and gating while an LLM generates user-facing responses
mcp-router
Amantux
Routes MCP tools using a pluggable decision engine with Laya as its default local model
laya
junaidariie
Classifies and routes support tickets with Laya before generating responses
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
LLMAutoRouter_Laya
nitesw
Routes Claude Code prompts to model tiers using a fine-tuned Laya decision model
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
aimtas-system-one-laya-slm
letrthang
Serves a multilingual, farm-focused Laya decision model through a Jev-compatible API
laya_explore
akshayaasd
Uses Laya to route queries among agents and tools in multi-agent and RAG workflows
laya-triage
dkv11
Triage plant-operator messages and sensor data to assign a team, priority, and reasons
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