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
openpave-jev
cnrai
Provides typed-decision commands for PAVE and Claude with local Laya and hosted Jev providers
design-os-generative-ui
jangtrinh
Builds a generative UI engine using local Laya-MLX decisions and a TypeSafe JEV cascade router
Routapse
pooyaphoenix
Routes prompts to models or specialist agents using Laya or Jev classification
Cascade_Router
EllroyOfficial
Routes requests through a three-stage cascade using Laya decisions, RAG checks, and output safeguards
systemone-lab
baldellimtt
Demonstrates typed System One decisions with local Laya, a playground, routing examples, and evaluation tests
laya-modernbert-decision-90pct
ameerhmz5
Fine-tunes Laya into a ModernBERT decision model and offers deployment formats
laya-v796
Falconsai
A ModernBERT-based Laya checkpoint for multilingual typed decisions and calibrated classification
relay-laya
eltonssouza
Provides a trained Laya classifier that routes coding requests by task, risk, and capability
laya-tr
TurkishCodeMan
Fine-tunes Laya for fast Turkish decision-making, candidate selection, and routing
laya-multilingual-calculator-router
Borcherding
A multilingual Laya model routes agent steps by predicting whether they need calculation
laya-for-clara
TheWiderLensInitiative
A Laya fine-tune routes assistant messages and selects the level of agent effort
laya-triage-en
elnachto
A Laya fine-tune that classifies GitHub issues for automated triage
laya-triage-multilingual
elnachto
A multilingual Laya fine-tune for classifying GitHub issues
laya-voice-router
IAMCB
Gated Laya fine-tune for voice-agent tool routing, tagged multilingual and Hinglish
sunday-laya-router
rithulkamesh
Fine-tunes Laya for Sunday agent intent routing and distributes the model as an ONNX export
laya-soc-bounded-triage
infosecn1nja
Publishes configuration and aggregate evaluations for a bounded Laya-based SOC triage layer
hermes-skill-router
cdepuy
Routes tasks to relevant Hermes skills using a local Laya model or SemIf
pi-laya-router
AdelysAlberto
Routes Pi coding-agent prompts using local Laya classification on Apple Silicon
decide
gopaljigaur
Provides a Python client that chains Laya with hosted and other decision-model backends
laya-omni-agent
yashrastogi069-dev
An autonomous agent combines local Laya or Jev routing with cloud reasoning and browser, OS, and data tools
Tern
AmRitJain0442
A model router uses local Laya-MLX inference to select between configurable provider tiers
moex-wall-trader
antonBy77
Researches MOEX order-book signals with a Laya- or Jev-compatible AI trading gate
god-llm-decisions
surajvs2710-stack
A decision engine fuses Laya and Jev predictions with confidence weighting and auditable logs
laya-studio-node
ajayjha1
Provides a Node.js and TypeScript toolkit for Laya classification, routing, CLI, and MCP use
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