Laya for Python
The reference implementation of Laya is the `laya` package on PyPI, maintained by Convai Innovations under Apache 2.0. It ships three checkpoints, a Router that picks one per request by script and language, a CLI, an HTTP server and an optional MCP server.
1712 projects
hermes-skill-router
cdepuy
Routes tasks to relevant Hermes skills using a local Laya model or SemIf
ultra_laya
roadius2
A fork of Laya adds multilingual decision routing and checkpoint selection
omp-laya
KiidxAtlas
Adds local Laya decision policies and verification controls to Oh My Pi
laya-go
lengoman
Provides Go types, routing, batching, and transports for using local Laya checkpoints
laya-plays-doom
shantanugoel
Trains Laya with reinforcement learning to play Doom through ViZDoom
pastewhat
mizorewww
A native macOS clipboard companion recommends entries using a local Laya model or optional Jev backend
jev-codex-workbench
qualixar
Adds Jev decisions and optional local Laya-MLX routing to a Codex plugin and MCP server
jev-vs-open-decision-models
elcronos
Benchmarks Jev against Laya and PrismNLI on zero-shot text classification tasks
laya
givespace-asia
A Claude Code plugin uses Laya to guard shell commands and code patches
laya
xosi
Runs Laya typed-decision inference locally on Apple Silicon with MLX
fastlaya
emtay-com
Serves English and multilingual Laya decision models through a FastAPI service
laya-server
pambrose
Implements a Jev-compatible API server backed by local Laya checkpoints
laya-mcp
PerryLink
An MCP server for Laya typed decisions with preflight checks and persisted calibration
laya-mlx-ddz
smile-magic
A browser-based 斗地主 game lets two local AI seats play using Laya on Apple Silicon
laya-plays-mario
DavidDevGt
Fine-tunes Laya as a control policy for playing Super Mario Bros
laya-mac-serve
chrisns
Serves Laya from a macOS menu bar app through an OpenAI-compatible HTTP endpoint
chinese-workflow-decision-bench
Adkid-Zephyr
Benchmarks Jev and Laya on synthetic Feishu message classification scenarios
decide
gopaljigaur
Provides a Python client that chains Laya with hosted and other decision-model backends
system-one
asynq-io
Offers a provider-neutral SDK for typed decisions through hosted and local backends
laya
ganeshdipdumbare
Serves Laya typed-decision predictions over HTTP in a self-hosted Docker deployment
laya
DilwoarH
Wraps the Laya Router agent in a Flask API for typed-decision predictions
SmartMom
clydechen0228
Uses Laya for edge classification and training within a smart-factory operations platform
laya_dashboard
ghozifadilah
A REST API and web studio serve Laya decisions and manage workflows
laya-micro
osamabinIaggin
Prunes and quantizes Laya for low-memory single-board computer deployment
Install
Python 3.10 or newer, per the core README:
python -m pip install laya
Optional extras: laya[serve] (HTTP server), laya[mcp] (MCP server), laya[langchain], laya[onnx] (ONNX Runtime) and laya[fast] (TileLang GPU fast path).
First decision
from laya import Router
router = Router() # downloads a checkpoint on first use
state = "Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan."
questions = {
"department": {"type": "choice", "instructions": "Which department should handle this?",
"criteria": {"billing": "invoices, payments, refunds",
"technical": "bugs, outages, system errors",
"other": "everything else"}},
"urgency": {"type": "score", "instructions": "How urgent is this?",
"criteria": ["not urgent", "soon", "blocking"]},
"churn_risk": {"type": "noul", "instructions": "Does the user threaten to cancel or leave?"},
}
result = router.predict(state, questions)
print(result["answers"]["department"]["choice"]) # billing
print(result["routing"]["model"]) # english
The package also installs a laya command, for example laya "My payment failed twice" --preset triage.
Checkpoints
| checkpoint | encoder | params | context |
|---|---|---|---|
laya |
ModernBERT-large | 421M | 512 |
laya-multilingual |
mmBERT-base | 322M | 1024 (up to 8,192) |
laya-typed-decisions |
ModernBERT-large | 421M | 1024 |
The README reports 32.8 ms for one question with laya-multilingual on a Tesla T4, and 193 to 464 ms per request on CPU with checkpoints preloaded.
Other Python projects
laya-mlx and laya-coreml for Apple Silicon, laya-openvino for Intel CPUs, edgejev for INT8 ONNX on CPU, and laya-mcp for agent tools.
Caveats
The README is direct about limits: the base checkpoints score near chance on its typed-decisions benchmark (0.362 and 0.352), and the 0.766 figure comes from the fine-tuned checkpoint. Temperatures should be refit on your own data before you trust the probabilities. The English checkpoint collapses on non-Latin scripts, which is why the Router exists.
More ways to use Laya