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.
770 projects
laya-ultrafast
ShinyDataTech
Ports a browser-use agent to run Laya locally for browser action decisions
laya-windows
mateusgl8
Ports a terminal Snake game to Windows with real-time decisions from the Laya model
Laya-Experiments
alperunlu07
Collects reproducible experiments using Laya, including a Pong controller comparison
laya-trade
LivingG0D
Analyzes crypto markets and manages Toobit positions using a fine-tuned Laya decision model
laya-doom
dylanbstorey
Runs Laya in a real-time control loop to play Doom on Apple Silicon
laya-infra
ulevitsky
Deploys Laya and its playground with Docker Compose or Kubernetes
laya-finetuning
tehtommeh
Runs Laya locally with an API and UI, serving multiple checkpoints through the official SDK
laya-api
hugomes14
Serves a multilingual ticket classification model through an HTTP API
laya-http
shaul1991
Serves local Laya predictions through an authenticated self-hosted HTTP API
laya-dino
that-daniel
Controls Chrome's dinosaur game with Laya through a real-browser decision loop
laya-local
arshadakl
Turns Malayalam and English voice or text commands into safe local actions using Laya
laya-chrome
korbinjoe
Uses local Laya to perform constrained browser tasks in Chrome
laya_mcp
fuleinist
Exposes Laya decision inference as tools for MCP clients
laya-server
cmoro-deusto
Serves Laya System 1 decisions through a Jev-compatible REST API
poc-laya
MayukhCars24
Measures Laya classification latency with a FastAPI backend, web console, and observability tools
chess-laya
Kpaul-create
Combines Minimax, Laya, and Gemini to play chess through parallel consensus
laya-cli
CHENG-LIANG1
Wraps Laya typed decisions in a stable JSON command-line interface
laya_playground
Sathish-30
Provides a local Gradio app for downloading and testing the Laya typed-decision model
laya-service
idCntrue
Exposes the Laya non-autoregressive decision engine through a production HTTP service
migration-laya
ViniCarvalhoDados
Evaluates Laya for triaging legacy SQL queries before database migration
laya-mcp
kodexArg
Provides an MCP server for local Laya choice, score, and binary decisions
laya-turbo
razaowais6112
Proposes bounded browser actions using a Laya-compatible decision endpoint
myLaya
RyanPeng1111
Provides an offline Windows CPU workbench for multilingual Laya decision inference
wireshark-laya
stefanus-ai-tech
Evaluates Laya and rule-based judgments of network traffic features extracted from PCAP files
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