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
Laya-Hebrew-V2.1
RoeiG
Fine-tunes a Laya-style model for calibrated Hebrew and English typed decisions
laya-tr-karar
hayriyigit
Fine-tunes Laya for Turkish typed decisions, including choice, yes/no, and score questions
laya-prompt-guard
16sulphur
A Laya fine-tune detects prompt injection and jailbreak attempts in text
laya-burger
xamjiang
Fine-tunes Laya for calibrated typed decisions in Taiwanese Traditional Chinese and English
laya-browser-v32b
ichenney
Fine-tunes a Laya-based decision model for browser-agent navigation and page-state judgments
laya-vision
savita10
Adds image input to Laya for calibrated 16-class scanned document classification
chunklaya
myxamediyar
Chunks long documents and uses Laya for typed-decision lookup across inputs up to one million tokens
laya-onnx
gqgs
Exports the Laya model to quantized ONNX for browser inference
pastewhat-ranker-v1
mizorewww
Distills a candidate-aware clipboard ranker into Laya multilingual for local inference
zero-shot-ie-bench
umstek
Compares Laya and other zero-shot systems across information-extraction and classification tasks
docker-laya
chneau
Serves Laya typed-decision predictions through an authenticated, multi-checkpoint FastAPI service
laya-mcp
wsargent
Runs local Laya inference on Apple Silicon and exposes typed-decision tools through an MCP server
structured-decision-bench
zhengbangbo
Benchmarks structured decisions from Qwen3, Jev, and Laya CoreML
laya-router-skill
wangmiaozero
Adds local Laya decision routing to coding agents through skills and MCP
jev-chat-windows-laya
ZJemYoung
Adds an optional local Laya backend to a Windows WeChat chat assistant
doomLaya
azalio
Trains and compares Laya and Jev agents playing FreeDoom with reproducible results
Laya-Showcase
zamax14
Demonstrates and benchmarks multilingual Laya alongside Jev and GPT models
laya-windows
Zuhair-01
Ports Laya typed-decision inference to Windows using ONNX Runtime and DirectML
laya-cli
MIt9
A CLI runs Laya typed decisions with batch, routing, and resident-daemon modes
Decis
chaitin
Serves open decision models through a self-hosted TypeSafe System One API
laya-cn
yangshun2005
Provides a Chinese translation of Laya documentation for its multilingual typed-decision engine
oh-my-laya
leo1394
Installs local Laya tools for classification, scoring, and routing in coding agents
laya-ternary-lite
xixi3548942758-design
Quantizes Laya to ternary weights for smaller, lower-memory inference
decidealot
psyb0t
Serves local Laya and Von decision models through TypeSafe-compatible HTTP and MCP APIs
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