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
Reflex
dimpu47
Routes infrastructure alerts using Jev or local Laya decision model APIs
MacJev-322M-4K-Laya-MLX
lawrence3699
Runs the MacJev typed-decision model natively on Apple silicon with MLX and compares it with Laya
Intelligent-Email-Routing-at-Local-Speed-Using-Laya
hasif154
Uses Laya to route emails with typed decisions and a checkpoint-selecting router
nocturn-gateway
yigiterturk-dev
Provides TypeScript and Python clients for a gateway to Jev and Laya
jev-deliberation-judge
SammySN-car
Plans a multi-agent deliberation judge using Laya jurors and vote, weight, or veto aggregation
jev-bench
brandonrc
Benchmarks Jev, Laya, Claude Haiku, and CLM on package-registry triage tasks
poi-governance
g31322543-crypto
Uses Laya for content moderation and DeepSeek or rules for POI deduplication
ai-second-brain-lab
dante01yoon
Combines an Obsidian knowledge workflow, coding-assistant hooks, local Laya classification, and a 3D Markdown viewer
Mark-LIII
shettysaaproductions
Provides a cross-platform desktop voice assistant with a local Laya decision model and multi-agent system
easy-open-jevs-instance
CarlosChiva
Deploys local Open-Jev and Laya inference services with Docker Compose and a test client
KVev
AdudodlaVarish
Serves cached long-document chat and uses Laya for offline routing experiments
decision-model-arena
sathik11
Compares Jev, Laya, and Microsoft Foundry for typed decisions in enterprise incident triage
stf-sim
JonRoosevelt
Simulates Brazilian Supreme Court cases using local Laya decisions, retrieval and bias probes
tool-output-pruning-lab
Dymyt-ry
Benchmarks Laya and other selectors for pruning tool output in coding-agent sessions
identity-jev
clawdreyhepburn
Fine-tunes Laya to rank identity and authentication standards from plain-language queries
narde
anliang0306
Reimplements the Laya decision engine and verifies behavioral parity against upstream
zhiyan
liuqing0224
Provides macOS chat assistance with local Laya analysis and generated reply suggestions
Wayfinder
manish-9245
Serves Laya decisions through an HTTP gateway with policies, a web console and an MCP server
model-router
gbaeke
Routes prompts to inexpensive or powerful language models using Laya complexity decisions
jev-agent-risk-gate
jayeshvpatil
Compares Jev, Claude, fine-tuned Qwen, and open Laya in experiments on agent shell-command risk gates
fly-brain-agent
shenjie002
Drives a browser-based fruit-fly simulation with Laya decisions and spiking-neuron dynamics
Verdict
TobyNoSkillSon
Keeps local System One models, including Laya, ready for coding-agent classification and scoring
sparky-reflex
Applied-AI-Solutions-hub
Routes desktop app messages locally with the Laya decision model through a Windows service
d3code-calibration
gkastanis
Compares Jev and open-weights Laya probability calibration against human ratings
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