Self-host a Laya API server
Most Laya servers implement the same `POST /v1/systemone` wire format as TypeSafe's hosted Jev API. An existing Jev client can often switch to a self-hosted Laya by changing its base URL. The answers then come from Laya, a different and smaller model.
167 projects
laya-server
nvkudva
Serves the Laya decision model locally through a Jev-compatible HTTP API
laya-api
sriramkasyap
Provides a self-hosted, Jev-compatible HTTP API for Laya typed decisions
laya-docker-api
ksalk
Packages the local Laya decision engine as a GPU-enabled Docker HTTP API
laya-local-service
uibuckets
Provides a local HTTP inference service and Python client for Laya
docker-laya-api
TheNerdMan
Packages the Laya decision model as a containerized HTTP API with an optional browser demo
sample-laya-mlx-http
daisuzz
Serves Laya MLX decisions through a local System One API with a Kotlin client
verdict
NakliTechie
Serves typed decisions on macOS through Apple Foundation Models or an optional Laya backend
laya
Yahia-Raouf
Provides a self-hosted Laya inference API, key management, and an administration portal
laya-server
falk-werner
Serves Laya predictions through a local web server with prepared-question support
LayaWatch
BLANCO-11
Runs Laya in-process and provides a self-hosted console for traces, metrics, access control, and model management
layad
rcwsr
Keeps the Laya decision model resident and serves it over HTTP with MLX or PyTorch
rest-laya
wdonega
Serves the Laya model over REST with optional Jev-compatible endpoints for non-Python clients
laya-mcp
WayneCommand
Wraps the Laya decision model in an MCP server and REST API for agent integrations
laya-agent
ahmadfreijeh
A support-action agent combines a Python Laya prediction service with a Node.js customer-facing server
laya-railway
nomideusz
Deploys Laya on Railway behind a Jev-compatible HTTP API
laya-fastapi
remominor
Serves Laya typed decisions through a local FastAPI and ONNX Runtime deployment
laya.cpp
kyr0
Implements native C++ inference and a JEV-compatible server for Laya typed decisions
laya-serve
ouijan
Serves Laya decisions over HTTP with a typed TypeScript client
laya-api
yrodrigez
A FastAPI service loads the Laya model and serves typed-decision predictions
laya-server
r2d-ai
Serves Laya's multilingual checkpoint through CUDA-backed REST and MCP interfaces
laya-service
xiaobai1017
Exposes Laya through a FastAPI service with a Jev-compatible System One API
oido-laya
Djancyp
Wraps the Laya decision model in a Dockerized HTTP API for typed predictions
agentify-laya
hongyaok
Serves local Laya classifications through an OpenAI-shaped HTTP API and usage dashboard
laya-jv
TimTan1234
Packages a self-hosted Laya decision model as a Docker HTTP service for Luna
Official: laya-serve
From the core README:
pip install "laya[serve]"
LAYA_DEVICE=cuda LAYA_PRELOAD=1 laya-serve # binds 0.0.0.0:8000, preloads all 3 checkpoints
curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -d '{
"state": {"body": "billed twice, refund please or we cancel"},
"questions": {"dept": {"type": "choice", "instructions": "which team?",
"criteria": {"billing": "refunds", "tech": "bugs"}}}
}'
Set LAYA_API_KEY to require a bearer token. Other settings are LAYA_HOST, LAYA_PORT, LAYA_MODELS and LAYA_THREADS. A Nix flake and a NixOS module are included.
ollaya
ollaya works like Ollama for decision models:
curl -fsSL https://ollaya.dev/install.sh | sh
ollaya run laya --preset triage "I was charged twice for my subscription this month and want a refund."
It serves /v1/systemone, and the README says the official TypeSafe SDK works unchanged with TYPESAFE_BASE_URL=http://localhost:11435.
Docker
LAYA SERVER adds a web console and API-key management:
docker run -d --name laya-server --init --restart unless-stopped \
-p 8080:8080 \
-v laya-data:/data \
-e LAYA_ADMIN_USERNAME=admin \
-e LAYA_ADMIN_PASSWORD='change-this-admin-password' \
1panel/laya-server:latest
docker-laya publishes ghcr.io/chneau/laya for amd64 and arm64. Its README reports roughly 0.35 s per predict on CPU.
Native servers
laya.cpp (C++, CUDA, Vulkan and Core ML), sys1 (Rust on candle) and laya-apple (MLX plus Neural Engine) all serve /v1/systemone.
Differences from Jev
The core README lists three for client ports. Options share a token budget instead of Jev's 255-option cap. Every score level needs a description. confidence is computed differently, so a threshold tuned on Jev does not transfer; gate on answer_confidence instead. laya-rs uses /v1/system-one with a hyphen and is not a drop-in replacement.
More ways to use Laya