Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

laya-server

Minimal FastAPI server exposing a /v1/systemone endpoint for Jev-style typed questions, with only run instructions documented.

Serviceprototype
View on GitHub ↗

Overview

This laya-server is a minimal FastAPI application that exposes a /v1/systemone endpoint accepting a state and typed questions, such as a noul 'Does this convey urgency?' and a choice of team among billing, technical and sales. The README only shows how to install dependencies with uv, run the server with uvicorn and test it with curl.

Which model answers the questions (presumably Laya, given the name) and how it is loaded are not documented in the README. It is best seen as a small personal example of serving a Jev-format endpoint locally.

What the decision model decides

TypeQuestionAnswers
Yes / noDoes this convey urgency?—
ChoiceWhich team should handle this?billing · technical · sales

How it works

  1. uv sync to install dependencies
  2. uv run uvicorn main:app
  3. POST a state and questions to /v1/systemone

Strengths

  • Very small, easy to read example

Caveats

  • Backend model not documented
  • No tests or configuration described
  • Personal example

Getting started

uv sync && uv run uvicorn main:app --reload

At a glance

Type
Service
Status
prototype
Language
Python
Runtime
FastAPI server
Has code
yes

Use cases and integrations

How curated lists describe it

Frequently asked questions

Which model does it use?

The README does not say; the name suggests Laya.

How do I call it?

POST a state and questions to http://127.0.0.1:8000/v1/systemone.

Is it production-ready?

No, it is a minimal example.

Related projects

  • decidealot

    Docker service exposing local Laya, Von, a CLM head or hosted Jev through one TypeSafe-compatible HTTP and MCP endpoint.

    MCP serverbetaPython
  • edgejev

    Converts open Jev reproductions (Laya, Kev, NanoJev, PlayJev) to INT8 ONNX for offline CPU decisions at about 15.6 ms per question.

    ServicebetaPython
  • go-system-one

    Native Go runtime serving Gemma 4 12B as a Jev-like decision model with hand-tuned PTX kernels and no CGo or CUDA toolkit.

    ProjectbetaGo
  • gojev

    Go harness for System One models: hosted Jev, open Kev in-process via llama.cpp, and Cloudflare Clef, with typed helpers and a CLI.

    ServicebetaGo
  • hearim

    Go gateway exposing the Jev /v1/systemone contract over ordinary LLM backends by reading single-token label logprobs.

    ServicebetaGo
  • instinct-ai

    Open-source dual-brain runtime that answers typed decisions with a fast local engine or the Jev API before falling back to LLMs.

    ServicebetaPython, TypeScript