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

Unsloth

Unsloth desktop app docs page: serves LAYA and Clef decision models locally through a TypeSafe-compatible /v1/systemone API.

Article
Open source ↗

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

This Unsloth documentation page covers running the LAYA decision model in the Unsloth desktop app. According to the list summary, the app serves LAYA and Clef locally through a TypeSafe-compatible /v1/systemone API on macOS, Windows and Linux.

This means applications written against TypeSafe's API, or its official SDKs pointed at a local base URL, can use open decision models on their own machine without a TypeSafe key. Details such as hardware requirements are not available in the summary.

What the decision model decides

TypeQuestionAnswers
OtherChoice, Score and Noul questions served by local LAYA or Clef models(inferred)—

How it works

  1. Install the Unsloth desktop app.
  2. Load LAYA or Clef.
  3. Point a System One client at the local /v1/systemone endpoint.

Strengths

  • Local, offline decision models with a TypeSafe-compatible API.
  • Cross-platform desktop app.

Caveats

  • Known only from a list summary.
  • Open models may differ in accuracy and calibration from Jev.

Getting started

See https://unsloth.ai/docs/models/decision-laya

At a glance

Type
Article
Runtime
Unsloth desktop app (local server)

Use cases and integrations

How curated lists describe it

Frequently asked questions

What does Unsloth serve?

LAYA and Clef decision models, per the list.

Is the API compatible with TypeSafe?

Yes, it exposes /v1/systemone.

Which operating systems?

macOS, Windows and Linux.

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
  • intern-decision-mlx

    Runs Intern-Decision-0.8B on Apple Silicon behind a local /v1/systemone endpoint that accepts screenshots for agent decisions.

    ServicebetaPython