What does this sample do?

It recommends which of five operating systems — Windows, macOS, Linux Desktop, Android and iOS/iPadOS — best fits a described user's needs, using the OpenThai-SystemOne decision model from Hugging Face.

How does the decision() helper work?

It builds one yes/no question per option as a Noul, sends the questions to SystemOneClient.system_one(), and returns (name, noul) pairs sorted by score. Templates and options are parameters, so it can rank anything.

Can I repurpose it beyond OS recommendations?

Yes. The README says the question and criteria are templates and decision() is not tied to OS recommendation: change the options and templates to rank other things, as the two bundled needs already do.

What language should the prompts be in?

According to the OpenThai-SystemOne model card, the model is Thai plus English, so the state, questions and options can be written in either language, per the README.

How do I install and run it?

The digest does not capture the commands: the README excerpt ends in the supported-languages section before any install block. The repository carries a local-llm topic, suggesting a local endpoint setup, but this is unverified.

Does it need an API key?

Not shown. The sample calls a SystemOneClient, presumably against a server, but no key, endpoint or hosting requirement is documented in the captured excerpt, so treat this as unanswered.

What are the limits of this entry?

The README is truncated, the repository has 0 stars and no declared licence, and no accuracy numbers were captured. Everything here comes from the README's how-it-works section and the GitHub metadata.

Jev directory

CommunityJev Demos & Experiments

OpenThai-SystemOne OS recommender sample

A small Python sample that uses OpenThai-SystemOne to recommend which of Windows, macOS, Linux Desktop, Android and iOS/iPadOS best fits a user's needs. A generic decision() helper builds one Noul question per option and sorts the match scores.

See highlights Open github.com

Stars: 0
Language: Python
Reading time: 2 min
Published by: Community
Author: hidao80
Last verified: Oct 2026

hidao80/system-one-model-py-sample

User repository on GitHub

View on GitHub

A sample that uses OpenThai-SystemOne to recommend which of Windows, macOS, Linux Desktop, Android, and iOS/iPadOS best fits a user's needs.

Forks: 0
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity github python local-llm

Works forJev for Ranking Jev for Classification

Used inJev for Software & DevTools

Languages: Python
Capabilities: Open sourceRuns locally

Highlights

Asks OpenThai-SystemOne which of Windows, macOS, Linux Desktop, Android and iOS/iPadOS best fits a user's needs.
A generic decision(state, options, question, yes, no) builds the same yes/no question per option as a Noul and passes it to SystemOneClient.system_one().
Returns (name, noul) match-score pairs sorted descending; options and templates are swappable to rank anything else.
Two example needs: a Developer avoiding licence fees and wanting customization, and a Beginner who browses and messages.
Per the model card, OpenThai-SystemOne handles Thai and English, so state, instructions, criteria and options can be written in either language.

Watch out

README reviewed 2026-10-17 from the round-eleven capture, which stops mid-sentence in the supported-languages section: the install command, endpoint configuration and any accuracy numbers are not in the digest, and the repository declares no licence.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Per-Tick Decisions in Games

Sep 28, 2026

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.

Jev Demos & Experiments#gaming#agents#control

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai