HunterAlphaHub
OpenRouter model reference Facts from the public catalogue, dated and labelled
Jev Laya Verified
2026-09-22

GitHub · Games and demos

PromptEngineer48/laya-vs-jev-arena

A two-game head-to-head you can play a side of yourself.

The repository's GitHub card, read on 2026-09-24

What it does

Runs Laya and Jev head to head in two games where each move comes from the model, and lets a person take one of the two places from a container.

The repository's own description: “Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision.”

How it works

Both sides answer identical typed questions about the game state, so the model is the only difference between them, and the game itself renders the outcome instead of a scoring script.

The repository, by the numbers

Stars
29
Licence
MIT
Stack
Docker · Python games
Last push
2026-09-22

Read from the GitHub API on 2026-09-24. Stars and the last push move daily — quote them with the date, the way we do.

What we checked

  • the README, read 2026-09-24
  • the docker command and the two game modes
  • the note that nothing in either game is scripted

What we did not check. Who wins, or how often. The repository is the arena, not a report of its results, and we have not run the container.

Open the repository ↗All builds

Send us a link

A project built with Jev, a post, a video, a correction, a tip. We open the link, check it says what you said it says, and write the entry ourselves.

Required a link, and an email to reply to. Optional everything else.

Add context — all optional

One or two sentences about what it does, in your words. We write the entry ourselves.

Cost, latency, a benchmark — anything you measured. We attribute these to you.

We store what you type and email it to ourselves. No IP address, no user agent, no referrer — the same rule as the mailing list.

What happens to what you send →