Skip to content

Laya playground

A local site, games, a benchmark, and an agent skill for Laya. The public pages replay recorded runs; the clone runs the model on your machine.

Stars
185
Language
JavaScript
License
MIT
Published by
Community
Author
wdobry
Last verified
Oct 2026

About this project

A website, three games, a benchmark and an agent skill for Laya, the open-source decision model: typed questions in, real probabilities out, one forward pass, no generated text. It runs on your own machine. The live site is at brainfunctioncollapse.com/laya. It has no model behind it and replays recorded runs. Clone this repository and the same pages run against the real model.

Quoted from the project's README. Read the full README.

Highlights

  • MIT. 180 stars on 3 October 2026. Live site is brainfunctioncollapse.com/laya.
  • The README says the live site has no model and replays recorded runs.
  • Cloning it installs NandhaKishorM's laya package and downloads the open weights.
  • Includes games, a benchmark, and an agent skill. It does not contain the model.

Watch out

A front end for someone else's weights. Recorded runs on the public site are not live inference.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

LinkedIn: What multimodal decision models actually change, and what they do not.

LinkedInJevDirectory.org

Hacker News: Software Bombe and live Enigma demo where Jev ranks cribs and judges plaintext.

ag_212 pointsShow HN: Jev as the Bletchley Park Analyst: A Software Bombe on EnigmaRead the thread on Hacker News

Related terms

Glossary definitions related to this entry.

More Jev resources like this

127GitHub stars
A completed Pokémon Red run: Jev picked menus, catches, and moves from RAM, and the harness handled pathfinding. The public page records the Hall of Fame stats.
Jev Demos & Experiments#community#games#javascript
A Mineflayer agent for Minecraft Java 1.16.5 where a planner sets the objective and Jev picks the next bounded action from game observations.
Jev Demos & Experiments#community#javascript#gaming
306GitHub stars
Local macOS computer-use automation on Apple silicon using on-device laya typed decisions and CUA-S1-FORMS for filling, via the Accessibility API.
Jev Demos & Experiments#community#browser#local
221GitHub stars
An agent skill that reproduces Jev-style single-step logits over indexed browser controls using local Qwen weights for offline browser use.
Jev Demos & Experiments#community#browser#open-models
58GitHub stars
An Apache-2.0 decision engine with a TypeSafe-compatible endpoint, document answers with source passages, and a ViZDoom demo that picks actions from structured game state.
Jev Models & Reimplementations#community#python#local
34GitHub stars
Kotlin NES emulator whose agent plays Super Mario Bros. and Final Fantasy through typed decisions. Each turn becomes one Choice over goals that can actually run, wired through SemIf against a local Qwen3.5-4B, so a button the game does not offer is never an option; 900 logged decisions never answered off-menu.
Jev Demos & Experiments#community#emulator#gaming

From the Jev guides

Original write-ups on what this entry is for.

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
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai