jandalhuysen/jev-clash-royale-test
User repository on GitHub
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Node Royale
A minimal real-time Clash Royale-style game engine in Node.js that pits a Jev System One bot against a traditional Ollama LLM bot, with an MCP server and a canvas web client. The Jev bot answers four tactical questions in one parallel call.
- Stars
- 1
- Language
- JavaScript
- Reading time
- 2 min
- Published by
- Community
- Author
- jandalhuysen
- Last verified
- Oct 2026
Used inJev for Gaming
- Languages
- JavaScript
- Capabilities
- Open sourceRequires API keyRuns locally
Highlights
- Two bots, two paradigms: jev_bot_loop.js uses Jev's typed decisions under 100 ms; bot_loop.js uses an autoregressive Ollama model at 2,000-5,000 ms.
- Speculative fan-out: code filters the hand by elixir, then one SystemOne Jev request answers should_play (Noul), card, lane and tactic (Choice) in parallel.
- The code policy engine banks elixir on low confidence or Hold, and only posts a 100% legal move; the README notes zero JSON parsing errors.
- Also ships an MCP server for external agent architectures and a canvas web client; you play as Player 0 (Blue) at localhost:3000.
- Quick start: npm install and npm run start, then npm run bot:jev with TYPESAFE_API_KEY, or npm run bot for the Ollama route.
Quickstart
bash
npm install
npm run start
export TYPESAFE_API_KEY="your_typesafe_api_key"
npm run bot:jevWatch out
Grounded on the truncated README and GitHub metadata reviewed 2026-10-15; the Ollama section is cut off mid-sentence, including the model name and MCP details, and the repo lists no license. The latency comparison is the project's own table, not a reproducible benchmark.
Questions about this entry
Short answers drawn from the linked project or page.
A minimal, real-time Clash Royale-style game engine built in Node.js that demonstrates a TypeSafe Jev System One bot against a traditional generative Ollama LLM bot, with an MCP server and a canvas web client.
In a single parallel SystemOne request it answers four typed questions: should_play as a Noul giving P(Play), card as a Choice over affordable cards plus Hold, lane as a Choice, and tactic as a Choice among bridge, mid and back.
The README's table puts Jev under 100 ms with typed primitives and zero JSON parsing errors, against roughly 2,000-5,000 ms for autoregressive generation that can hallucinate cards or illegal coordinates. These figures are the project's own.
Code filters the hand by current elixir before asking Jev, so the choices are structurally constrained. The code policy engine then banks elixir on Hold or low confidence and posts only a move the game accepts.
npm install, then npm run start and open http://localhost:3000. You control Player 0 (Blue); Player 1 waits idle until you launch a bot with npm run bot:jev for Jev or npm run bot for the local Ollama model.
The README lists a Model Context Protocol server providing standardized tool endpoints for external agent architectures, so other agents can drive the game. The digest truncates the section, so the exact tools are not verified here.
The metadata lists no license, the README is cut off inside the Ollama bot section where the model name is incomplete, and the latency comparison is the project's own table rather than an independent benchmark.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev picks which Apple HIG guides go into the agent's context. NatashaTheRobot built a small AskHIG CLI and…
X: Three decision models, one game of Snake
X: Diogo Almeida with a16z on Jev
X: Luna plans, Jev plays poker
More Jev resources like this
A small web app where TypeSafe's Jev plays Tetris by itself — the only control is Reset. Code enumerates every reachable placement and its board facts, and one typed Choice call picks the move with probabilities, latency and cost.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
pinebit/jev-tetrisJavaScript
pinebit/jev-tetrisJavaScriptA 25-second IT-buzzword typing game built to feel how fast and cheap Jev is: each word gets five typed judgments in one request, and the screen shows the running cost next to the real HTTP request and response.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
pochang6/jev-buzzword-rushJavaScript
pochang6/jev-buzzword-rushJavaScriptA playable Three.js driving simulator where Jev-powered autopilot picks steering and speed up to four times per second: compact tables of eligible paths, traffic and road boundaries go to Jev while geometry and control math stay local.
Jev Demos & Experiments#community#catalog-import#cobanov
Community
standardagents/jevpilotJavaScript
standardagents/jevpilotJavaScriptA public operator lab for TypeSafe Jev: a chess match as the flagship page, a row of smaller judgment booths, and one shared client that keeps the API key out of the browser via a local Python server or a Cloudflare Worker.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
4anti/jev-broadcast-labJavaScript
4anti/jev-broadcast-labJavaScriptFighters in this arena are paragraphs of plain English, and Jev pilots them in real time — typed move, action and reflex decisions with live probabilities. Join the ladder with a pull request and swap the brain: Jev, Laya, kev or any LLM.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
eliot5566/jev-arenaJavaScript
eliot5566/jev-arenaJavaScriptA workshop of small, inspectable Python experiments for TypeSafe System One models: ten critical bays, from fraud screening to emergency dispatch, each giving Jev a realistic state while deterministic policy keeps authority over the next action.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
jgalego/jevs-garagePython
jgalego/jevs-garagePythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.