# I built a roguelike whose dungeon master is an LLM running 100% in the browser

> Source: <https://dev.to/aipredictions_dev/i-built-a-roguelike-whose-dungeon-master-is-an-llm-running-100-in-the-browser-4pke>
> Published: 2026-06-17 19:54:19+00:00

Most "AI games" phone home. Every turn is an API round-trip, every player burns your tokens, and the whole thing dies the day the bill scares you. I wanted the opposite: a text roguelike where the dungeon master is an LLM that runs **entirely in the player's browser** — no server, no API key, no per-token cost, and it keeps working offline after the first load.

Here's the architecture and the one bug that taught me the most.

[WebLLM](https://github.com/mlc-ai/web-llm) compiles quantized models to WebGPU, so inference runs on the *player's* GPU. There is no backend at all.

``` js
const cdn = "https://esm.run/@mlc-ai/web-llm";
const webllm = await import(/* webpackIgnore: true */ cdn);
const engine = await webllm.CreateMLCEngine(MODEL_ID, {
  initProgressCallback: p => setLoading(p.text),
});
```

First load pulls the weights once (the browser caches them). After that every turn is local and free.

A dungeon master should be creative, but it must not be allowed to break the rules. The split that made it stable:

My most instructive bug: early on I let the prose drive death detection (regex for "you die"), and the model cheerfully killed players on turn one with pure flavor text — "this could be the end of you" → game over. Moving death to an integer the engine owns (`if (hp <= 0)`

) fixed it instantly.

Rule of thumb: the LLM writes the story; your code keeps the score.

The tradeoff is model size: you run something small enough to load in a tab, so prompt design carries real weight. For a narrative game master that's a fair trade.

Genre is just a config object — palette, HUD labels, seed scenarios, system prompt. Same engine, swap the config, ship a different game. Adding a genre is *data*, not a code change, which means a generator can author new ones.

If you want to poke at a live one, the cyberpunk build (NeonHeist) and a few others are up under Games at [bestpaid.app](https://bestpaid.app) — all running on-device.

Happy to go deeper on the JSON-contract prompt or the WebGPU loading UX in the comments.