# SheepSeb/tinyworldformer

> A research project running two tiny neural networks on a Raspberry Pi Pico 2 W: a looped-transformer world model that predicts the next frame and reward, and an actor network that plays the generated game.

- Magnitude: 4.3 out of 10 — Early signal
- Stars: 73 total · +57 stars measured 2026-10-29, 21:23–23:36 UTC
- Star trust: star growth looks organic
- Category: AI agents · Language: Rust · Created: 2026-10-22 · Last push: 2026-10-27
- GitHub: https://github.com/SheepSeb/tinyworldformer · Homepage: https://sheepseb.github.io/stealth/posts/tinyworldformer.html · Page: https://gitnova.dev/en/r/SheepSeb/tinyworldformer

## Useful for

- Run the world model and actor on a Pico 2 W to play Breakout, Pong, Flappy Bird, Doom-lite or Pac-Man lite.
- Train a stream-x RL agent from scratch on the board to learn inside the dreamed game.
- Compare exact-frame accuracy of the world model across 1-4 transformer loops for each game.

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 21:23–23:36: 16 → 73 stars (+57). This is the change over that interval.
- The repository is 7 days old and already has 73 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “A tiny world model running games on a Raspberry Pi Pico 2 W” — 75 points, 3 h ago.
- Recent forks include notable developers: @justinmk (1,985 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 8 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 22

## Stars per day, last 9 days (oldest → newest, today is partial)

2026-10-22 … 2026-10-30: 0, 0, 0, 0, 1, 1, 0, 72, None

## Hacker News

- A tiny world model running games on a Raspberry Pi Pico 2 W — 75 points, 7 comments: https://news.ycombinator.com/item?id=50295450

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **HKUDS/DeepTutor** — 8.8 · Breakout · AI agents · Python · +2,047 stars measured 2026-10-29, 00:02–23:34 UTC
   A lifelong personalized AI tutor with long-term memory: builds learning paths, reads documents and books, and runs practice and assessments via a multi-agent system and RAG.
   Full card: https://gitnova.dev/en/r/HKUDS/DeepTutor.md
2. **unclebob/ub-mode** — 8.0 · Breakout · AI agents · +943 stars measured 2026-10-29, 00:02–23:34 UTC
   An agent skill that enforces disciplined software engineering practices when writing or changing code: TDD, root-cause fixes, behavior testing, and quality gates via mutation testing. Installed as SKILL.md into the agent's skills directory.
   Full card: https://gitnova.dev/en/r/unclebob/ub-mode.md
3. **pbakaus/impeccable** — 7.8 · Breakout · AI agents · Rust · +2,650 stars measured 2026-10-29, 00:02–23:34 UTC
   A set of commands and detector rules for AI coding agents that helps them produce better frontend design instead of generic templates. Installs as a skill into Claude Code, Cursor, Codex and other harnesses.
   Full card: https://gitnova.dev/en/r/pbakaus/impeccable.md
4. **elayadesign/ai-design-skills** — 7.7 · Breakout · AI agents · +1,013 stars measured 2026-10-29, 00:02–23:34 UTC
   A collection of markdown-based design skills for AI coding tools like Claude Code, Cursor, Codex and Windsurf, covering landing page design and turning static designs into animated showcases.
   Full card: https://gitnova.dev/en/r/elayadesign/ai-design-skills.md
5. **milind-soni/OpenMausBot** — 7.7 · Breakout · AI agents · TypeScript · +444 stars measured 2026-10-29, 10:43–23:34 UTC
   ,
   Full card: https://gitnova.dev/en/r/milind-soni/OpenMausBot.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 23:45 UTC, updated every 30 minutes.