██╗███╗ ██╗███████╗██╗███╗ ██╗██╗████████╗██╗ ██╗ ██║████╗ ██║██╔════╝██║████╗ ██║██║╚══██╔══╝╚██╗ ██╔╝ ██║██╔██╗ ██║█████╗ ██║██╔██╗ ██║██║ ██║ ╚████╔╝ ██║██║╚██╗██║██╔══╝ ██║██║╚██╗██║██║ ██║ ╚██╔╝ ██║██║ ╚████║██║ ██║██║ ╚████║██║ ██║ ██║ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝ ╚═╝ █████╗ ██████╗ ██████╗ █████╗ ██████╗ ███████╗ ██╔══██╗██╔══██╗██╔════╝██╔══██╗██╔══██╗██╔════╝ ███████║██████╔╝██║ ███████║██║ ██║█████╗ ██╔══██║██╔══██╗██║ ██╔══██║██║ ██║██╔══╝ ██║ ██║██║ ██║╚██████╗██║ ██║██████╔╝███████╗ ╚═╝ ╚═╝╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═╝╚═════╝ ╚══════╝
Create playable retro-style games with LLMs in minutes! Enter your prompt and your game pops open, it's that simple.
Push your imagination to the limit, it's 100% free and local.
Infinity Arcade will detect the hardware you have available and load a recommended LLM.
| Configuration | GPU/APU | Memory | Disk Space | LLM |
|---|---|---|---|---|
| Minimum (CPU) | Ryzen AI 7000-series chip or newer | 32 GB RAM | 5 GB | Playable1-GGUF |
| Suggested (iGPU) | Ryzen AI 300-series chip or newer | 32 GB RAM | 5 GB | Playable1-GGUF |
| Suggested (dGPU) | Radeon 7800XT or newer | 16 GB VRAM | 20 GB | Qwen3-Coder-30B |
| Suggested (APU) | Strix Halo (Ryzen AI MAX 395) | 64 GB unified memory | 20 GB | Qwen3-Coder-30B |
Windows: click this:
Linux: click this
Infinity Arcade combines the convenience of a ChatGPT-like interface with the concept of a game emulator. Instead of emulating existing games, it uses LLMs (served by Lemonade) to generate completely new games based on your prompts, then lets you play them instantly.
- Lemonade integration: automatically connects to Lemonade Server and has access to any Lemonade LLM.
- AI Game Generation: Describe a game concept and watch as an LLM creates a playable Python game.
- Game Library: All generated games are saved and can be replayed anytime.
- Easy Management: View game source code, copy prompts for remixing, and delete games you don't want with a simple click.
Navigate to the Releases page, download the .exe, and get started!
From PyPI (recommended):
pip install infinity-arcade
infinity-arcadeFrom Source:
-
Clone this repository:
git clone https://github.com/lemonade-sdk/infinity-arcade cd infinity-arcade -
Install the package:
pip install -e . -
Run it:
infinity-arcade
Games are generated with the following constraints:
- Pure Python using the pygame library only.
- No external images, sounds, or asset files.
- Complete and playable with proper game mechanics.
- Proper event handling and game loops.
- Visual appeal using pygame's built-in drawing functions.
Note: LLMs are imperfect, and may fail to generate the game you asked for or fail to generate a functioning game at all.
Games are cached under the .infinity-arcade folder in your home directory.
~/.infinity-arcade/
└── games/
├── metadata.json # Game titles and descriptions
├── abc12345.py # Generated game files
└── xyz67890.py
- Ensure Lemonade Server is running on
http://localhost:8000. - Check that you have models installed in Lemonade Server by opening the model manager: http://localhost:8000/#model-management.
- Visit lemonade-server.ai for setup instructions.
- Check the generated code for any syntax errors.
- Try regenerating the game with a more specific prompt.
- Try a simpler game concept.
- Make sure your selected model supports code generation.
- Check the
infinity-arcadeand Lemonade Server logs for errors.
Here are some example prompts that work well:
- Classic Games: "pong", "tetris", "pacman maze game", "asteroids"
- Variations: "snake but food teleports", "breakout with power-ups", "flappy bird in space"
- Original Ideas: "catching falling stars", "color matching puzzle", "maze with moving walls"
Contributions are welcome! Feel free to:
- Share interesting game prompts and results by opening an issue!
- Report bugs or request features via GitHub issues.
- Submit pull requests for improvements.
This project is licensed under the MIT license. It was built with Python with ❤️ for the gaming and LLM communities. It is built on the shoulders of many great open source tools, including llama.cpp, Hugging Face Hub, and OpenAI API.
Most of the code for this project was generated by Claude Sonnet 4.
This project is maintained by @jeremyfowers.
