# NitroGen
NitroGen is an open foundation model for generalist gaming agents. This multi-game model takes pixel input and predicts gamepad actions.
NitroGen is trained through behavior cloning on the largest video-action gameplay dataset, assembled exclusively from internet videos. It can be adapted via post-training to unseen games.
# Installation
## Prerequisites
We **do not distribute game environments**, you must use your own copies of the games. This repository only supports running the agent on **Windows games**. You can serve the model from a Linux machine for inference, but the game ultimately has to run on Windows. We have tested on Windows 11 with Python ≥ 3.12.
## Setup
Install this repo:
```bash
git clone https://github.com/MineDojo/NitroGen.git
cd NitroGen
pip install -e .
```
Download NitroGen checkpoint from [HuggingFace](https://huggingface.co/nvidia/NitroGen):
```bash
hf download nvidia/NitroGen ng.pt
```
# Getting Started
First, start an inference server for the model:
```bash
python scripts/serve.py
```
Then, run the agent on the game of your choice:
```bash
python scripts/play.py --process '.exe'
```
The `--process` parameter must be the exact executable name of the game you want to play. You can find it by right-clicking on the game process in Windows Task Manager (Ctrl+Shift+Esc), and selecting `Properties`. The process name should be in the `General` tab and end with `.exe`.
**Disclaimer**: This project is strictly for research purposes and is not an official NVIDIA product.