Build a G-Assist Plug-In | Tutorial
- NVIDIA is hosting a virtual hackathon, inviting developers to create AI plug-ins for its geforce RTX systems using Project G-Assist.
- Project G-Assist, accessible through the NVIDIA App, is an experimental AI assistant designed to help users tune, control, and optimize their NVIDIA GeForce RTX systems.
- The hackathon encourages developers to expand G-Assist's capabilities through custom plug-ins, which can even connect to agentic frameworks like Longflow.
Eager to build your own AI assistant for NVIDIA GeForce RTX? This in-depth tutorial from News Directory 3 guides you through developing G-Assist plug-ins, a key capability for the latest NVIDIA GPUs. Discover how to leverage Python, C++, or the no-code builder to craft innovative features.We’ll cover the essential steps—from setting up your growth environment to submitting your project for a chance to win a top prize, including a GeForce RTX 5090 laptop. Learn how to integrate secondary_keyword, enhance your gaming experience, and optimize your system with natural language control. Don’t miss the July 16 deadline for submissions! Discover what’s next with AI on RTX.
NVIDIA G-Assist AI Hackathon: Build RTX Plug-ins and Win Big
Updated june 18, 2025
NVIDIA is hosting a virtual hackathon, inviting developers to create AI plug-ins for its geforce RTX systems using Project G-Assist. The Plug and Play: Project G-Assist Plug-In hackathon runs through July 16, offering participants a chance to win prizes and gain recognition on NVIDIA’s social media channels.
Project G-Assist, accessible through the NVIDIA App, is an experimental AI assistant designed to help users tune, control, and optimize their NVIDIA GeForce RTX systems. It employs a small language model that runs on the device, enabling users to manage their GPU and system settings using natural language commands directly from the NVIDIA Overlay.
The hackathon encourages developers to expand G-Assist’s capabilities through custom plug-ins, which can even connect to agentic frameworks like Longflow.
plug-In and Win
To participate, developers must register and explore the provided technical resources. Plug-ins can be developed using Python for rapid prototyping, C++ for performance-critical applications, or custom system interactions for hardware and operating system automation.
For those preferring a low-code approach, NVIDIA offers the G-Assist Plug-In Builder, a chatgpt-based application that allows enthusiasts to create plug-ins using natural language commands.
Submissions require a GitHub repository containing the source code (plugin.py), requirements.txt, manifest.json, config.json (if applicable), a plug-in executable file, and a README file. Participants must also submit a video, between 30 seconds and two minutes, showcasing the plug-in in action and promote their plug-in using #AIonRTXHackathon on social media.
Judges will evaluate plug-ins based on innovation, technical execution, and usability. Winners will be announced on Aug. 20. The first-place winner will receive a GeForce RTX 5090 laptop, second place a GeForce RTX 5080 GPU, and third place a GeForce RTX 5070 GPU. The top three winners will also be featured on NVIDIA’s social media channels, meet the NVIDIA G-Assist team, and receive an NVIDIA Deep Learning Institute self-paced course credit.
Project G-Assist requires a GeForce RTX 50, 40, or 30 Series Desktop GPU with at least 12GB of VRAM, Windows 11 or 10, a compatible CPU (Intel Pentium G Series, core i3, i5, i7 or higher; AMD FX, Ryzen 3, 5, 7, 9, Threadripper or higher), specific disk space, and a recent GeForce Game Ready Driver or NVIDIA Studio Driver.
Plug-In(spiration)
NVIDIA provides open-source plug-in samples on GitHub to demonstrate the potential of on-device AI. Popular plug-ins include:
- Google Gemini: Enables search-based queries using Google Search integration and large language model-based queries using Gemini capabilities in real time.
- Discord: Allows users to share game highlights or messages directly to Discord servers.
- IFTTT: Enables users to create automations across hundreds of compatible endpoints to trigger IoT routines.
- Spotify: Lets users control Spotify using simple voice commands or the G-Assist interface.
- Twitch: Checks if any Twitch streamer is currently live and can access detailed stream information.
Get G-Assist(ance)
Developers can join the NVIDIA Developer Discord channel for collaboration and support. NVIDIA is also hosting a webinar, “How to Build a G-Assist Plug-In,” on July 9, from 10-11 a.m.PT.
NVIDIA’s GitHub repository provides resources for developing with G-Assist, including sample plug-ins and documentation. The ChatGPT Plug-In Builder transforms ideas into functional G-Assist plug-ins with minimal coding.
What’s next
The hackathon provides a platform for developers to explore the capabilities of AI on RTX and contribute to the G-Assist ecosystem. The winning plug-ins could shape the future of how users interact with their NVIDIA GPUs and gaming experiences.