Submissions for NVIDIA’s Plug and Play: Project G-Assist Plug-In Hackathon are due Sunday, July 20, at 11:59pm PT. RTX AI Garage offers all the tools and resources to help.
The hackathon invites the community to expand the capabilities of Project G-Assist, an experimental AI assistant available through the NVIDIA App that helps users control and optimize NVIDIA GeForce RTX systems.
Entrants gain the chance to win a GeForce RTX 5090 laptop, or a limited NVIDIA GeForce RTX 5080 or RTX 5070 Founders Edition graphics card, plus NVIDIA Deep Learning Institute credits. Finalists may also be featured on NVIDIA’s social media channels.
Register for the hackathon and check out the curated technical resources below to bring these submissions to life.
(G-)Assist With AI
When in the heat of a gaming moment or the flow of a creative project, interrupting one’s focus to navigate complex PC settings menus is a common frustration. For example, manually tweaking GPU performance or optimizing system parameters often requires leaving the user’s current application, which breaks concentration.
Enter Project G-Assist, which allows users to control their RTX GPU and other system settings using natural language. It’s powered by a small language model that runs on device and can be accessed directly from the NVIDIA overlay within the NVIDIA App — no need to tab out or switch programs.
Users can also expand its capabilities via plug-ins and even connect it to agentic frameworks such as Langflow. G-Assist plug-ins can be built in several ways, including with Python for rapid development, with C++ for performance-critical apps and with custom system interactions for hardware and operating system automation.
Project G-Assist requires a GeForce RTX 50, 40 or 30 Series Desktop GPU with at least 12GB of VRAM, a Windows 11 or 10 operating system, 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 requirements and a recent GeForce Game Ready Driver or NVIDIA Studio Driver.
Cross the Finish Line
As the hackathon’s submission deadline approaches this weekend, RTX AI Garage is providing resources that can help:
Sydney Altobell, a senior software engineer at NVIDIA, offers tips and tricks for working with G-Assist plug-ins in this on-demand webinar. The presentation and Q&A are available on the NVIDIA Developer YouTube channel and embedded below.
Fellow community developers are collaborating and sharing notes in the NVIDIA Developer Discord server. Altobell and the G-Assist engineering team have already answered many questions about plug-in submissions — keep the questions coming.
Plus, explore NVIDIA’s GitHub repository, which provides everything needed to get started developing with G-Assist, including step-by-step instructions and documentation for building custom functionalities. Take inspiration from sample plug-ins, which include code for using G-Assist to integrate into Discord, IFTTT, Google Gemini and more.
Learn more about the ChatGPT Plug-In Builder to transform ideas into functional G-Assist plug-ins with minimal coding. The tool uses OpenAI’s custom GPT builder to generate plug-in code and streamline the development process.
NVIDIA’s technical blog walks through the architecture of a G-Assist plug-in, using a Twitch integration as an example. Discover how plug-ins work, how they communicate with G-Assist and how to build them from scratch.
Find submission details and requirements on the Hackathon entry page.
Each week, the RTX AI Garage blog series features community-driven AI innovations and content for those looking to learn more about NVIDIA NIM microservices and AI Blueprints, as well as building AI agents, creative workflows, productivity apps and more on AI PCs and workstations.
Plug in to NVIDIA AI PC on Facebook, Instagram, TikTok and X — and stay informed by subscribing to the RTX AI PC newsletter.
Follow NVIDIA Workstation on LinkedIn and X.
See notice regarding software product information.