NVIDIA G-Assist Plug-In Hackathon

Project G-Assist, an experimental AI assistant available through the NVIDIA App, helps optimize NVIDIA GeForce RTX systems. The NVIDIA Plug and Play: Project G-Assist Plug-In Hackathon, invites the community to explore AI and build custom G-Assist plug-ins for prizes and social media features. The virtual hackathon runs through Wednesday, July 16.

G-Assist lets users control RTX GPUs and system settings using natural language via an on-device small language model. It operates from the NVIDIA Overlay in the NVIDIA App without needing to switch programs. Plug-ins can expand its capabilities, connecting it to agentic frameworks such as Langflow. Find popular G-Assist plug-ins, hackathon details, and tips below. Register and explore technical resources to join the hackathon.

G-Assist plug-ins can be built using Python, C++, or custom system interactions. The G-Assist Plug-In Builder, a ChatGPT-based app, allows no-code or low-code development. To submit an entry, provide a GitHub repository with source code (plugin.py), requirements.txt, manifest.json, config.json (if applicable), a plug-in executable, and a README file. Include a 30-second to 2-minute video showcasing the plug-in. Promote the plug-in using #AIonRTXHackathon on Instagram, TikTok, or X. Submit projects by Wednesday, July 16.

Judges will assess plug-ins based on innovation, technical execution/integration (technical depth, G-Assist integration, scalability), and usability/community impact. Winners will be selected on Wednesday, August 20. First place receives a GeForce RTX 5090 laptop, second place a GeForce RTX 5080 GPU, and third a GeForce RTX 5070 GPU. The top three will be featured on NVIDIA’s social media, meet the NVIDIA G-Assist team, and earn 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.

Explore open-source plug-in samples on GitHub. Join the NVIDIA Developer Discord channel to collaborate and gain support. A webinar on building G-Assist Plug-Ins is scheduled for Wednesday, July 9, from 10-11 a.m. PT. NVIDIA’s GitHub repository offers sample plug-ins and documentation. The ChatGPT Plug-In Builder helps transform ideas into functional G-Assist plug-ins with minimal coding. NVIDIA’s technical blog explains the architecture of a G-Assist plug-in, using a Twitch integration as an example. The RTX AI Garage blog series features community-driven AI innovations.

Plug in to NVIDIA AI PC on Facebook, Instagram, TikTok, and X, and subscribe to the RTX AI PC newsletter. Follow NVIDIA Workstation on LinkedIn and X. See notice regarding software product information.