Available through the NVIDIA app, Project G-Assist is the graphics card giant’s AI assistant for GeForce RTX PCs. It’s designed to help optimise and control systems through voice or text commands, and its highly customisable, allowing users to create their own plug-ins. Now NVIDIA is giving an extra incentive to do just that, holding a virtual Hackathon to get people inspired.
Anyone can enter, and one developer will win a GeForce RTX 5090 laptop, while two runners up will bag new 5000 series graphics cards (see our pick of the best graphics cards for video editing and our NVIDIA GeForce RTX 5090 FE review).
(Image credit: Nvidia)
NVIDIA describes Project G-Assist as a customisable AI assistant that lives in the user’s PC overlay, understands natural language, and can help optimise, automate and control any GeForce RTX system without needing to ever alt-tab.
Running until 16 July, the virtual Plug and Play: Project G-Assist Hackathon invites developers of all skillsets to build and share custom plug-ins, which can be be built with Python or C++, or created using the G-Assist Plug-In Builder, a ChatGPT-based tool that generates plug-in code from natural language for those who prefer vibe coding.
This week’s RTX AI Garage shows how developers can extend Project G-Assist, NVIDIA’s experimental tool with custom features.
To submit an entry, participants must provide a GitHub repository, including source code file (plugin.py), requirements.txt, manifest.json, config.json (if applicable), a plug-in executable file and READme code. Then, submit a video between 30 seconds and two minutes showcasing the plug-in in action. Hackathoners will also have to promote their plug-in using #AIonRTXHackathon on a social media channel: Instagram, TikTok or X. Projects must be submitted via an online form by Wednesday, 16 July.
Judges will assess plug-ins based on three main criteria: 1) innovation and creativity, 2) technical execution and integration, reviewing technical depth, G-Assist integration and scalability, and 3) usability and community impact, aka how easy it is to use the plug-in.
Daily design news, reviews, how-tos and more, as picked by the editors.
NVIDIA has resources available for anyone interested in submitting, including a webinar on building G-Assist Plug-Ins on 9 July, a technical blog on the architecture of an NVIDIA G-Assist Plug-In that explains the process of building a plug-in, a GitHub repository containing sample plug-ins, instructions and documentation and the NVIDIA developer Discord channel for support.
