Nvidia is inviting developers to take part in the Plug and Play: Project G-Assist Plug-In Hackathon for the chance to win one of many prizes. Nvidia has been running a bunch of giveaways during its ‘GeForce Summer of RTX’, and this particular competition includes prizes such as an RTX 5090 laptop, RTX 5080 or RTX 5070 Founders Edition graphics cards, and NVIDIA Deep Learning Institute credits.

The GPU maker is currently giving away three more RTX 5090s, though that’s just pot luck. If you want to get more involved in this Hackathon, you have from now until Monday, July 21st @ 7:59 BST / 08:59 CEST to enter the competition. Finalists may also be featured on Nvidia’s official social media channels.

Create a plug-in for Project G-Assist

Project G-Assist is an AI assistant that is available on RTX 30, 40, and 50 series desktop GPUs with 12GB VRAM or higher. You can read more about the project here. It’s not too dissimilar from the one AMD debuted earlier this year. Nvidia notes that Project G-Assist allows user to control their RTX GPU and other system settings using natural language. A small language model, that runs on the device, powers the tech; it is easily accessible through the Nvidia overlay, which is available on the Nvidia app.

For those still working on their entries, RTX AI Garage has curated resources to help cross the finish line:

• A new on-demand webinar hosted by NVIDIA software engineer Sydney Altobell covering plug-in tips and best practices. The presentation and Q&A are available on the NVIDIA Developer YouTube channel.
• Community support via the NVIDIA Developer Discord with active Q&A from the G-Assist engineering team.
• A GitHub repository with sample plug-ins, step-by-step docs, and examples integrating with services like Discord, IFTTT, and Google Gemini.
• NVIDIA’s technical blog walks through the architecture of a G-Assist plug-in, using a Twitch integration as an example.
• Plus, the ChatGPT-based Plug-In Builder to accelerate prototyping with minimal coding.
• Find the full toolkit and submission details here.

Nvidia

To take part, you’ll have to build a custom G-Assist plug-in that adds new commands, connects external tools, and uses AI workflows tailored to specific needs. It should enable on-device AI-assisted functionality that responds to commands via text or voice. You can check out the Hackathon’s registration page to get started. Nvidia says you can build:

• Python plug-ins for rapid development
• C++ plug-ins for performance-critical applications
• Custom system interactions for hardware and OS automation

About the Author

Jack Goodall

At PC Guide, Jack is mostly responsible for reporting on hardware deals. He also specializes in monitors, TVs, and headsets and can be found putting his findings together in a review or best-of guide.