Project G-Assist Plug-In Builder Empowers Users to Customize AI on GeForce RTX PCs

NVIDIA´s Project G-Assist now lets users add custom functionality to GeForce RTX Artificial Intelligence PCs with an easy-to-use plug-in builder.

NVIDIA has introduced Project G-Assist Plug-In Builder, enabling developers and enthusiasts to customize the capabilities of the G-Assist Artificial Intelligence assistant directly on GeForce RTX PCs. Available as an experimental feature through the NVIDIA app, Project G-Assist allows users to interact through voice and text commands for performance monitoring, hardware adjustments, and integration with other Artificial Intelligence-powered tools.

The new plug-in builder leverages ChatGPT-based technology, allowing users to create and customize G-Assist functionalities tailored to specific needs. Developers can write plug-ins using simple JSON for function definitions and Python for logic, making it possible to add new commands, connect to external tools, and build specialized workflows. With this approach, G-Assist can be enhanced to control music, engage with large language models, and interact with various applications and peripherals—all accessible directly from NVIDIA´s in-game overlay without disrupting the user´s workflow.

The platform offers free access to hundreds of developer-friendly APIs, facilitating the extension of G-Assist’s abilities across entertainment, productivity, smart home, and hardware management. Sample plug-ins available include integrations with Spotify for music control, Google Gemini for complex Artificial Intelligence queries, Twitch for live streamer status, as well as utilities for stock checks and weather updates. Users are encouraged to share their own plug-ins via NVIDIA´s GitHub repository, contributing to a growing ecosystem of Artificial Intelligence-driven PC enhancements. Step-by-step guides, sample code, and integration instructions are provided to streamline the plug-in development process, and advanced users can leverage C++ and Python bindings or frameworks like Langflow for broader multi-agent systems integration.

NVIDIA’s open approach with Project G-Assist Plug-In Builder is designed to lower the barrier for both power users and developers to shape and enhance the future of on-device Artificial Intelligence PC experiences. The tools and documentation available on GitHub empower users to define, build, and share new plug-ins, fostering a collaborative community focused on pushing the boundaries of personalized Artificial Intelligence workflows for the desktop environment.

68

Impact Score

Who decides how America uses Artificial Intelligence in war

Stanford experts are divided over how the United States should govern Artificial Intelligence in defense, surveillance, and warfare. Their views converge on one point: decisions with such high stakes cannot be left to companies alone.

GPUBreach bypasses IOMMU on GDDR6-based NVIDIA GPUs

Researchers from the University of Toronto describe GPUBreach, a rowhammer attack against GDDR6-based NVIDIA GPUs that can bypass IOMMU protections. The technique enables CPU-side privilege escalation by abusing trusted GPU driver behavior on the host system.

Google Vids opens free video generation to all Google users

Google has made Google Vids available to anyone with a Google account, adding free access to video generation with its latest models. The move expands Google’s end-to-end video workflow and increases pressure on rivals that charge for similar tools.

Court warns against chatbot legal advice in Heppner case

A federal court found that chats with a publicly available generative Artificial Intelligence tool were not protected by attorney-client privilege or the work-product doctrine. The ruling highlights litigation risks when executives or employees use chatbots for legal guidance without lawyer supervision.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.