NVIDIA’s G-Assist chatbot, a context-aware in-game assistant that provides walkthroughs and graphics setting tweaks, can now interact with external services like Spotify through a new plugin system. It’s an odd idea, but it may be useful to those who don’t want to open a browser window while gaming.
G-Assist is an eight-year old April Fool’s joke that became a real piece of softwarein 2024. The sales pitch is pretty simple—instead of navigating away from your game to look up walkthroughs, tips, or other info, you can just pull up the G-Assist chatbot and ask it for guidance. Because G-Assist is “context-aware,” it can “see” what’s going on in your game, and it can automatically adjust your graphics settings or GPU clock speed to improve game performance.
Now, thanks to a new plugin builder, developers can add custom functionality to G-Assist. This plugin system is fairly robust, with the ability to make API calls or adjust system controls through C++ and Python bindings. Plugins run locally, of course, and developers can share plugins with other people through GitHub or other repositories.
NVIDIA has published a repo of sample plugins, some of which are fairly compelling. There’s a plugin that can adjust your RGB lighting, for example, and another that can control Spotify playback. One of NVIDIA’s plugins will check if your favorite Twitch streamer is live—kinda weird, but okay—while another invokes Google Gemini. I’m not sure why you’d need Gemini while in-game, but I guess it’s nice to have the option, as NVIDIA’s game walkthrough database is still pretty slim.
Community-made plugins will (presumably) be more exciting or useful than what NVIDIA is offering. I also see this as an interesting tool for homelab-obsessed gamers—you could use G-Assist to interact with apps or services that are running on your local network, such as a self-hosted game server, an LLM, or a game caching server. Of course, plugins designed for local networks may be difficult to share with other people, so developers may focus their attention on web-based services like Spotify and so on.
As for whether G-Assist is genuinely “useful” to the average gamer—ehhh. Even with the plugin system, it’s basically just a tool that saves you from navigating away from your games. It might make sense to someone who uses a single-monitor setup (or a gaming laptop). But if you’ve got more than one screen, hopping into a web browser to look up a walkthrough or open a Spotify playlist isn’t much of a hassle. And if you’re like me, you rarely multitask or look up walkthroughs while gaming, so an in-game chatbot would mostly go unused.
Related
Nvidia Drivers on Linux: What You Need to Know
Nvidia is known for being somewhat tricky on Linux, but is that reputation earned or exaggerated?
I assume that G-Assist will mainly appeal to developers and AI enthusiasts, at least for the time being. New community-made plugins may help the chatbot enter the mainstream, but I don’t believe we’ll reach that point anytime soon. For what it’s worth, Microsoft and Razer are also interested in the idea of context-aware gaming chatbots, so its not like NVIDIA is working in a vacuum—the industry is pushing for something like G-Assist to gain traction.
You can find instructions for loading, building, or sharing plugins at the NVIDIA G-Assist GitHub repository. G-Assist itself is available within the NVIDIA app for Windows and requires a compatible RTX GPU with at least 12GB of VRAM (side note, NVIDIA needs to stop introducing new 8GB GPUs). Note that G-Assist requires about 10GB of storage and may impact game performance.
