ContextKeeper is a local AI assistant that lets you control your PC with voice or text commands — adjusting system settings, game parameters, and peripheral lighting. Built on NVIDIA's G-Assist platform, it runs entirely on your local RTX GPU with no cloud dependency, ensuring privacy and fast response times. It placed 4th at the NVIDIA G-Assist Hackathon and is listed on the NVIDIA Store.
Key Features
Local SLM Inference — Runs a Small Language Model on your local RTX GPU — no data leaves your machine.
Voice & Text Control — Natural language commands to control your PC, from system settings to game configurations.
Peripheral Lighting — Integrates with Logitech, Corsair, Nanoleaf, and other brands for synchronized lighting control.
Plugin Ecosystem — Supports Python and C++ plugin development, with community-extensible integrations for Twitch, Spotify, Gemini AI, and more.
Results
- 4th place at the NVIDIA G-Assist Hackathon
- Listed on the NVIDIA Store
- Supports zero-shot function calling — say "dim the lights" and it just works
ContextKeeper 是一个本地 AI 助手,用说话或打字的方式控制电脑——调系统设置、游戏参数、外设灯光。基于 NVIDIA G-Assist 平台,运行在本地 RTX 显卡上,不需要联网,隐私安全、响应快速。在 NVIDIA G-Assist Hackathon 获得第四名,已上架 NVIDIA 商店。
核心功能
SLM 本地运行 — AI 跑在本地 RTX 显卡上,不上传数据到云端。
语音/文字控制 — 支持自然语言指令控制 PC,从系统设置到游戏配置。
外设灯光控制 — 支持 Logitech、Corsair、Nanoleaf 等品牌的灯光联动。
插件生态 — 支持 Python/C++ 插件开发,社区可扩展对接 Twitch、Spotify、Gemini AI 等服务。
成果
- NVIDIA G-Assist Hackathon 第四名
- 已上架 NVIDIA 商店
- 支持零样本函数调用——说"把灯调暗一点"就行
