Ghost Core is a dedicated personal AI computer designed to execute models locally, continuously gathering contextual data from apps, wearables, and smart devices to provide proactive assistance.
What the product does and how it is positioned
Ghost Core is a standalone personal AI computing device designed to run machine learning models locally on dedicated desktop-grade hardware. It is built with an AMD Ryzen 5 7600 CPU and an NVIDIA RTX PRO 4000 Blackwell SFF Edition GPU with 24 GB of GDDR7 ECC memory, allowing computation to occur without sending data to external cloud services.
The system is designed to operate continuously, indexing information across user applications, files, browsing sessions, smart appliances, and health trackers. By maintaining continuous context, Core evaluates routines and surfaces contextual suggestions and notifications proactively without requiring explicit user prompts.
Source-supported ways to use the product
Core connects to calendars, commute information, and reminders to surface proactive alerts and logistics updates throughout the day.
Core integrates with health trackers such as Oura and Whoop to observe daily recovery, activity metrics, and routine changes over time.
Ghost Core is built on a compact hardware architecture designed specifically for local inference workloads. It includes an AMD Ryzen 5 7600 processor offering 6 cores and 12 threads, paired with 64 GB of DDR5 system memory and a 1 TB NVMe SSD.
Graphics and machine learning acceleration are handled by an NVIDIA RTX PRO 4000 Blackwell SFF Edition graphics processor equipped with 24 GB of GDDR7 ECC memory and 432 GB/s memory bandwidth. The unit supports running several specified models locally, including Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B, and Muse-Glimmer-30B.
Checks to run with your own material and workflow
What was checked and when
Answers based on the source-checked product record
Ghost Core features an AMD Ryzen 5 7600 six-core processor, an NVIDIA RTX PRO 4000 Blackwell SFF Edition GPU with 24 GB GDDR7 ECC memory, 64 GB of DDR5 RAM, and a 1 TB NVMe SSD.
Official specifications state that Ghost Core supports Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B, and Muse-Glimmer-30B running locally on the hardware.
Ghost Core executes models entirely on device, and official documentation states that no personal data leaves the home network during operation.
Ghost Core includes integrated Wi-Fi and Bluetooth connectivity to communicate with supported local devices, smart appliances, and wearables.
The system connects to email, calendars, finances, files, recordings, web browser history, smart-home devices like lights and cameras, and health trackers like Oura, Whoop, and Eight Sleep.
