Clairvoyance Hivemind pools idle office GPUs for local AI
Hivemind in Clairvoyance 0.90 shares local inference capacity from idle team computers, while Locama manages different GPUs, NPUs, and machines through a common runtime.
AT A GLANCE
Key points
- Hivemind shares local inference capacity among peer machines.
- Locama manages local models across GPUs, NPUs, and additional computers.
- The release adds hardware benchmarking for local AI suitability.
What is changing?
Stardock’s Clairvoyance workspace is adding Hivemind, a shared local-inference feature, in version 0.90. Hivemind makes spare compute from idle team computers available for common AI workloads. Clairvoyance’s Locama layer manages the installation and execution of local models and routes work across GPUs, NPUs, and additional machines.
The release also introduces a benchmarking approach intended to show how well specific hardware runs AI models. Clairvoyance’s official press kit describes Hivemind as shared local inference among peers and Locama as the local inference host that brings GPUs, NPUs, and extra machines under one runtime layer.
Explore the original sources
Source date: 5 November 2026.
Published by AI Radar: 5 Nov 2026, 22:07 (Istanbul, UTC+3). Updated: 5 Nov 2026, 23:12.
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…