{"version":1,"type":"story","url":"https://digestai.news/story/stardock-adds-hivemind-to-clairvoyance-for-shared-local-ai-inference","json":"https://digestai.news/story/stardock-adds-hivemind-to-clairvoyance-for-shared-local-ai-inference.json","markdown":"https://digestai.news/story/stardock-adds-hivemind-to-clairvoyance-for-shared-local-ai-inference.md","slug":"stardock-adds-hivemind-to-clairvoyance-for-shared-local-ai-inference","headline":"Stardock adds Hivemind to Clairvoyance for shared local AI inference","summary":"Stardock released Clairvoyance 0.90 on November 5, embedding **Hivemind**—a feature that pools idle GPUs across a team’s machines for local AI inference. The update extends **Locama**, its local-model manager, to distribute workloads across Windows, macOS, and Linux systems, targeting routine tasks like procurement and legal operations. The company argues this reduces reliance on cloud services by leveraging existing hardware, though it does not specify how workloads are split or whether it supports tensor-parallel execution.\n\nHivemind’s value hinges on balancing hardware availability with task-specific performance, as routing requests may introduce latency. Clairvoyance also includes a **Local AI Benchmark** measuring prefill, decoding, and response times, with public results tied to user-submitted hardware configurations. The product integrates with **Qualcomm’s GenieX runtime**, expanding local compute options beyond traditional GPUs. Pricing starts at **$20/month for Professional** (including Hivemind) and **$100/seat/month for Enterprise**, with a free tier for non-commercial use.","keyPoints":["Hivemind shares idle GPUs across a team’s machines for local AI inference, reducing cloud dependency","Clairvoyance 0.90 adds a benchmark measuring prefill, decoding, and response times for local models","Professional plan costs $20/month with Hivemind; Enterprise at $100/seat/month includes team features"],"whyItMatters":"For businesses running high-volume AI tasks, Hivemind could cut cloud costs by repurposing underused hardware, though latency and model fit remain critical factors.","category":{"slug":"hardware","name":"Hardware & Compute","url":"https://digestai.news/category/hardware"},"entities":{"companies":["Stardock","Qualcomm"],"models":["Locama","GenieX"],"people":["Brad Wardell"]},"firstPublishedAt":"2026-11-05T18:00:00Z","updatedAt":"2026-11-05T18:00:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Unite.AI","title":"Stardock’s Clairvoyance Adds Hivemind to Share Idle GPUs for Local AI","url":"https://unite.ai/stardock-clairvoyance-hivemind-idle-gpus-local-ai","publishedAt":"2026-11-05T18:00:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Stardock adds Hivemind to Clairvoyance for shared local AI inference\", 5 November 2026, https://digestai.news/story/stardock-adds-hivemind-to-clairvoyance-for-shared-local-ai-inference","publisher":"Digest AI","title":"Stardock adds Hivemind to Clairvoyance for shared local AI inference","datePublished":"2026-11-05T18:00:00Z","url":"https://digestai.news/story/stardock-adds-hivemind-to-clairvoyance-for-shared-local-ai-inference"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}