pstuart.ai is a lab notebook, not a product. The fleet is four local machines: two DGX Sparks (GB10), a Mac Studio M5 Max, and a gaming PC with an RTX 5090 under WSL. They pool through llama-swap — a private trusted-network gateway — for local coding and inference.
One Spark is the coordinator (resident agent / lightning, embeddings, Kokoro; on-demand Mage-Flow image and perception). The other is the GB10 coding peer (tensor-parallel Qwen3.8-Flash-Next, Coder-Next / long-context profiles, ornith, voice clone). The 5090 is exclusive media — music, video, image edit — not the Spark chat roster.
This site will not expose live internals, private hostnames, connect recipes, or a public API. The journal carries the study chronology from the internal benches record (page last-modified 2026-09-12): gates, rejects, and deploys, labeled as historical. The Oct 1 snapshot on the home page is a separate attributed pull — live generation that day was idle (0 tok/s). A later coordinator-page pull had incomplete live gauges, so that idle probe stays the published snapshot.