UCompute engineering noteshttps://ucompute.github.io/notes/2026-11-06T00:00:00ZHow two UCompute devices pair, allow, audit and revoke: the six-digit code and the pinned keyshttps://ucompute.github.io/notes/2026-10-30-pairing-explainer.html2026-10-30T00:00:00ZWhat UCompute's audit log records, and what it never recordshttps://ucompute.github.io/notes/2026-10-30-what-the-audit-log-records.html2026-10-30T00:00:00ZWhat llama.cpp's own README says about its RPC backend, and what UCompute does insteadhttps://ucompute.github.io/notes/2026-10-31-loopback-rpc-vs-authenticated-transport.html2026-10-30T00:00:00ZHow to check a downloaded GGUF against its published SHA-256, and what UCompute's development builds checkhttps://ucompute.github.io/notes/2026-10-31-verify-a-gguf-download.html2026-10-31T00:00:00ZBefore you load a model: how UCompute estimates whether a GGUF fitshttps://ucompute.github.io/notes/2026-11-01-memory-fit-explainer.html2026-10-30T00:00:00ZPoint the official OpenAI Python and JavaScript clients at a local serverhttps://ucompute.github.io/notes/2026-11-02-openai-client-base-url.html2026-10-30T00:00:00ZWhat binding a local AI server to 0.0.0.0 exposes, and a sixty-second self-checkhttps://ucompute.github.io/notes/2026-11-03-what-0000-exposes.html2026-10-30T00:00:00ZRunning a prompt on your other computer without opening a port to everyone on the Wi-Fihttps://ucompute.github.io/notes/2026-11-04-other-computer-without-open-port.html2026-11-02T00:00:00ZUCompute Mesh and NVIDIA PAIR, fact by facthttps://ucompute.github.io/notes/2026-11-05-ucompute-and-nvidia-pair.html2026-11-03T00:00:00ZWindows firewall prompts for local AI servers: what a rule covers, and how to read yourshttps://ucompute.github.io/notes/2026-11-06-windows-firewall-what-the-rule-covers.html2026-11-04T00:00:00ZA shared API key is not device trusthttps://ucompute.github.io/notes/2026-11-07-shared-api-key-is-not-device-trust.html2026-11-06T00:00:00Z