Homelab and Infrastructure
Hardware, DNS, smart-home, bridge, voice, mail, and deployment infrastructure.
- Vaultwarden for agentic self-hosters: give your AI agent its own vault account November 14, 2026
How we run Vaultwarden so an AI agent can use real credentials without ever holding the owner's master password: a least-privilege account of its own, a CLI wrapper that locks after every call, nightly checked backups, and a restore drill that caught a broken restore script. Step by step, plus what is still open. - DGX Station GB300: How We Run It November 4, 2026
How we run our DGX Station GB300 (MSI WS300 + RTX PRO 6000 Max-Q): every maker ships the same software, what the 1,250 W power cap really costs (measured: almost nothing), why 240 V isn't a speed upgrade, the RTX at 325 W (+1%, kept at 300 W), security, storage and our update routine. Every setting has a check, apply and undo; machine-readable JSON, Markdown and a read-only check script for agents. Checked weekly. - DGX Spark: How We Run Them November 3, 2026
How we run eight headless DGX Sparks: stock NVIDIA kernel and driver kept current by hand, every setting with a check, apply and undo, two open kernel bugs mitigated, and our monthly update routine. Includes a machine-readable JSON copy, a Markdown copy and a read-only check script for agents. Checked weekly. - Testing DGX Spark Kernels November 2, 2026
We installed and tested DGX Spark kernels 7.0.0-1019 and 7.0.0-1024 on four Sparks. 1024 had 0 resets in 6 h of soak and the same speed as 6.17; 1019 works only with NVIDIA's kho=off fix. Plus our full Spark setup: October firmware, 0.5 GB display memory and headless mode gave +2.0 GiB per Spark. - Leaving Tailscale for plain WireGuard: one hub, one DNS name, help only on request October 31, 2026
Plan for moving the lab off Tailscale to plain WireGuard on the UniFi gateway: dynamic DNS for the hub only, on-request macOS Screen Sharing for people we help, scoped access for outside collaborators, retiring third-party remote-desktop apps, and what Hermes docs and plugins offer. - Networking DGX Station and DGX Sparks with MikroTik CRS804 October 30, 2026
A short how-to for linking eight DGX Sparks and a DGX Station GB300 with two MikroTik CRS804 switches: which cable goes where, the switch, Spark and Station settings, the checks, and the speeds to expect (24 GB/s NCCL across eight Sparks, 392 Gb/s from the Station's GPU memory). - GhettoRak's second switch: Kimi-K3 in four tiers October 28, 2026
Four tiers for one 1,499 GiB model: GB300 HBM, Grace, the RTX PRO 6000 sidecar, and eight Sparks at 100 GiB each. 1,485 GiB of expert memory for a 1,426 GiB expert set ā 58.6 GiB of slack, where the three-tier plan had 4.88. NVMe is the failure path, not a tier. - Why Four DGX Sparks Talk Slowly in the Middle: NCCL Tuning in Plain English October 26, 2026
A thread on X showed two NCCL settings that fix a mid-size all-reduce hole on four DGX Sparks. We reproduced it on ours: a 1 MiB exchange went from 1,154 µs to 137 µs (1.36 to 11.5 GB/s) with the 256 MiB peak unchanged at ~22 GB/s. Both of our serving recipes already carried the fix; what changed is our fabric gate, which only looked at big messages. Also measured: the Spark's 10 GbE Realtek port drops packets only under an 850 kpps UDP flood; every TCP test ran 9.41 Gbit/s with zero retransmits, so it stays stock. - CRS804 fan noise: why the fans surge, and the setting that stops it October 22, 2026 · updated October 30
On RouterOS 7.25 the CRS804's fans swing between 3,180 and 16,000 RPM every few minutes. One setting stops it: fan-min-speed-percent=38% holds a steady ~5,900 RPM with the chip at 55ā56 °C. Why it surges, what does not work, and the hardware options for real quiet. - DeepSeek Flash 1017: TensorFold vs SGLang vs vLLM on 4 DGX Sparks October 19, 2026
Third lane on the same four Sparks: a vLLM fork (Christopher Owen's spark-ds41f r6x, TileLang kernels, local build), not stock vLLM, which cannot serve V4.1 on SM121 yet. It leads SGLang at every concurrency (92 vs 85 tok/s at C1, 287 vs 263 at C6), prefills ~6K tok/s cold at 93K and reads a 300K needle in 55 s; TensorFold EXL3 still wins one stream at 100. Why Tony's 48.5 was a kernel-family gap, and nine tuning arms that all lost to Owen's defaults. - DeepSeek Flash 1017: TensorFold vs SGLang on 4 DGX Sparks October 18, 2026
Same model, same day, same switch: LibertAI's 3.5 bpw EXL3 pack on TensorFold (Sparks 1ā4) against the native MXFP4/FP8 checkpoint on SGLang via knapcio v2.4 (Sparks 5ā8). EXL3 wins single-stream decode by 18% (100 vs 85 tok/s); native wins prefill 1.6ā2Ć and the Hermes 20-hop agent gauntlet by 26%, and leads from four streams up. Quality gate identical, 71/75 both. Now extended to a 3-way with a tuned vLLM fork lane; since October 19 Lane B is stopped (kept) because that lane runs on its nodes. - GhettoRak: an 8-node DGX Spark cluster Updated October 29, 2026
Eight Sparks and the GB300 Station on two CRS804 switches. 24 GB/s all_reduce; 196 Gb/s RDMA per Station port; a 2,200 MHz clock cap keeps the rack on one 15 A strip. - StudioStack on the M4 Max: what we put in it October 16, 2026
One 8 TB SN850X in the M.2 slot, HDD bay empty, 80 Gb/s TB5 link, holds ~/Downloads. 6.29 GB/s read in one dd pass. - Switching 8 DGX Sparks and a GB300 Station: CRS804 Ć2 vs one 32Ć400G switch September 30, 2026
Two CRS804s vs one N9200-32DC for 8 Sparks + GB300: inter-switch latency ā1 µs (<0.5%/token); the real costs are the 2:1 trunk, zero spare ports, noise, and 240 V. - Sep Security Work: a container-escape bug, and what it shook loose September 23, 2026
Unpatched Ubuntu container-escape CVE; the audit found Docker bypassing ufw, a default DB password, and the vault key in agent files. All fixed. - A 1 MW solar datacenter that can grow to a gigawatt: where to put it September 20, 2026
Sourced site screen for a 1 MWā1 GW solar inference campus. Eastern NM / West TX wins on power, sun, land, and rules. - Fill the yard with solar. Then see what compute fits. September 19, 2026
Yard-first solar: 18ā21 kW islanded IT in winter. NVL72 does not fit a home lot. Theorycraft, no spend. - Photo Hunt, Part 2: 7,038 Photos Off a Wiped SSD September 2, 2026
Erased and reinstalled in 2019, Pictures empty. Imaged read-only, carved the image: 7,038 photos back, 1,495 of them lab scans of Mom's prints. - Photo Hunt: Mom's Photos Aren't on the NAS August 31, 2026
The NAS Aperture library was 2013ā2015 camera shots. The older photos should be on a 2009 Mini. If a reinstall wiped the catalog, they may still be retrievable. - MS-01 (Forge) ā a Full Inventory, August 2026 August 26, 2026
Read-only inventory of the rack's GPU-less Docker and agent host. Not overloaded ā just loaded. - Milo-Ark: A Model Archive Is Not a Downloads Folder June 18, 2026 Ā· updated November 13, 2026
70 checksummed trees, 27.46 TB on miloshare, nothing waiting on verify. Fourteen trees added since September, including the 1.56 TB Kimi-K3.1-Pro and Muse-Spark-Open NVFP4; DeepSeek-V4.1-Flash-1017 is the first tree with a passed smoke test in its manifest. - The DGX Sparks Arrived February 2026
Two NVIDIA DGX Spark GB10 units showed up. Here's what they look like out of the box. - DGX Spark Setup: From Box to Inference February 2026
Everything we learned setting up NVIDIA DGX Sparks. Drivers, containers, vLLM, networking. Honest notes from a home lab. - GoDaddy's UI Is Broken. Their API Isn't. April 9, 2026
Cisco Desk Pro needs a public TLS cert just to use its own microphone on a private LAN. GoDaddy's UI refused to accept the DNS record we needed. Their API did not. Milo handles DNS now. - The Linux Node, One Week In April 22, 2026
The $500 MS-01 was about token cost, not spare compute. - Adding an OpenClaw Linux Node April 21, 2026
Parts list and bring-up for the TecMojo MS-01 as an OpenClaw Linux node. - Milo Home: Wiring Up the House in a Weekend April 15, 2026
Building a local smart home automation layer ā Lutron, Roomba, Hue, HVAC, presence detection, and an event-driven automation engine ā from scratch in a day. - MiloBridge v2: Voice Clone, Smart Glasses, and Five Bugs That Nearly Killed It April 17, 2026
End-to-end voice pipeline validated: AirPods PTT to on-device STT (86ms) to Claude Haiku to zero-shot voice clone (RTF 0.46) on a DGX Spark ā with captions on Even G2 smart glasses. The five bugs were the interesting part. - MiloBridge v1: Voice Pipeline Goes Live April 5, 2026
AirPods PTT to first audio in 1.5 seconds. FluidAudio CoreML STT, Claude Haiku, Orpheus TTS. - I Built an AI to Manage My AI's Email April 13, 2026
Milo gets email. Lots of it. So we built a Python/SQLite triage pipeline that classifies, digests, and learns ā and explicitly refuses to send anything without approval. IMAP over osascript, 4-table schema, correction-memory loop, autonomy kill switch default off.