Devember 2026: Home Lab Edition A homelab practitioner has outlined a Devember 2026 project to turn a dual-R9700 Linux workstation into a local-first AI operator, nicknamed Darth, that monitors infrastructure and performs allowlisted actions through a tool broker rather than direct root access. The project follows months of work on a custom PowerShell assistant built from several million .md files, which the author says outperformed commercial tools including CoPilot on detailed PowerShell projects. The author, who built the machine in Q1 2026 and has only SSH and WebUI access while out of town following a family death, set goals of read-only observation first, then shadow mode and human approval before any autonomous action, with all tool invocations logged and monitoring designed to survive the AI system being offline. Below is what I am shooting for, though my stepfather passed away last week, so I am out of town with my mother for who knows how long. I have full SSH and WebUI access to the machine I will be testing on, but physical access is relegated to how often my son is down to help be my hands and eyes. I built this machine back in Q12026 and spent several months tooling a custom PowerShell assistant from several million .md files from the usual PS places, of note, MS directly. It has worked well and helped me automate a lot of things in my daily work flow for the better without worrying about token costs. But the main reason is anyone that has used the big players to work on intricately detailed PS projects they just are not that good. Even CoPilot I would say is the worst. But I jays2cents. With all of the INSANE advancements in tooling for the ROCm and R9700 platform specifically of late, I figure why not build what I really need. Outlined below is the local AI assisted on my current build goals for this Devember. Again, if I fall short with everything going on with the family life thing, apologies for wasting your time. Admittedly the goals are lofty to say the least, but not entirely impossible.Without further ado: My Devember 2026 project is to learn how to turn a dual-R9700 Linux workstation into a local-first AI operator for my homelab. The goal is not simply to run a large language model. The goal is to build a system that can observe the state of my infrastructure, correlate telemetry across otherwise separate systems, explain failures in useful technical language, and eventually perform tightly controlled actions on my behalf. Examples of the questions it should ultimately answer include: Why is this NAS not responding? What is the uptime and current load of that Docker server? Does that Windows host appear to need a reboot? Which containers are unhealthy? Why has a requested movie not reached Plex yet? When was a monitored license plate last observed by UniFi Protect? Which smart-home devices are unreachable? What changed immediately before a service failure? This is a learning project first. AI may assist with research, code review, debugging, documentation, and boilerplate, but important architectural decisions, configuration, testing, troubleshooting, and integration work must remain understandable to me. I should be able to explain: why each component exists; how data moves through the system; what permissions each service has; what happens when a dependency fails; how a decision or action can be audited; and how to recover the system without AI assistance. Local first. Inference, telemetry, automation, logs, and household data should remain local wherever technically practical. Observe freely; act narrowly. Darth may receive broad read-only visibility into the homelab, but write operations will be explicitly allowlisted. No unrestricted root shell for the model. The language model will not receive direct root SSH, unrestricted Docker socket access, full Home Assistant administrator access, or blanket UniFi administrator credentials. Tool broker between AI and infrastructure. Infrastructure actions will be exposed as discrete tools such as: get host uptime host get container health host, container pause download client, id restart allowlisted container host, container set home assistant entity entity, state The broker, not the model, defines what is possible. Read → Suggest → Approve → Automate. New capabilities begin read-only. They progress through Shadow Mode and human approval before any policy-driven autonomous action is considered. Everything important is logged. Tool invocation, arguments, requesting user, result, errors, approval state, and execution time should be auditable. Monitoring must survive Darth being offline. Persistent telemetry and logs should live on lower-power always-on infrastructure rather than depending exclusively on the AI workstation. Recovery before cleverness. No change to kernels, GPU drivers, storage, networking, or remote access is accepted until rollback is understood. Darth Omniscience: AMD Ryzen 9 9950X3D 128 GB system RAM 2 × AMD Radeon AI PRO R9700 64 GB aggregate VRAM Ubuntu Linux Dedicated AI/model/data storage The first technical phase will benchmark the current R9700 software ecosystem rather than assuming a single inference runtime is best. Candidate runtimes include: Radiance Paiton vLLM/RDNA4 variants Strata llama.cpp AMD-supported ROCm inference stacks The architecture will be chosen from measured results on this hardware. Infrastructure observability Linux hosts Windows endpoints ZimaOS systems TrueNAS/Synology storage Docker containers UniFi networking UPS/power state system logs and metrics Home automation Home Assistant approximately 90 WiZ lights and sensors local-only device control wherever possible inventory, location, naming, firmware state, and health IT management NinjaOne/NinjaRMM read-only telemetry initially pending reboot and patch state device health and alerts future allowlisted remediation Media automation Plex Sonarr Radarr Overseerr/Jellyseerr Transmission related storage paths Security and cameras UniFi Protect camera health event history ALPR event research local retention/querying of useful event metadata where supported Private administration will not require direct public exposure of the homelab. A small client application, provisionally called DarthConnect , will eventually: determine whether Darth is securely reachable; establish the approved VPN path if required; validate the service endpoint; open the Darth interface; report connection state clearly. UniFi WireGuard, Teleport, Tailscale, or another appropriate private-access method will be evaluated. Judges will not receive broad VPN or LAN access. If a live demonstration endpoint is provided, it will use a separate Judge Mode with sanitized telemetry and restricted read-only tools. Private systems such as cameras, ALPR data, household automation, NAS contents, NinjaOne endpoints, and unrestricted infrastructure controls will remain inaccessible. The default delivery profile is Captain : calm measured precise authoritative dryly understated when appropriate British in cadence The intent is a distinguished Shakespearean-command style rather than a literal imitation or clone of any real actor. Before Darth receives meaningful write authority, new integrations operate in Shadow Mode. Example: User: “Why is Zima2 behaving badly?” Darth: Diagnosis: HandBrake has been continuously CPU-bound for 47 minutes and its worker stopped producing output 19 minutes ago. Recommended action: restart container "zima2", "handbrake" Shadow Mode: No action performed. Only after repeated correct recommendations will a tool graduate to approval-required execution. A successful Devember project does not require every planned integration to be complete. The core project succeeds when Darth can reliably: observe several independent homelab systems; correlate their telemetry; answer useful operational questions; explain how it reached its conclusions; recommend a remediation; execute a small set of explicitly authorized actions; record what it did; remain remotely recoverable; and demonstrate meaningful use of the dual R9700 hardware. The project should leave behind not only a working system, but documentation sufficient for someone else to understand the architecture, reproduce the important pieces, and learn from the failures encountered along the way.