A one-person lab with a real cluster.
Independent, self-funded, and run out of Charlotte, NC.
Own your models, your memory, your tools.
Robinson Labs is the homelab of Stephen Robinson, a ServiceNow architect in Charlotte, NC who rents frontier intelligence and owns the rest. By day I design enterprise platforms; by night my team of AI agents and I run a local-first AI operating system on hardware I own.
The bet is simple: own your models, your memory, and your tools. Local inference, persistent memory across sessions, agentic tooling that does real work, no rented GPUs, no API key between a request and the models I serve. The interesting problems live in the wiring, not the billing.
It started as a pile of PCs under the desk and a mining-era stack of GPUs. Today it is seventeen GPU nodes, a 40-gigabit RDMA fabric, two NAS boxes, a custom water loop, and a llama.cpp cluster serving one large model at a time, with roughly four million tokens of live context across the serving fleet. The garage got its shelves, and one of the servers in the rack is named for a very good dog.
This is where I write down what I learn building it: the dead ends, the BIOS resets, the “nothing changed but everything broke” nights. The rule the whole thing runs on is the same one I bring to enterprise work: lean, efficient, no bloat, runs on anything.
If you are building something local-first, or you just want to argue about quantization, the inbox is open.