Lance Keay
Full-stack · DevOps · Notebook
I build web systems and the infrastructure under them, and I test the tools before I recommend them.
I'm Lance Keay, a senior full-stack developer and DevOps engineer working as a contractor. This is my CV and my notebook: hands-on reviews of AI tools, agents and self-hosted software, plus a monthly look at what model tokens cost.
Latest posts
All posts →Sample entries: placeholder posts showing the layout until real articles are published.
-
AI token market, November 2026
SummaryFrontier prices held still; the money moved to the small-model tier.
-
Serving a local model to a coding agent: Ollama, vLLM and llama.cpp compared
Use itvLLM if you have the VRAM to spare; Ollama if you'd rather not think about it.
-
Moving the homelab from Docker Compose to k3s, and back again
SkipFor eleven containers on one box, k3s cost more evenings than it saved.
-
Open WebUI as a shared front-end for self-hosted models
Worth a lookGood for a small team; plan your own SSO and backups before anyone relies on it.
Hiring a contractor?
Full-stack web work, CI/CD, cloud and on-prem infrastructure, and putting AI tooling into production with sensible guardrails. Remote, or on site by arrangement.
How the reviews work
Every tool runs on my own hardware or a paid account for at least a week of real work before I write about it. Each review states the version tested, what it cost, its licence, and a one-line verdict at the top, so you can stop reading there.
The monthly token market
At the start of each month I list published per-token prices for the main hosted models in one wide table, side by side with last month's, and note what actually changed for people paying the bills.