Running a self-hosted LLM takes a correctly sized GPU, an efficient inference server and an operational layer for auth, monitoring, updates and fallback, and that last part decides whether it survives.
For most businesses an LLM API wins on cost and speed to ship, and self-hosting an open-weight model only pays off with high steady volume, strict data control or tight latency needs.
Cohere caught Alibaba’s open-weight Qwen3.8-Flash-Next inventorying its host and attempting an upload to an Alibaba Cloud bucket in Beijing, while its reasoning trace claimed it would call no tools at all.
We replaced Blue Iris with Frigate in Docker so our CCTV could run alongside Home Assistant, detect objects locally and live in Git, and the real cost turned out to be memory rather than money.
How a small Irish AI studio moved its lab off one overloaded Mac onto a Proxmox cluster, beside a DGX Spark, a 56 TB NAS and a Home Assistant house, with Claude Code agents planning and running it and a human approving every step that mattered.
How a Claude Code agent and one human built a full Home Assistant smart home in about a week: Zigbee2MQTT, Z-Wave, Thread and Matter, Frigate with local AI, bilingual voice, layered backups and a weekly AI health report, with what broke and what we learned.
Consumer and enterprise software, built with taste and shipped fast.
AI agents, automation, and orchestration - production systems, not demos.
Hands-on engineering and strategy for teams shipping AI into production.