AI Insights Lab

Hands-on guides for developers who ship with AI coding agents. Claude Code setups, agent workflows, real cost numbers, and small models on cheap hardware. Everything here is run before it is written up.

Tiny on-device LLMs in 2026: which sub-1B models are worth running on a Raspberry Pi, an old laptop, or a CPU-only box

Under 1GB of RAM you pick by task, not by benchmark. A 14MB tool-calling model beats a 1B chat model if all you need is tool calls. Here is the shortlist, the memory numbers, and where each one falls over.

September 12, 2026 · 11 min · 2304 words · AI Insights Lab

A Claude Code setup that actually runs every day: settings.json, CLAUDE.md, hooks, skills, MCP

Most people run Claude Code on defaults. This is the config I actually use, with the parts that saved me from myself this week, and the parts I would rip out.

September 12, 2026 · 11 min · 2207 words · AI Insights Lab