Your first AI loop should be for yourself (template included)
Mine your Claude Code and Codex sessions for content ideas, tool fixes, skills, hooks, and safer self-improvement loops.
Topic
15 essays on this topic, newest first.
Mine your Claude Code and Codex sessions for content ideas, tool fixes, skills, hooks, and safer self-improvement loops.
The system I used to make 100 illustrations hold together: style anchor, character sheet, fixed wrapper, in that order.
A practical multi-Mac setup for AI agents: mirrored folders, Tailscale, SSH aliases, relative paths, launchd, and phone-reachable sessions.
A practical way to make a local AI agent reachable from Telegram, Slack, or another inbox while keeping the work close to your files and tools.
Every Codex CLI command, safety setting, model pick, and prompting pattern I actually use now that GPT-5.4 is here.
The Claude Code commands, permission modes, model picks, and prompt patterns that actually matter in April 2026.
A setup guide for people building for someone who will never read a setup guide.
The complete checklist: hardware, subscriptions, email, remote access, and messaging. Get these set up and your AI agent can go live in a day.
ChatGPT and Claude have memory built in. OpenClaw doesn't. Here's how to build your own memory system with 5 plain text files.
How I turned my dictation history into actionable insights with a simple Claude Code skill