Every AI tool I use keeps its own history, and one of them quietly deletes it after a month. So I turned two years of chats and coding sessions into one plain-text archive that any AI can read.
My AI Chats Had a 30-Day Self-Destruct Timer. So I Built Them a Memory. Read More »
My AI agent kept breaking when cloud APIs throttled. The fix was not another vendor. It was running a small model on a VPS I already pay for.
My AI Agent Went Quiet. So I Stopped Renting Its Brain. Read More »
I set out to connect my AI agent to Postiz so it could help run social posts. What followed was a tiny masterclass in Docker, Traefik, Temporal, secrets, and why “one-click deploy” sometimes means “one-click into debugging.”
I Gave My AI Agent a Social Media Dashboard. Obviously Docker Had Other Plans. Read More »
I now run multiple AI agents. Not because I planned to. Because one couldn’t do everything I needed. This weekend I got two agents authenticated with different providers — one on OpenAI OAuth, one on Claude OAuth — both running through OpenClaw. A third is on the drawing board but I’m holding off until the
I Spent the Weekend Wiring Up a Multi-Agent Setup. Here’s What Actually Happened. Read More »
After weeks of broken configs and wrong usernames, the WordPress MCP integration finally works. Here’s a poem about it.
It’s Alive: My AI Can Post to My Blog Now (Send Help) Read More »