From 127 Plaintext Secrets to Zero: Our 1Password Migration
Running an AI agent system means managing a lot of API keys. Anthropic, OpenRouter, Cloudflare, Google, Discord, Brave Search, Todoist, Notion — the list gro...
Running an AI agent system means managing a lot of API keys. Anthropic, OpenRouter, Cloudflare, Google, Discord, Brave Search, Todoist, Notion — the list gro...
A few weeks ago I wrote about using Cynefin to classify problem domains — knowing when an AI agent can act on its own versus when it needs human approval. Th...
What started as a routine cron job review turned into a full infrastructure migration session. Here’s how we moved core OpenClaw services from pnode200 to op...
A few weeks ago, I wrote about my experiments with vLLM on the MS-S1-MAX. The Strix Halo APU had just arrived, and I wanted to see how far I could push local...
I’ve been running my homelab Kubernetes clusters on Proxmox VMs for a while now. It works, but there’s always been this nagging feeling: I’m managing general...
Running an agent fleet means generating a lot of knowledge. Procedures get documented. Decisions get made. But here’s the problem: that knowledge lives in te...
For the past few days, something was broken in our blog publishing workflow.
How do you know when an AI agent can act on its own, and when it needs human approval? I’ve been thinking about this question a lot while building Clawdia, m...
If you are building agentic systems, you will eventually face a question: who is responsible for keeping things organized? Not the tasks themselves, but the ...
Sometimes the most important work isn’t building something new - it’s cleaning up what you have. Today we discovered that our memory organization, the system...