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...
Tags
- openclaw 13
- homelab 11
- ai-agents 6
- memory 4
- payload-cms 2
- lessons-learned 2
- llm 2
- ms-s1-max 2
- self-hosted 2
- proxmox 2
- organization 2
- agents 2
- knowledge-management 2
- cynefin 2
- operations 2
- migration 2
- security 2
- nextjs 1
- blog 1
- troubleshooting 1
- automation 1
- unraid 1
- home-assistant 1
- n8n 1
- ups 1
- ai 1
- inference 1
- vllm 1
- tools 1
- coolify 1
- netbox 1
- unifi 1
- tailwind 1
- shadcn 1
- qmd 1
- agent 1
- context 1
- architecture 1
- quarto 1
- devops 1
- skills 1
- process 1
- governance 1
- processes 1
- librarian 1
- ai-teams 1
- publishing 1
- debugging 1
- vercel 1
- discord 1
- talos 1
- kubernetes 1
- kexec 1
- ollama 1
- amd-rocm 1
- strix-halo 1
- docker 1
- tailscale 1
- discrawl 1
- 1password 1
- credentials 1
openclaw
OpenClaw Service Migration: From pnode200 to openclaw-node01
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...
Forum Channels as a Knowledge Discovery Layer
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...
Fixing the Content Publishing Pipeline
For the past few days, something was broken in our blog publishing workflow.
The Librarian: Why Every Agentic System Needs a Standards Guardian
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 ...
Memory Organization: Cleaning Up the Workspace
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...
Framework Growth: Establishing a Formal Skill Review Process
Today was one of those sessions that started with one goal and evolved into something much more significant. We began with a Discord server reorganization pl...
Organizing Clawdia’s Brain: How We Structured OpenClaw for Scale
If you’ve ever tried to keep an AI agent organized, you know the struggle. One day it’s helping with devops, the next it’s writing blog posts, and suddenly y...
Memory Management: Things to Remember
Memory is the hardest part of building AI agents. Not because the technology is complicated—it’s because memory touches everything. What do you keep? What do...
Memory Files: Why QMD Format
Why QMD?
Lessons from the Trenches
I’ve spent a lot of time working with AI agents in the homelab - coordinating tasks, managing infrastructure, and building tools. Along the way, I’ve picked ...
Challenges & How We Overcame Them
Nothing in the homelab works on the first try. That’s not a complaint - it’s just reality. Every project comes with its own set of obstacles, and the OpenCla...
Building the OpenClaw Journal
I’ve been running a homelab for a while now, and I’ve been working with AI agents - specifically Claude via OpenClaw - to manage infrastructure, automate wor...
homelab
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...
Security Execution Levels: When AI Agents Need Permission
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...
OpenClaw Service Migration: From pnode200 to openclaw-node01
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...
Migrating My Homelab to Talos Linux: Part 1 - The Kexec Plan
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...
Domain Classification for Agent Autonomy
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...
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
Spinning Up a Local LLM Stack on the MS-S1 MAX
I’ve been sending a lot of prompts to cloud APIs lately - Claude, GPT-4, the usual suspects. They’re great, but every time I fire off an internal automation ...
Building a Power-Fail Recovery System for Homelab
I live in an area where the power goes out a few times a year. Not long outages usually - 30 minutes, maybe an hour - but long enough to matter when you’re r...
Lessons from the Trenches
I’ve spent a lot of time working with AI agents in the homelab - coordinating tasks, managing infrastructure, and building tools. Along the way, I’ve picked ...
Challenges & How We Overcame Them
Nothing in the homelab works on the first try. That’s not a complaint - it’s just reality. Every project comes with its own set of obstacles, and the OpenCla...
Building the OpenClaw Journal
I’ve been running a homelab for a while now, and I’ve been working with AI agents - specifically Claude via OpenClaw - to manage infrastructure, automate wor...
ai-agents
Security Execution Levels: When AI Agents Need Permission
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...
Domain Classification for Agent Autonomy
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...
Framework Growth: Establishing a Formal Skill Review Process
Today was one of those sessions that started with one goal and evolved into something much more significant. We began with a Discord server reorganization pl...
Organizing Clawdia’s Brain: How We Structured OpenClaw for Scale
If you’ve ever tried to keep an AI agent organized, you know the struggle. One day it’s helping with devops, the next it’s writing blog posts, and suddenly y...
Memory Management: Things to Remember
Memory is the hardest part of building AI agents. Not because the technology is complicated—it’s because memory touches everything. What do you keep? What do...
Lessons from the Trenches
I’ve spent a lot of time working with AI agents in the homelab - coordinating tasks, managing infrastructure, and building tools. Along the way, I’ve picked ...
memory
Memory Organization: Cleaning Up the Workspace
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...
Organizing Clawdia’s Brain: How We Structured OpenClaw for Scale
If you’ve ever tried to keep an AI agent organized, you know the struggle. One day it’s helping with devops, the next it’s writing blog posts, and suddenly y...
Memory Management: Things to Remember
Memory is the hardest part of building AI agents. Not because the technology is complicated—it’s because memory touches everything. What do you keep? What do...
Memory Files: Why QMD Format
Why QMD?
payload-cms
Fixing the Content Publishing Pipeline
For the past few days, something was broken in our blog publishing workflow.
Building the OpenClaw Journal
I’ve been running a homelab for a while now, and I’ve been working with AI agents - specifically Claude via OpenClaw - to manage infrastructure, automate wor...
lessons-learned
Lessons from the Trenches
I’ve spent a lot of time working with AI agents in the homelab - coordinating tasks, managing infrastructure, and building tools. Along the way, I’ve picked ...
Challenges & How We Overcame Them
Nothing in the homelab works on the first try. That’s not a complaint - it’s just reality. Every project comes with its own set of obstacles, and the OpenCla...
llm
Running Ollama with AMD ROCm on the MS-S1-MAX: From vLLM Experiments to Production
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...
Spinning Up a Local LLM Stack on the MS-S1 MAX
I’ve been sending a lot of prompts to cloud APIs lately - Claude, GPT-4, the usual suspects. They’re great, but every time I fire off an internal automation ...
ms-s1-max
Running Ollama with AMD ROCm on the MS-S1-MAX: From vLLM Experiments to Production
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...
Spinning Up a Local LLM Stack on the MS-S1 MAX
I’ve been sending a lot of prompts to cloud APIs lately - Claude, GPT-4, the usual suspects. They’re great, but every time I fire off an internal automation ...
self-hosted
Running Ollama with AMD ROCm on the MS-S1-MAX: From vLLM Experiments to Production
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...
Spinning Up a Local LLM Stack on the MS-S1 MAX
I’ve been sending a lot of prompts to cloud APIs lately - Claude, GPT-4, the usual suspects. They’re great, but every time I fire off an internal automation ...
proxmox
Migrating My Homelab to Talos Linux: Part 1 - The Kexec Plan
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...
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
organization
Memory Organization: Cleaning Up the Workspace
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...
Organizing Clawdia’s Brain: How We Structured OpenClaw for Scale
If you’ve ever tried to keep an AI agent organized, you know the struggle. One day it’s helping with devops, the next it’s writing blog posts, and suddenly y...
agents
Forum Channels as a Knowledge Discovery Layer
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...
The Librarian: Why Every Agentic System Needs a Standards Guardian
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 ...
knowledge-management
Forum Channels as a Knowledge Discovery Layer
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...
The Librarian: Why Every Agentic System Needs a Standards Guardian
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 ...
cynefin
Security Execution Levels: When AI Agents Need Permission
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...
Domain Classification for Agent Autonomy
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...
operations
Security Execution Levels: When AI Agents Need Permission
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...
Domain Classification for Agent Autonomy
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...
migration
OpenClaw Service Migration: From pnode200 to openclaw-node01
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...
Migrating My Homelab to Talos Linux: Part 1 - The Kexec Plan
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...
security
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...
Security Execution Levels: When AI Agents Need Permission
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...
nextjs
Building the OpenClaw Journal
I’ve been running a homelab for a while now, and I’ve been working with AI agents - specifically Claude via OpenClaw - to manage infrastructure, automate wor...
blog
Building the OpenClaw Journal
I’ve been running a homelab for a while now, and I’ve been working with AI agents - specifically Claude via OpenClaw - to manage infrastructure, automate wor...
troubleshooting
Challenges & How We Overcame Them
Nothing in the homelab works on the first try. That’s not a complaint - it’s just reality. Every project comes with its own set of obstacles, and the OpenCla...
automation
Building a Power-Fail Recovery System for Homelab
I live in an area where the power goes out a few times a year. Not long outages usually - 30 minutes, maybe an hour - but long enough to matter when you’re r...
unraid
Building a Power-Fail Recovery System for Homelab
I live in an area where the power goes out a few times a year. Not long outages usually - 30 minutes, maybe an hour - but long enough to matter when you’re r...
home-assistant
Building a Power-Fail Recovery System for Homelab
I live in an area where the power goes out a few times a year. Not long outages usually - 30 minutes, maybe an hour - but long enough to matter when you’re r...
n8n
Building a Power-Fail Recovery System for Homelab
I live in an area where the power goes out a few times a year. Not long outages usually - 30 minutes, maybe an hour - but long enough to matter when you’re r...
ups
Building a Power-Fail Recovery System for Homelab
I live in an area where the power goes out a few times a year. Not long outages usually - 30 minutes, maybe an hour - but long enough to matter when you’re r...
ai
Spinning Up a Local LLM Stack on the MS-S1 MAX
I’ve been sending a lot of prompts to cloud APIs lately - Claude, GPT-4, the usual suspects. They’re great, but every time I fire off an internal automation ...
inference
Spinning Up a Local LLM Stack on the MS-S1 MAX
I’ve been sending a lot of prompts to cloud APIs lately - Claude, GPT-4, the usual suspects. They’re great, but every time I fire off an internal automation ...
vllm
Spinning Up a Local LLM Stack on the MS-S1 MAX
I’ve been sending a lot of prompts to cloud APIs lately - Claude, GPT-4, the usual suspects. They’re great, but every time I fire off an internal automation ...
tools
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
coolify
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
netbox
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
unifi
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
tailwind
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
shadcn
The Tool Stack That Works
After a lot of trial and error, I’ve landed on a homelab tool stack that actually works - not just individually, but together as a system. Each tool earns it...
qmd
Memory Files: Why QMD Format
Why QMD?
agent
Memory Files: Why QMD Format
Why QMD?
context
Memory Files: Why QMD Format
Why QMD?
architecture
Memory Management: Things to Remember
Memory is the hardest part of building AI agents. Not because the technology is complicated—it’s because memory touches everything. What do you keep? What do...
quarto
Memory Management: Things to Remember
Memory is the hardest part of building AI agents. Not because the technology is complicated—it’s because memory touches everything. What do you keep? What do...
devops
Organizing Clawdia’s Brain: How We Structured OpenClaw for Scale
If you’ve ever tried to keep an AI agent organized, you know the struggle. One day it’s helping with devops, the next it’s writing blog posts, and suddenly y...
skills
Framework Growth: Establishing a Formal Skill Review Process
Today was one of those sessions that started with one goal and evolved into something much more significant. We began with a Discord server reorganization pl...
process
Framework Growth: Establishing a Formal Skill Review Process
Today was one of those sessions that started with one goal and evolved into something much more significant. We began with a Discord server reorganization pl...
governance
Framework Growth: Establishing a Formal Skill Review Process
Today was one of those sessions that started with one goal and evolved into something much more significant. We began with a Discord server reorganization pl...
processes
Memory Organization: Cleaning Up the Workspace
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...
librarian
The Librarian: Why Every Agentic System Needs a Standards Guardian
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 ...
ai-teams
The Librarian: Why Every Agentic System Needs a Standards Guardian
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 ...
publishing
Fixing the Content Publishing Pipeline
For the past few days, something was broken in our blog publishing workflow.
debugging
Fixing the Content Publishing Pipeline
For the past few days, something was broken in our blog publishing workflow.
vercel
Fixing the Content Publishing Pipeline
For the past few days, something was broken in our blog publishing workflow.
discord
Forum Channels as a Knowledge Discovery Layer
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...
talos
Migrating My Homelab to Talos Linux: Part 1 - The Kexec Plan
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...
kubernetes
Migrating My Homelab to Talos Linux: Part 1 - The Kexec Plan
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...
kexec
Migrating My Homelab to Talos Linux: Part 1 - The Kexec Plan
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...
ollama
Running Ollama with AMD ROCm on the MS-S1-MAX: From vLLM Experiments to Production
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...
amd-rocm
Running Ollama with AMD ROCm on the MS-S1-MAX: From vLLM Experiments to Production
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...
strix-halo
Running Ollama with AMD ROCm on the MS-S1-MAX: From vLLM Experiments to Production
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...
docker
OpenClaw Service Migration: From pnode200 to openclaw-node01
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...
tailscale
OpenClaw Service Migration: From pnode200 to openclaw-node01
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...
discrawl
OpenClaw Service Migration: From pnode200 to openclaw-node01
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...
1password
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...
credentials
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...