An Agent Wrote the Code. An Agent Reviewed the Code. A Human Merged It in Three Hours.

An Agent Wrote the Code. An Agent Reviewed the Code. A Human Merged It in Three Hours.
An Agent Wrote the Code. An Agent Reviewed the Code. A Human Merged It in Three Hours.

I recently wrote about giving Claude Code persistent memory using the MCP Memory Service. Go read that if you want the why. This post is about something else entirely. This post is about speed. I needed a feature in an open source project. I used an agent to write the code. A different agent reviewed

How to Give Claude Code Persistent Memory

How to Give Claude Code Persistent Memory
How to Give Claude Code Persistent Memory

Claude Code doesn’t remember anything between sessions. Every time you start a new session, it’s a blank slate. You can stuff context into CLAUDE.md files, but that’s static text, not searchable memory. It doesn’t learn your preferences, remember your decisions, or recall the research you did yesterday. The fix is an MCP memory server. I’ve

Stop Polishing the Cathedral

Stop Polishing the Cathedral
Stop Polishing the Cathedral - 90s zine collage showing megaphone from on high versus collaborative roundtable

In large enterprise software companies like Red Hat, two organizations build the product: the Business Unit (BU) and the Engineering org. The BU owns business strategy, market positioning, pricing, and customer relationships. Engineering writes the code and ships the bits. These aren’t adversaries. They’re two halves of the same machine. Steven Sinofsky, who ran Microsoft

Self-Hosting Postiz on RHEL 10: One Container, Six Platforms, Zero SaaS

Self-Hosting Postiz on RHEL 10: One Container, Six Platforms, Zero SaaS
Self-Hosting Postiz on RHEL 10: One Container, Six Platforms, Zero SaaS

I replaced Buffer with a self-hosted instance of Postiz running on RHEL 10. One Podman container. Six social media platforms. Full API control. This is the technical walkthrough of what I built and what broke along the way.

I Upgraded Request Tracker with an AI Co-Pilot. Here’s What Actually Happened.

I Upgraded Request Tracker with an AI Co-Pilot. Here’s What Actually Happened.
I Upgraded Request Tracker with an AI Co-Pilot. Here's What Actually Happened.

Request Tracker 4.4 reached end of life in November 2025. I’d been running RT 4.4.4 in a container on one of my Linode servers since 2020, and the upgrade to RT 6.0.2 had been sitting in my backlog for months. It’s the kind of task that’s never urgent until it is. You and I both

Building a Real Monitoring Stack: From 3 Alpine Containers to One UBI 10 Image with Zabbix

Building a Real Monitoring Stack: From 3 Alpine Containers to One UBI 10 Image with Zabbix
Zine-style collage showing the transformation from three chaotic Alpine containers to one clean UBI 10 Zabbix container with organized monitoring

I rebuilt my entire Zabbix monitoring stack — consolidating three Alpine containers into a single UBI 10 image, wiring up CloudFlare health checks, and building an IT Services dependency tree. With Claude Code and an MCP server, AI can now troubleshoot my infrastructure directly.

CI/CD for Your RHEL 10 Bootc Workstation: A Practical Guide to GitHub Actions, Podman, and Quay.io

CI/CD for Your RHEL 10 Bootc Workstation: A Practical Guide to GitHub Actions, Podman, and Quay.io
CI/CD for Image Mode RHEL - Lock and Ship concept with padlocked container crate

A practical walkthrough of setting up CI/CD for a RHEL 10 bootc workstation image using GitHub Actions, Podman, and Quay.io — including the workarounds you’ll actually need.

Red Hat Summit 2026 (May 11th – 14th)

Red Hat Summit 2026 (May 11th – 14th)
Red Hat Summit 2026 conference badge collage in 90s zine style - lanyard, boarding pass to Atlanta, vintage postcard, CRT terminal

We’ll be heading to Atlanta this May for Red Hat Summit 2026 and I’m pleased to share that my session has been accepted. The Roadmap Beyond RHEL 10: Building RHEL the open source way (RM1169) RHEL 10 is barely out the door and people are already asking what’s next. Fair enough — it’s the right

Running a Fully Local Voice Pipeline for Claude Code on RHEL 10 with Intel GPU Acceleration

Running a Fully Local Voice Pipeline for Claude Code on RHEL 10 with Intel GPU Acceleration

How I set up a fully local voice pipeline for Claude Code on RHEL 10 using Whisper.cpp, Kokoro TTS, and Intel Meteor Lake GPU acceleration via PyTorch XPU — achieving a 22x speedup with no cloud dependencies.

Local Models and Open Source Agents (and Why You Need to Pay Attention)

Local Models and Open Source Agents (and Why You Need to Pay Attention)

There’s a lot of negativity toward AI in the Fedora and RHEL communities right now. I get it — the hype cycle is real, and a lot of the marketing is insufferable. But I think the negativity is causing people to tune out, and when you tune out, you miss genuinely cool work that’s directly