Galley's First Public Release

In August I wrote about why I built Galley, a Mac app for reading the markdown files an agent writes. Back then you had to build it yourself. Today Galley is a download. I have used it every day since, and the biggest changes in this release came straight from that daily use. Something I only noticed recently: I hardly open my code editors any more. Some weeks I open an IDE twice. Most of my day is now reading what agents write and telling them what to change, and that reading happens in Galley. ...

October 16, 2026 · 3 min · 533 words · Clement Ozemoya

Why I Built a Mac Markdown Reader for Agent Collaboration

Motivation Some months ago I realised I was the bottleneck. I am someone who still likes to read the plans and outputs the LLMs create. When working on multiple projects at a time, this starts to pile up and the rate of approval and understanding drops a lot. To add to that, I discovered the tools I was using to review the plans and outputs of the LLM were also flawed, and contributed to the problem. ...

August 28, 2026 · 6 min · 1217 words · Clement Ozemoya

You Need Permissions, Not Faith

Every week someone posts a screenshot of an agent deleting something it shouldn’t have, and the replies underneath say the same thing: the model is reckless and shouldn’t need babysitting. I understand the feeling and I think it’s a fair one. These things have improved so fast that expecting them not to make silly mistakes has started to feel reasonable. They still make them. But the distance between what a model might do and what it can actually reach on your machine is a config file most people have never opened. You need permissions to keep things running smooth, not faith. ...

August 19, 2026 · 6 min · 1209 words · Clement Ozemoya