A few days ago was the first time I was actually able to kick off a complicated agent-based workflow before bed and have it completely finished when I got up the next morning. It's really quite impressive what these tools can accomplish these days. Using amux workflows

Running multiple agents in parallel has been pretty addicting as I've been working on amux, but I wanted to force them to follow my preferred workflow. I wanted to make it repeatable and tweakable over time so I can more closely guide how agents get work done without

I worked over the weekend to get the core workflow that was introduced in v0.2 feeling smoother: write spec (now even faster), kick off work, validate results, update tests and docs, commit and push. When you are repeating this workflow interleaved across several agents working at the same time,

As I started working more with code agents and they became entwined in my workflows, I started getting itchy. The itchiness came from running an agent and sitting there while it worked. It felt like a waste, since my brain had already planned out the next 3 tasks I wanted

After working closely with a number of agentic code tools over the past year, I'm starting to coalesce towards a workflow that has been getting some pretty great results. Today I want to show off aspec — a tool that automates this workflow by managing predictable, secure agentic code

I, like many others lately, have found myself pulled into the Generative AI vortex. I kept some distance from this space for a while, only trying out the big chatbots that came out, but a few months ago I was pulled in to a project involving LLMs, and needed to

💡This post has been sitting in my drafts for several months, and rather than let it sit around longer, I’m going to publish it even though I don’t think it’s 100% “done”. Feedback is welcome. I’m attempting to give a name - “Anywhere Apps” - to a type

A few weeks ago I started hacking on Lipstick, a Go library that can replicate a local database called a store (initially SQLite) across geographically distant nodes. It uses the concept of a fabric - a durable messaging layer (initially based on NATS) to connect servers across regions. Lipstick allows an

Writing an application that runs on many servers in separate locations around the world is no easy task. You have to deal with access to application data, routing, inter-service communication, and many other things. The situation quickly becomes much more complicated than having an application server with a pool

I've been running a homelab for about 5 years now, starting with a single Raspberry Pi to experiment with Linux. It's evolved into something quite useful, and the latest iteration is something I'm interested in sharing more about. I fondly refer to this setup