Writing
Notes, devlogs, and side quests
What I'm building, what I'm learning, life, and everything in between.
Orchestrating a Claude Code agent fleet: 500 pages in 15 languages overnight
I started a Claude Code agent fleet from my phone, went to sleep, and woke up to 500 SSR pages in 15 languages. A devlog on running an overnight fleet of Opus, Sonnet, and Haiku agents.
The Claude Code habits quietly running up your usage
Most of what makes Claude Code slow and expensive is habit, not the tool. Here are the seven that cost me the most, each with a one-line fix and where to dig deeper.
The tools I use for agentic work
Agentic work has quietly become the new IDE. Here is the software I actually reach for: the coding agent itself, the terminal I run it in, the editor I read the diff in, remote access, local models, and the app that keeps the Mac awake through it all.
Running Claude Code on local models with LM Studio and Ollama
The Claude CLI is just a client for the Anthropic API, so anything that speaks that API can sit behind it. Point it at LM Studio or Ollama and you get the same terminal workflow on a local model. The same trick runs local models, voice, and memory in MyAgens.
Keepresso: keep your Mac awake, even with the lid closed
Keepresso is a native menu-bar app that keeps your Mac awake, even with the lid closed: smart triggers for AI agents and games, timed sessions, closed-display mode, plus CLI leases and an MCP server agents can call directly.
MyAgens: a self-hosted AI headquarters, reachable from Telegram
MyAgens runs a persistent fleet of AI agents on your own machine, reachable from Telegram or a browser. This is the catch-up post on everything it grew into: connectors to your tools, a crew of specialist Leads, durable memory, and a task board that delegates to agents.