How to Run Multiple Claude Code Agents at Once (2026)
Run multiple Claude Code agents at once, plus Codex and Agy, from one terminal: a free one-command herdr setup with 3-keystroke launchers and a fleet CLI.
$ ./read.sh --all --sort=latest
$ ls ~/write
my name is on itRun multiple Claude Code agents at once, plus Codex and Agy, from one terminal: a free one-command herdr setup with 3-keystroke launchers and a fleet CLI.
A real 1M req/sec benchmark on AWS. The database broke exactly once. Here's what broke the other four times, and what actually fixed each one.
A live test of DeepSeek Harness, a self-hosted AI coding agent, shows what happens when an obedient agent is asked to expose a server, and why the firewall around it mattered more than the model inside it.
Block's Buzz gives AI coding agents their own keypairs and channel membership. A code-level walkthrough of how one agent wakes another up, with no orchestrator.
Tech firms are spending $750B on AI while cutting six-figure layoffs since 2023. A complete, sourced breakdown of who's actually hurt, why, and what's next.
A measurement procedure that tells you which layer of your stack owns the delay, before you optimize the wrong one. Worked through on a system that turned out to be 98% network.
Nginx serves your HTML fine but hands back CSS as text/plain. Why the obvious types{} fix breaks HTML, and what to use instead.
MCP is called the USB-C of AI. What that analogy actually means, why AI tool calling needed a standard, and what MCP still does not solve for you.
CVE-2026-63030 is critical, but automated exploitation fails on one overlooked detail that 70% of production sites already defend against.
Per-customer TLS breaks past a few hundred domains. How a shared edge resolves millions of custom hostnames: the registration payload, priority rules, and the RFC forcing an apex workaround.
A hands-on guide to GitHub Actions: local testing with act, automated test/deploy/npm-publish workflows, cron schedules, custom actions, and 2026 platform updates.
From gut instinct to Gödel: a personal walk through how logical reasoning escalates from everyday intuition to research-grade abstraction, and which rungs actually matter.
Mark Manson argues confidence, people-pleasing, and purpose are one knot: an unwillingness to be uncomfortable. Untie that, and everything else loosens.
Why the most successful people seem unreadable — never oversharing, occasionally vanishing, always a step ahead. The psychology of power unpacked into blunt, practical rules.
$ ls ~/notes
I kept this one short$ ls ~/write/medium
I brought the linksMy writing on Medium. Same name. Same lack of restraint. I publish new posts here first.