Volodymyr Zakhovaiko
Latest in AI

Oct 05, 2026

One setting cut my Claude Code cost per request by 39%. My first three mods: under 1%.

I replayed a month of my Claude Code logs. Most of the cost is the model re-reading context, so one setting that compacts earlier cut the cost of a request by 39%. The first three mods I wrote: under 1%.

Writing

Oct 05, 2026

One setting cut my Claude Code cost per request by 39%. My first three mods: under 1%.

I replayed a month of my Claude Code logs. Most of the cost is the model re-reading context, so one setting that compacts earlier cut the cost of a request by 39%. The first three mods I wrote: under 1%.

AIDXCost

Sep 27, 2026

My agents write code faster than I can read it, so I built Treeix

Running Claude Code and Codex in parallel worktrees moved the bottleneck from writing code to reading it. So I built Treeix, a free, open source AI workspace for Mac: every agent's diff, pull request and ticket in one app, and my comments go back as the next prompt.

AIDXTooling

Jun 20, 2026

One source of truth for Claude, Codex, and Copilot

Different teammates use different AI agents, and each reads its own instruction file. rulesync keeps one set of rules, subagents, commands, and MCP config in sync across all of them.

AIDXTooling