Karajan is a local-first multi-agent orchestrator. It doesn't call /v1/messages: it runs your existing AI CLIs as subprocesses (Claude Code, Codex, Gemini, Aider, OpenCode) and coordinates them through a TDD-first pipeline. I just published v3.0.0. Here's why I built it and how it's grown.
karajan-code@3.0.0 is on npm. nvm install 22.22.1 && npm i -g karajan-code@3 and you're done.
Why I built Karajan
I love coding with AI. What I don't love is babysitting it.
If you've spent any time with Claude Code, Codex, or Gemini, you know the loop:
You describe what you want.
Most developers using Claude Code work the same way: one long conversation, manual prompting between...
If you've been using Claude Code, Codex, or similar AI coding agents, you've probably felt the...
Every new agentic coding tool arrives with a version of the same implicit promise: this one will...
I built a team of 9 AI agents that run my work and life. Here's how you can too.
I Built a Local Autonomous Coding Agent with Ollama — Soul, Autonomy, and a 40-Round...
I’ve been experimenting with Claude Code to go beyond “AI as a copilot” and instead simulate a small...
