baxian turns AI coding into a developer and QA review loop
baxian is an tool for coordinating multiple . It is built around a , where one agent writes code and another agent checks it. The developer agent implements the requested change and opens a real GitHub PR.
The QA agent reviews the code changes separately. Any issues become fixes, or the system records a clear reason for not changing them. The loop repeats until the code is considered ready.
The agents run as real Claude Code or Codex CLI sessions inside tmux. The tool shows a live wall of terminals in the browser, while still letting people attach from the shell, and it can run locally or on remote machines through SSH.
Key points
- baxian coordinates instead of relying on one agent alone.
- A developer agent writes the code and opens a GitHub PR.
- A QA agent reviews the changes independently.
- Problems are either fixed or answered with a clear reason.
- It runs Claude Code or Codex CLI sessions in tmux, locally or through SSH.