Run Claude Code, Codex, OpenCode, Gemini CLI, Grok and Pi in one tmux list with live status per session. space answers a blocked agent without attaching, f forks the conversation into a named sibling, T pins a plain shell next to the agents, and ctrl+r opens whole-file diffs where line comments go back as one review prompt. Sessions can spawn into their own git worktrees. Ordinary tmux sessions survive quitting the manager. One Go binary, Apache-2.0. macOS, Linux, Windows via WSL2.
Daily reality: Claude Code in one pane, Codex in another, Cursor in a third, plus a few shells. An agent stops and waits for "yes". By the time I find the right pane, 20 min gone.
Just me? What's your setup notifications, layout tricks, or you've accepted the tax?
agent-manager
