Open330

Muxa — Development skill for Claude Code

Development community

Agent CLI observability and orchestration layer for tmux.

How to install Muxa

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Open330/muxa and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Muxa does

Agent CLI observability and orchestration layer for tmux.

Alternatives in Development

Claude Code Otel — A comprehensive observability solution for monitoring Claude Code usage, performance, and costs 306 ★
Tui Tmux Debugging — tmux-cli TUI Debugging 200 ★
Codex Agent — 让 OpenClaw 以“受控运行时”的方式操作 Codex CLI，而不是只靠一堆临时 tmux 命令 159 ★

README

**Work-oriented AI-agent observability & orchestration for tmux.**

See which agents are working, waiting, idle, or blocked from your tmux status line, a live TUI, desktop notifications, and local reports.

[![CI](https://github.com/Open330/muxa/actions/workflows/ci.yml/badge.svg)](https://github.com/Open330/muxa/actions/workflows/ci.yml) ![MSRV](https://img.shields.io/badge/MSRV-1.89-informational) ![License](https://img.shields.io/badge/license-MIT%20OR%20Apache--2.0-blue) ![status](https://img.shields.io/badge/status-beta-yellow)

**English** · [한국어](README.ko.md)

Try Muxa onboarding before reading

Launch the complete fullscreen tour. The script runs the real `muxa onboard` from a temporary copy of the release binary — checksum-verified, deleted on exit, nothing installed. It needs a supported release platform and network access; the live tour also needs tmux. Use `muxa onboard --print` for a non-interactive guide:

curl -fsSL https://raw.githubusercontent.com/Open330/muxa/main/scripts/onboard.sh | sh

muxa watch: sixteen agent sessions on one screen, the inspector, the swarm view, and muxa attend jumping to the agent that needs you

muxa watch — the fleet, the inspector, the swarm view, and muxa attend.

`muxa` is a small daemon and CLI for observing — and now driving — AI coding agents running inside terminal multiplexer panes. It reads agent state from existing hook/event systems (Claude Code, OpenAI Codex, Google Gemini CLI and its Antigravity successor), falls back to screen-manifest detection for hook-less agents, and correlates it all with multiplexer panes and sessions. Through `muxa mcp` a coding agent can also orchestrate the others — inspect state, send prompts, wait for changes.

It does not fork the multiplexer or modify