nikitaclicks/agents.tmux — explained in plain English
Analysis updated 2026-05-18
See at a glance whether Claude Code, Copilot, Cursor, or Codex agents in tmux need your input.
Jump straight to a waiting agent's tmux window from the menu bar in iTerm2.
Run multiple AI coding agents in parallel without alt-tabbing to check each one.
| nikitaclicks/agents.tmux | a-bissell/unleash-lite | abhiinnovates/whatsapp-hr-assistant | |
|---|---|---|---|
| Stars | 1 | 1 | 1 |
| Language | Python | Python | Python |
| Setup difficulty | easy | hard | hard |
| Complexity | 2/5 | 4/5 | 3/5 |
| Audience | developer | researcher | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires macOS, tmux, and Python 3.11+ (or 3.9+ with tomli), iTerm2 is optional.
agents.tmux is a macOS menu bar app that watches tmux sessions and shows you, at a glance, whether the AI coding agents running inside them need your attention. If you run several agents like Claude Code, GitHub Copilot, Cursor, or Codex in parallel across different tmux panes, this app puts a single small badge in the menu bar summarizing their state instead of you having to alt tab between terminal windows to check. The badge uses a simple color code: green means agents are busy and you are free to do something else, yellow means at least one agent is waiting for input while others are still running, and red means every agent is waiting on you and needs action now. Clicking the badge shows a per agent status line and, if you use iTerm2, lets you jump straight to that agent's tmux window. Detection mostly relies on CPU usage: if an agent's process is using enough CPU it is considered busy, avoiding the need to parse terminal text for most cases. It also checks the last few lines of each pane's output for signs that an agent is waiting for input. These thresholds and settings live in a configuration file you can adjust, for example raising the CPU threshold if brief focus events cause false positives. Agents running outside tmux in their own terminal window are still detected through the operating system's process list and marked as external. To install it, you clone the repository and run a setup script that installs dependencies and starts the app, you can also run a Python script directly to check detection without opening the graphical interface. It requires macOS, tmux, and Python 3.11 or later, and is intended for developers who juggle multiple AI coding agents at once.
A macOS menu bar app that shows at a glance whether your tmux-based AI coding agents need attention.
Mainly Python. The stack also includes Python, tmux, iTerm2.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.