tmux status bar monitor for AI coding agents — track Claude, Codex, Gemini sessions in real time
<p align="center"> <img src="docs/banner-ansi.png" alt="marmonitor" width="640"> </p> <p align="center"> <strong>tmux status bar monitor for Claude Code, Codex & Gemini — track AI coding sessions in real time</strong> </p> <p align="center"> <a href="https://www.npmjs.com/package/marmonitor"><img src="https://img.shields.io/npm/v/marmonitor" alt="npm version"></a> <a href="https://github.com/mjjo16/marmonitor/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/marmonitor" alt="license"></a> <img src="https://img.shields.io/node/v/marmonitor" alt="node version"> <img src="https://img.shields.io/badge/platform-macOS%20%7C%20Linux-blue" alt="platform"> </p> <p align="center"> <b>English</b> | <a href="README.ko.md">한국어</a> </p> --- ## Why marmonitor? Running multiple AI coding agents in tmux is now the norm — Claude Code refactoring your backend, Codex writing tests in another pane, Gemini reviewing docs in a third. But as sessions multiply, you hit the same wall: - You switch to a pane only to find the agent has been waiting for `allow` for 10 minutes - You forget which window has the Codex session you were just working with - You have no idea how many tokens you've burned across sessions **There's no dashboard for this.** You're alt-tabbing between panes, checking each one manually. **marmonitor** fixes this. One line in your tmux.conf, and your status bar becomes a live control panel for every AI session on your machine. <p align="center"> <img src="docs/use_sample.png" alt="marmonitor tmux statusbar" width="640"> <br> <em>Agent counts, phase badges, and numbered attention pills — all in your tmux bar</em> </p> ### What it does **tmux statusline** — always visible at the bottom of your terminal: - Agent counts (`Cl 12`, `Cx 2`, `Gm 1`) — how many sessions are running - Phase alerts (`⏳ 1`, `🤔 2`, `🔧 1`) — which sessions need attention - Numbered pills (`1 ⏳Cl my-project allow`, `2 •Cx api-server 6m`) — jump to any session with
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.