Skip to main content
Termix is a local terminal dashboard that lets you run, monitor, and manage multiple CLI coding agents from a single browser tab. Think of it as Slack for your terminal — a coordination layer over your existing tools, not a replacement. You keep using Claude Code, Codex, Gemini CLI, and OpenCode exactly as you do today. Termix wraps each agent in its own terminal panel and adds the things you’ve been missing: live status indicators, message previews, browser notifications, session resume, and project grouping.

​
Why Termix

Running multiple AI agents across different terminal windows gets chaotic fast. You lose track of which agent is working, which one finished, and what it said. Termix solves this with a simple idea: put all your agents in one place and show you what’s happening.
  • Status at a glance — Green dot means working, “zzZ” means idle. No more checking each terminal window.
  • Live previews — See the latest message from each agent right in the sidebar, without switching tabs.
  • Notifications — Get a browser notification (with optional sound) when an agent finishes working. Walk away from your computer and come back when something needs your attention.
  • Session resume — Shut down Termix, come back later, and resume your agent sessions right where you left off.
  • Zero interference — Termix doesn’t sit between you and the agent. The terminal is a real terminal. Your keystrokes go directly to the agent, and the agent’s output comes directly to you.

​
Supported Agents

Termix works out of the box with four CLI agents:

Claude Code

Anthropic’s CLI agent. Telemetry works automatically — no setup needed.

Codex

OpenAI’s CLI agent. One-click telemetry setup from the Termix UI.

Gemini CLI

Google’s CLI agent. One-click telemetry setup from the Termix UI.

OpenCode

Run any model (local or cloud) through OpenCode’s TUI. Uses a plugin bridge for real-time status.
You can also add any CLI tool as a custom agent or a plain shell session.

​
How It Works

Termix runs a lightweight local server on your machine. Each agent session gets a real PTY (pseudo-terminal), rendered in your browser using xterm.js. The agent doesn’t know Termix exists — it thinks it’s running in a normal terminal. The key feature is telemetry integration. Each supported agent emits OpenTelemetry logs that Termix receives locally. This is how Termix knows when an agent is working, idle, or waiting for input — without parsing terminal output or intercepting your commands.
All data stays on your machine. Termix doesn’t send anything to external servers. The telemetry flows from the agent to Termix over localhost.

​
Quick Start

Get running in under a minute: 
npm install -g termix-cli
termix
Then open http://localhost:4000 in your browser.

Full setup guide

Detailed installation instructions and first session walkthrough.