cmux - Ghostty-based terminal with vertical tabs and notifications
I run a lot of Claude Code and Codex sessions in parallel. I was using Ghostty with a bunch of split panes, and relying on native macOS notifications to know when an agent needed me. But Claude Code's notification body is always just "Claude is waiting for your input" with no context, and with enough tabs open, I couldn't even read the titles anymore. I tried a few coding orchestrators but most of them were Electron/Tauri apps and the performance bugged me. I also just prefer the terminal since GUI orchestrators lock you into their workflow. So I built cmux as a native macOS app in…
In plain words
cmux is a macOS terminal application built on Ghostty that manages multiple parallel AI agent sessions. It features vertical tabs displaying git branch, working directory, and listening ports, plus a notification system that shows contextual information about when agents need input. Designed for developers running multiple Claude Code and Codex sessions simultaneously, cmux prioritizes native performance and terminal-based workflows over GUI-based orchestrators.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I run a lot of Claude Code and Codex sessions in parallel. I was using Ghostty with a bunch of split panes, and relying on native macOS notifications to know when an agent needed me. But Claude Code's notification body is always just "Claude is waiting for your input" with no context, and with enough tabs open, I couldn't even read the titles anymore. I tried a few coding orchestrators but most of them were Electron/Tauri apps and the performance bugged me. I also just prefer the terminal since GUI orchestrators lock you into their workflow. So I built cmux as a native macOS app in Swift/AppKit. It uses libghostty for terminal rendering and reads your existing Ghostty config for themes, fonts, colors, and more. The main additions are the sidebar and notification system. The sidebar has vertical tabs that show git branch, working directory, listening ports, and the latest notification text for each workspace. The notification system picks up terminal sequences (OSC 9/99/777) and has a CLI (cmux notify) you can wire into agent hooks for Claude Code, OpenCode, etc. When an agent is waiting, its pane gets a blue ring and the tab lights up in the sidebar, so I can tell which one needs me across splits and tabs. Cmd+Shift+U jumps to the most recent unread. The in-app browser has a scriptable API ported from agent-browser [1]. Agents can snapshot the accessibility tree, get element refs, click, fill forms, evaluate JS, and read console logs. You can split a browser pane next to your terminal and have Claude Code interact with your dev server directly. Everything is scriptable through the CLI and socket API – create workspaces/tabs, split panes, send keystrokes, open URLs in the browser. Demo video: https://www.youtube.com/watch?v=i-WxO5YUTOs Repo (AGPL): https://github.com/manaflow-ai/cmux [1] https://github.com/vercel-labs/agent-browser
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
