Overview

Codemux is a terminal-first agent development environment (ADE). It combines terminal multiplexing, an embedded browser, full git integration, and multi-agent orchestration into a single desktop application.

What It Does

• Prompt-first workspaces — Describe what you want to do, and Codemux creates a workspace with an auto-generated branch, selected agent, and your task as the initial prompt. Image paste works directly in the prompt input.
• Project management — Open existing repos or create new ones (empty or clone). An onboarding wizard detects your package manager and sets up dependencies automatically.
• Terminal multiplexer — Split panes, multiple tabs, WebGL rendering with Unicode 11 widths. Run AI coding agents (Claude Code, Codex, OpenCode, Gemini, Antigravity, Copilot, Cursor Agent, Amp, Grok, Droid, Mastracode, Pi) side by side. Panes persist across workspace switches so alt-screen TUIs keep their state.
• Agent status indicators — Real-time status dots show what each agent is doing: working (amber), needs input (red), ready for review (green). Visible in the sidebar and tab bar.
• Preset bar — Pin agent presets for one-click launch. A Run button with Ctrl+Shift+G executes your project's dev command instantly.
• Embedded browser — Hybrid browser with three input tiers: CSS selector, CDP coordinate-based, and OS-level (ydotool / Win32 SendInput) for stealth interaction. Agents control it programmatically. Viewport presets resize the actual viewport via CDP for responsive testing.
• Git workflow — Stage, commit, push, pull, view diffs, create PRs, merge branches locally, review CI checks — all from the sidebar panel. Sidebar PR icon, Review tab, "Checkout default branch" action.
• Local branch merge — Merge a base branch into your feature branch directly from the Changes panel. Conflict resolution with per-file ours/theirs/AI resolve.
• AI tools — Generate commit messages with AI, resolve merge conflicts with an AI agent on a safe temp branch.
• Setup scripts — Configure per-project setup/teardown commands that run automatically when workspaces open or close. Docker Compose support built in.
• Auth and sync — Sign in with GitHub OAuth or email/password. Personal settings sync across devices via your account. With Agent Chat (Beta) on, user-authored skills sync end-to-end encrypted via Skills Sync.
• Agent Chat (Beta) — Native conversational pane for Claude, Codex, and OpenCode with streaming, mode pills, attachments, plan proposals, and a unified multi-provider model picker. Opt-in via Settings → Beta Features.
• OpenFlow orchestration — Run multiple AI agents in coordinated workflows with an orchestrator managing delegation, communication, and phase transitions. (Linux/macOS only — Windows support pending bash-wrapper rewrite.)
• Cross-platform — Native Linux (AppImage / .deb / .rpm / AUR) and Windows (NSIS installer) binaries. Same auto-updater on both platforms.

Architecture

• Frontend: React 19 + Tailwind v4 + shadcn/ui, state via Zustand
• Backend: Rust (Tauri 2), async via Tokio
• Terminal: xterm.js with WebGL rendering (DOM fallback), Unicode 11 widths, kitty keyboard protocol, PTY via portable-pty (forked on Windows for hidden-console behavior)
• Browser: Pure-Rust agent-browser via direct CDP. Hybrid 3-tier input (selector → CDP coordinates → OS-level ydotool / Win32 SendInput), screenshot-based rendering with reactive stream-url reconnect
• Git: Direct git CLI calls from Rust, GitHub via gh CLI
• Agent Chat: AgentProvider trait with three concrete adapters — Claude (Claude Agent SDK via Bun-compiled sidecar), Codex (codex app-server JSON-RPC), OpenCode (Rust-direct HTTP against a managed opencode serve child)

Key Differences

Terminal-first: The terminal is the primary interface, not an afterthought. Panes resize, split, and swap fluidly. Canvas rendering avoids WebGL freezes.

Agent-native: Built for AI coding agents. Builtin presets launch any major coding-agent CLI — Claude Code, Codex, OpenCode, Gemini, Antigravity, Copilot, Cursor Agent, Amp, Grok, Droid, Mastracode, Pi — with one click, each in its own skip-permissions mode. Browser automation lets agents test their own output. OpenFlow coordinates multiple agents on a single task.

Workspace isolation: Each workspace can use git worktrees so agents work on separate branches without interfering with each other.