smtg-ai/claude-squad

Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.

What it solves

Claude Squad addresses the difficulty of managing multiple AI coding agents simultaneously. Instead of juggling separate terminal windows or risking code conflicts when running multiple tasks, it provides a centralized way to run various agents in isolated environments.

How it works

The tool uses a combination of three technologies to manage agents:

  1. tmux: Creates isolated terminal sessions for each agent instance.
  2. git worktrees: Ensures each session operates on its own branch and isolated codebase to prevent conflicts.
  3. TUI (Terminal User Interface): Provides a single window to navigate, manage, and monitor all active sessions.

Who it’s for

It is designed for developers who use AI coding assistants (like Claude Code, Aider, Codex, or Gemini) and want to run multiple autonomous tasks in the background across different branches of the same project.

Highlights

  • Multi-Agent Management: Run multiple instances of different AI agents in one terminal window.
  • Isolated Workspaces: Each task gets its own git workspace to avoid merge conflicts.
  • Background Execution: Complete tasks in the background, including an optional "yolo" auto-accept mode.
  • Review Workflow: Allows users to review changes and checkout branches before pushing them to GitHub.

Related

  • Project
    standardagents/dmux

    A tool that manages multiple AI coding agents in parallel by isolating each in its own tmux pane and git worktree.

  • Project
    johannesjo/parallel-code

    A GUI for dispatching multiple AI coding agents in parallel, each isolated in its own git worktree for easy review and merging.

  • Project
    YoanWai/agent-manager

    A terminal-based manager for AI coding agents that allows you to run multiple CLI agents side-by-side with integrated diff review and live status tracking.

  • Project
    asheshgoplani/agent-deck

    A command center for AI coding agents that allows users to manage, monitor, and orchestrate multiple agent sessions across different projects from a single terminal.

  • Project
    openwong2kim/wmux

    A workspace multiplexer for AI agents that allows running multiple agents in parallel across isolated git worktrees with persistent sessions and agent-to-agent coordination.