YoanWai/agent-manager

The fastest developer workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.

What it solves

Developers often use multiple AI coding agents (like Claude Code, Gemini CLI, or Grok) simultaneously. Switching between different terminal tabs or windows to track which agent is finished, stuck, or needs input is inefficient. agent-manager provides a unified interface to run, monitor, and interact with these various CLI-based agents in one place.

How it works

It acts as a thin management layer over existing CLI tools. Each agent session is launched in its own persistent tmux session on a private server, ensuring that the agents maintain their own configurations, logins, and MCP servers. The manager provides a centralized list with live status updates, allowing users to send prompts to agents without needing to attach to their sessions manually. It also integrates a diff review system where users can comment on specific lines of changed code, and those comments are sent back to the agent as a review prompt.

Who it’s for

Developers who use multiple AI coding agents and want a faster, more organized workflow for managing concurrent AI-driven development tasks.

Highlights

  • Multi-Agent Orchestration: Run various tools like Claude Code, OpenCode, and Gemini CLI side-by-side in a single view.
  • Unified Prompting: Send prompts to any session using a quick-prompt feature (space) without leaving the main list.
  • Integrated Diff Review: Review changes as full-file diffs and send line-specific comments back to the agent.
  • Session Management: Organize agents into a project tree, fork conversations into separate sessions, and revive dead sessions.
  • Tmux Integration: Sessions survive the manager quitting because they run on a private tmux server.
  • Git Worktree Support: Ability to spawn sessions into their own git worktrees for isolated environment testing.

Related

  • Project
    smtg-ai/claude-squad

    A terminal application that manages multiple AI coding agents in isolated git workspaces, allowing developers to run several tasks simultaneously without conflicts.

  • Project
    thinkany-ai/termany

    Termany is a specialized terminal emulator designed to manage multiple concurrent AI coding agent sessions, providing a unified interface for monitoring, reviewing agent output, and handling project workflows.

  • Project
    Ark0N/Codeman

    A self-hosted mission control dashboard that manages multiple AI coding agents in persistent tmux sessions, providing a mobile-optimized web interface for remote monitoring and control.

  • Project
    jamesrochabrun/AgentHub

    A macOS desktop hub for managing multiple AI coding agent sessions (Claude Code and Codex) with integrated terminal, GitHub support, and live previews.

  • Project
    RizRiyz/luvus

    Luvus is a cross‑platform terminal UI that lets you launch, monitor, and orchestrate AI coding agents (Claude, Codex, Grok, etc.) alongside shells, editors, and Git tools. It provides persistent workspaces, pane management, agent‑aware status panels, Git/GitHub integration, remote‑machine support, a read‑only web view, and an extensible module system. Install via a script, Homebrew, or PowerShell, then use `luvus` to start a session, `luvus doctor` to verify setup, and `luvus update` for upgrades.