agent-of-empires: what it is, what problem it solves & why it's gaining traction

What it solves

Agent of Empires (AoE) solves the complexity of managing multiple AI coding agents simultaneously. It prevents the "part-time job" of tracking which agents are stuck, waiting for input, or modifying the working tree by providing a centralized dashboard for monitoring and controlling parallel agent sessions.

How it works

AoE acts as a session manager that runs each AI agent in its own isolated tmux session. This ensures that agents continue running even if the terminal is closed or the connection is lost. It integrates with git worktrees to allow agents to operate on different branches in parallel and offers optional Docker sandboxing to isolate agent environments. Users can interact with these agents via a Terminal User Interface (TUI), a web dashboard (installable as a PWA), or an HTTP API.

Who it’s for

Developers who use multiple AI coding agents (such as Claude Code, OpenCode, or Gemini CLI) and need a way to organize, monitor, and sandbox their workflows across different git branches and repositories.

Highlights

• Multi-agent support: Compatible with a wide range of tools including Claude Code, OpenCode, Mistral Vibe, and Copilot CLI.
• TUI & Web Dashboards: Visual interfaces to manage sessions, with a mobile-first "Structured View" for approving tool calls and viewing plans.
• Remote Access: Ability to expose the dashboard over HTTPS via Tailscale Funnel or Cloudflare Tunnel for phone access.
• Isolation: Support for Docker, Podman, and Apple Containers for sandboxing agents.
• Git Integration: Built-in management for git worktrees and multi-repo workspaces.
• Persistence: Sessions persist across reboots and terminal crashes thanks to tmux integration.