This is an early release preview. You may encounter bugs.
Agent of Empires logo
Unclaimed

Tool deployment coding

Agent of Empires

Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.

A 87/100 GitHub score ? This grade is derived from GitHub signals, not user votes. Open for the full breakdown.
Discussion

01 / Summary

About Agent of Empires.

Agent of Empires (AoE) is a session manager for AI coding agents on Linux and macOS, written in Rust. It launches each agent in its own persistent tmux session, so agents keep running when you close the tool, disconnect SSH, or the terminal crashes. You run several agents in parallel across branches and monitor them all from one place, as a keyboard-driven terminal interface or a web dashboard.

Each agent can run on its own Git worktree, with automatic worktree creation and cleanup, and multi-repo workspaces let one session span several repositories. For safety, agents run in isolated containers through Docker, Podman, or Apple Containers, with configurable volume mounts and persistent auth. Status detection shows at a glance whether an agent is working, waiting for input, or idle, and notifications surface that without switching sessions.

The same live sessions are reachable from a terminal interface, a web dashboard, a CLI, and an HTTP API. The web dashboard runs in any browser with a real terminal in the page and a mobile view that renders agent state through the Agent Client Protocol, including plan panels, tool-call cards, and swipe-to-approve. Pressing a key exposes the dashboard over HTTPS with QR pairing through Tailscale Funnel or Cloudflare Tunnel. It drives Claude Code, Codex, OpenCode, Gemini CLI, Mistral Vibe, and other coding agents.

  • Persistent sessions: each agent runs in its own tmux session and keeps running after you close the tool or disconnect
  • Parallel agents: run agents across branches with automatic Git worktree creation and cleanup
  • Container sandboxing: isolate agents in Docker, Podman, or Apple Containers with configurable mounts and persistent auth
  • Multiple surfaces: a terminal interface, a web dashboard, a CLI, and an HTTP API over the same sessions
  • Web and mobile: a browser dashboard with a real terminal and a mobile view via the Agent Client Protocol, with swipe-to-approve
  • Remote access: expose the dashboard over HTTPS with QR pairing through Tailscale Funnel or Cloudflare Tunnel
  • Status detection: shows whether each agent is working, waiting, or idle, with notifications
  • Multi-repo workspaces: drive one session across several repositories with a project registry and multi-select pickers
  • Diff review: review diffs, with profiles, repo hooks, and custom agent commands
  • Broad agent support: works with Claude Code, Codex, OpenCode, Gemini CLI, Mistral Vibe, and more

02 / Discussion CREDIBILITY-GATED

Discussion

Reading is open to everyone. Posting and voting need a verified identity or a GitHub grade of B or higher.

  • No discussions yet.

04 / Build

Build with Agent of Empires.

Browse the catalog for frameworks, tools, and harnesses, each scored on real GitHub credibility.

Get Agent of Empires →

Browse the catalog