[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74673":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":20,"hasPages":22,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":44,"readmeContent":45,"aiSummary":46,"trendingCount":16,"starSnapshotCount":16,"syncStatus":47,"lastSyncTime":48,"discoverSource":49},74673,"agent-of-empires","njbrake\u002Fagent-of-empires","njbrake","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. Uses tmux and git worktrees.","http:\u002F\u002Fwww.agent-of-empires.com\u002F",null,"Rust",2385,203,13,53,0,209,28.93,"MIT License",false,"main",true,[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"ai-coding","claude","claude-code","cli","codex","cursor","factory-droid-cli","gemini","gemini-cli","github-copilot-cli","hermes-agent","llm","mistral-vibe","opencode","orchestrator","pi","terminal","tmux","vibe","vibe-coding","2026-06-12 02:03:26","\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Flogo.png\" alt=\"Agent of Empires\" width=\"128\">\n  \u003Ch1 align=\"center\">Agent of Empires (AoE)\u003C\u002Fh1>\n  \u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F22434\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F22434\" alt=\"njbrake%2Fagent-of-empires | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n  \u003C\u002Fp>\n  \u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fnjbrake\u002Fagent-of-empires\u002Factions\u002Fworkflows\u002Fci.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fnjbrake\u002Fagent-of-empires\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg\" alt=\"CI\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fformulae.brew.sh\u002Fformula\u002Faoe\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fhomebrew\u002Fv\u002Faoe\" alt=\"Homebrew\">\u003C\u002Fa>\n    \u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg\" alt=\"License: MIT\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fclawhub.ai\u002Fnjbrake\u002Faoe\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClawHub-aoe-blue\" alt=\"ClawHub\">\u003C\u002Fa>\n    \u003Cbr>\n    \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002F@agent-of-empires\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FYouTube-channel-red?logo=youtube\" alt=\"YouTube\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fx.com\u002Fnatebrake\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ffollow-%40natebrake-black?logo=x&logoColor=white\" alt=\"Follow @natebrake\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002F5N3QKX3f6s\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Mozilla.ai-5865F2?logo=discord&logoColor=white\" alt=\"Discord\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fp>\n\nA session manager for AI coding agents on Linux and macOS. Use it from the terminal (TUI) or from any browser ([web dashboard](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fweb-dashboard\u002F)).\n\nRun multiple AI agents in parallel across different branches of your codebase, each in its own isolated session with optional Docker sandboxing. Access your agents from your laptop, phone, or tablet.\n\n## Why AoE?\n\nRunning one AI agent is easy. Running five of them across different branches, keeping track of which is stuck, which is waiting on input, and which just made a mess of your working tree, becomes a part-time job. AoE makes it a glance: one dashboard, one status column, git worktrees and Docker sandboxes set up for you, and sessions that outlive your terminal.\n\n> If you find this project useful, please consider giving it a star on GitHub: it helps others discover the project!\n>\n> Want merch? Visit the [store](https:\u002F\u002Fbrake.printful.me\u002F).\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fdemo.gif\" alt=\"Agent of Empires Demo\" width=\"800\">\n  \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Kk8dX_F-P4E\">Watch the getting started video\u003C\u002Fa>\n\u003C\u002Fp>\n\n## Features\n\n- **Multi-agent support**: Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI, Cursor CLI, Copilot CLI, Pi.dev, Factory Droid, Hermes, Kiro CLI, and Qwen Code\n- **TUI app**: visual interface to create, monitor, and manage sessions\n- **Web app** (Beta, stabilization in progress): create, monitor, and control your agents from any browser, installable as a PWA ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fweb-dashboard\u002F))\n  - **Cockpit** (Alpha, opt-in): mobile-first native rendering of agent state via the Agent Client Protocol, with plan panels, tool-call cards, and swipe-to-approve ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fcockpit\u002F))\n- **CLI app**: create, monitor, and control agents from the command line (integrates with tools like OpenClaw) ([reference](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fcli\u002Freference\u002F))\n- **Remote access from your phone**: press `R` in the TUI to expose the web dashboard over HTTPS with QR + passphrase auth. Uses Tailscale Funnel when available (stable URL, installable PWAs keep working across restarts) or Cloudflare Tunnel as a fallback ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fremote-phone-access\u002F))\n- **Status detection**: see which agents are running, waiting for input, or idle\n- **Git worktrees**: run parallel agents on different branches of the same repo ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fworktrees\u002F))\n- **Multi-repo workspaces**: drive a single session across several git repositories ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fmulti-repo-workspaces\u002F))\n- **Docker sandboxing**: isolate agents in containers with shared auth volumes ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fsandbox\u002F))\n- **Diff view**: review git changes and edit files without leaving the TUI ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fdiff-view\u002F))\n- **Session resume**: persist and resume Claude conversations across reboots and upgrades ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fsession-resume\u002F))\n- **Profiles**: separate workspaces for different projects or clients ([guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fguides\u002Fconfiguration\u002F#profiles))\n\n## Web Dashboard (Beta, stabilization in progress)\n\nAccess your agents from any browser. The real agent terminal renders in the page; switch sessions, type into the terminal, and review diffs without leaving the tab. Press `R` in the TUI to start the server, or see the [web dashboard guide](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fweb-dashboard\u002F) for details.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fweb-desktop.gif\" alt=\"Web dashboard\" width=\"800\">\n\u003C\u002Fp>\n\n## How It Works\n\nEach agent runs in its own [tmux](https:\u002F\u002Fgithub.com\u002Ftmux\u002Ftmux\u002Fwiki) session, so your agents keep running when you close the TUI, disconnect SSH, or your terminal crashes. Reopen `aoe` and everything is exactly where you left it.\n\nThe key tmux shortcut to know: **`Ctrl+b d`** detaches from a session and returns to the TUI.\n\n## Installation\n\n**Prerequisites:** [tmux](https:\u002F\u002Fgithub.com\u002Ftmux\u002Ftmux\u002Fwiki) (required), [Docker](https:\u002F\u002Fwww.docker.com\u002F) (optional, for sandboxing)\n\n```bash\n# Quick install (Linux & macOS)\ncurl -fsSL \\\n  https:\u002F\u002Fraw.githubusercontent.com\u002Fnjbrake\u002Fagent-of-empires\u002Fmain\u002Fscripts\u002Finstall.sh \\\n  | bash\n\n# Homebrew\nbrew install aoe\n\n# Nix\nnix run github:njbrake\u002Fagent-of-empires\n\n# Build from source\ngit clone https:\u002F\u002Fgithub.com\u002Fnjbrake\u002Fagent-of-empires\ncd agent-of-empires && cargo build --release\n```\n\n## Quick Start\n\n```bash\naoe                          # Launch the TUI\naoe add --cmd claude         # Create a session running Claude Code\naoe serve                    # Start the web dashboard\n```\n\nIn the TUI, press `?` for help. The bottom information bar shows all available keybindings in context.\n\n## Documentation\n\n- **[Installation](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Finstallation\u002F)**: prerequisites and install methods\n- **[Quick Start](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fquick-start\u002F)**: first steps and basic usage\n- **[Web Dashboard](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fweb-dashboard\u002F)**: browser access, PWA install, auth modes\n- **[Cockpit (Native Agent Rendering)](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fcockpit\u002F)**: mobile-first ACP rendering with plan panels and swipe-to-approve\n- **[Remote Phone Access](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fremote-phone-access\u002F)**: check on your agents from your phone via Tailscale Funnel or a Cloudflare tunnel\n- **[Git Worktrees](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fworktrees\u002F)**: parallel agents on different branches\n- **[Multi-Repo Workspaces](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fmulti-repo-workspaces\u002F)**: drive one session across several git repositories\n- **[Docker Sandbox](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fsandbox\u002F)**: container isolation for agents\n- **[Repo Config & Hooks](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Frepo-config\u002F)**: per-project settings and automation\n- **[Diff View](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fdiff-view\u002F)**: review and edit changes in the TUI\n- **[Session Resume (Claude)](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fsession-resume\u002F)**: persist and resume Claude conversations across reboots\n- **[Agent Command Overrides](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Fagent-override\u002F)**: custom scripts or sandboxed wrappers per agent\n- **[tmux Status Bar](https:\u002F\u002Fwww.agent-of-empires.com\u002Fguides\u002Ftmux-status-bar\u002F)**: integrated session monitoring\n- **[Sound Effects](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fsounds\u002F)**: audible agent status notifications\n- **[Configuration Reference](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fguides\u002Fconfiguration\u002F)**: all config options\n- **[CLI Reference](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fcli\u002Freference\u002F)**: complete command documentation\n- **[HTTP API Reference](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fapi\u002F)**: REST endpoints for external orchestrators\n- **[Development](https:\u002F\u002Fwww.agent-of-empires.com\u002Fdocs\u002Fdevelopment\u002F)**: contributing and local setup\n\n## FAQ\n\n### What happens when I close aoe?\n\nNothing. Sessions are tmux sessions running in the background. Open and close `aoe` as often as you like. Sessions only get removed when you explicitly delete them.\n\n### Which AI tools are supported?\n\nClaude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI, Cursor CLI, Copilot CLI, Pi.dev, Factory Droid, Hermes, Kiro CLI, and Qwen Code. AoE auto-detects which are installed on your system.\n\n### Can I use AoE over SSH?\n\nYes. AoE runs in your terminal and sessions persist across disconnects. If your mobile SSH client drops the connection, reconnect and `aoe` finds every session still running. See [mobile SSH clients](#using-aoe-with-mobile-ssh-clients-termius-blink-etc) for the one extra step needed on mobile.\n\n### Does it work on Windows?\n\nOnly through WSL2. AoE depends on tmux and POSIX process handling, so native Windows is not supported.\n\n### How is this different from just using tmux directly?\n\ntmux gives you persistent sessions. AoE adds agent-aware status detection (running, waiting, idle, error), git worktree management, Docker sandboxing, a web dashboard, remote phone access, and a diff viewer, all wrapped around your existing tmux workflow. You can still `tmux attach` to any AoE session directly.\n\n## Troubleshooting\n\n### Using aoe with mobile SSH clients (Termius, Blink, etc.)\n\nRun `aoe` inside a tmux session when connecting from mobile:\n\n```bash\ntmux new-session -s main\naoe\n```\n\nUse `Ctrl+b L` to toggle back to `aoe` after attaching to an agent session.\n\n### Claude Code is flickering\n\nThis is a known Claude Code issue, not an aoe problem: https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fclaude-code\u002Fissues\u002F1913\n\n## Development\n\n```bash\ncargo check          # Type-check\ncargo test           # Run tests\ncargo fmt            # Format\ncargo clippy         # Lint\ncargo build --release  # Release build\n\n# Debug logging (writes to debug.log in app data dir)\nAGENT_OF_EMPIRES_DEBUG=1 cargo run\n\n# View the resulting log with the best viewer available\n# (lnav > bat > less > stdout). Add --serve for the daemon log,\n# --all to merge both, --follow to live-tail, --path to print the\n# resolved file path, --no-pager to dump plain text.\naoe logs\n```\n\nDebug builds use a parallel namespace so they don't collide with an installed\nrelease `aoe`: app data lives in `~\u002F.agent-of-empires-dev` (macOS\u002FWindows) or\n`~\u002F.config\u002Fagent-of-empires-dev` (Linux), tmux sessions are prefixed\n`aoe_dev_`, and `aoe serve` defaults to port `8081`. Release builds are\nunchanged.\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=njbrake\u002Fagent-of-empires&type=date&legend=top-left)](https:\u002F\u002Fwww.star-history.com\u002F#njbrake\u002Fagent-of-empires&type=date&legend=top-left)\n\n## Acknowledgments\n\nInspired by [agent-deck](https:\u002F\u002Fgithub.com\u002Fasheshgoplani\u002Fagent-deck) (Go + Bubble Tea).\n\n## Author\n\nCreated by [Nate Brake](https:\u002F\u002Fx.com\u002Fnatebrake) ([@natebrake](https:\u002F\u002Fx.com\u002Fnatebrake)), Machine Learning Engineer at [Mozilla.ai](https:\u002F\u002Fwww.mozilla.ai\u002F).\n\n## License\n\nMIT License -- see [LICENSE](LICENSE) for details.\n","Agent of Empires (AoE) 是一个用于管理和运行多个AI编码代理的会话管理器，支持在Linux和macOS上通过终端（TUI）或网页界面访问。其核心功能包括多代理支持、基于tmux和git worktrees的会话隔离及Docker沙箱选项，能够同时运行Claude Code、OpenCode等不同类型的AI代理，并保持每个代理环境的独立性。AoE特别适合需要跨多个代码分支并行开发或测试AI助手能力的开发者使用，无论是从笔记本电脑还是移动设备都能轻松接入和管理这些智能助手，极大地简化了多任务处理流程。",2,"2026-05-12 11:07:52","high_star"]