AIHouse
监控你的 AI Agent 在干什么。
一个开源的桌面应用,监控你所有 AI 编码 Agent 的任务状态。 任务跑完了没、卡住了没、成功了没、花了多少钱——瞟一眼就知道。
中文 | English
🖥️ 界面预览
┌──── 系统托盘 ───────────────────┐
│ 🟢 AIHouse · 一切正常 │ ← 瞟一眼就知道状态
└─────────────────────────────────┘
┌──────────────────────────────────┐
│ AIHouse 14:30 全部正常 ✅ │
│──────────────────────────────────│
│ Claude Code 🟢 重构用户模块 3m │ ← 每个 Agent 一行
│ Cursor 🔵 空闲 │
│ Hermes 🟢 生成文章 2m │
│ │
│ 📊 今日: 7完成 · 0失败 · 1卡住 │
│ 💰 今日费用: $2.45 │
│ │
│ [历史] [设置] [刷新] │
└──────────────────────────────────┘
✨ 功能
- 实时监控 — 系统托盘图标,颜色代表整体状态(绿/蓝/黄/红)
- 多 Agent 统一面板 — Claude Code、Cursor、Hermes、OpenCode 等在一个界面显示
- 任务追踪 — 每个 Agent 当前在跑什么任务、跑了多久
- 卡住检测 — Agent 长时间无活动自动告警
- 费用统计 — 每日 API 花费汇总,超预算自动通知
- 通知推送 — 微信推送(PushPlus)/ 桌面通知 / iOS(Bark)
- 历史记录 — 查看所有 Agent 的历史任务
- 自动检测 — 自动识别本机已安装的 Agent
- 跨平台 — macOS / Windows / Linux
- 轻量 — Python 后端 + Tauri 桌面端,打包仅 ~10MB
📦 安装
从 GitHub Releases 下载最新版 wheel 包安装。
macOS / Linux
pip install https://github.com/988hj7tczd-oss/aihouse/releases/download/v0.1.0/aihouse-0.1.0-py3-none-any.whl
aihouse init
aihouse start
aihouse status
Windows
pip install https://github.com/988hj7tczd-oss/aihouse/releases/download/v0.1.0/aihouse-0.1.0-py3-none-any.whl
aihouse init
aihouse start
aihouse status
后续上传 PyPI 后,只需
pip install aihouse
桌面端(可选)
桌面端提供系统托盘图标和可视化面板。
# 安装 Node.js:https://nodejs.org/
# 安装 Rust:https://rustup.rs/
cd desktop
npm install
npm run tauri dev # 开发模式
npm run tauri build # 打包安装程序
详细安装说明请查看 安装指南
🚀 快速开始
# 1. 初始化配置
aihouse init
# 2. 检测本机 Agent
aihouse detect
# 3. 启动监控
aihouse start
# 4. 查看状态
aihouse status
# 5. 查看任务历史
aihouse tasks
# 6. 停止监控
aihouse stop
详细使用说明请查看 快速开始
🤖 支持的 Agent
| Agent | 类型 | 监控方式 | 状态 |
|---|---|---|---|
| Hermes | CLI 工具 | 读 state.db SQLite | ✅ 稳定 |
| Claude Code | CLI 工具 | 读 ~/.claude/logs/ | ✅ 稳定 |
| Cursor | 桌面应用 | 进程检测 | ✅ 稳定 |
| Codex CLI | CLI 工具 | 进程检测 | ✅ 稳定 |
| OpenCode | CLI 工具 | 读 SQLite | ✅ 稳定 |
| OpenClaw | CLI 工具 | 读 JSON/SQLite | ✅ 稳定 |
| Kilo Code | VS Code 插件 | 进程检测 | ⚠️ 基础 |
| Cline | VS Code 插件 | 进程检测 | ⚠️ 基础 |
| GitHub Copilot | VS Code 插件 | 进程检测 | ⚠️ 基础 |
| 通义灵码 | VS Code 插件 | 进程检测 | ⚠️ 基础 |
| 通用模式 | 任意 Agent | 进程 + 文件变化 | ✅ 兜底 |
📋 CLI 命令
| 命令 | 说明 |
|---|---|
aihouse init |
初始化配置目录 |
aihouse start |
启动后台监控 |
aihouse stop |
停止监控 |
aihouse restart |
重启监控 |
aihouse status |
查看 Agent 状态 |
aihouse tasks |
查看任务历史 |
aihouse detect |
检测本机 Agent |
aihouse log |
查看运行日志 |
aihouse desktop |
启动桌面端 |
aihouse diagnose |
诊断适配器状态 |
完整命令参考请查看 CLI 命令
🏗️ 架构
┌──────────────────────────────────────┐
│ 桌面端 (Tauri) │
│ ┌──────────┐ ┌──────────────────┐ │
│ │ 系统托盘 │ │ 弹出面板 │ │
│ │ 🟢🔵🟡🔴 │ │ Agent 状态列表 │ │
│ └──────────┘ │ 任务详情 / 历史 │ │
│ │ / 设置 │ │
│ └────────┬─────────┘ │
└─────────────────────────┼────────────┘
│ REST API
┌─────────────────────────┼────────────┐
│ 后端 (Python) │ │
│ ┌────────────────────────────────┐ │
│ │ 调度器 → 适配器 → 分析引擎 │ │
│ │ ↓ │ │
│ │ SQLite 存储 ← 通知器 → 微信 │ │
│ └────────────────────────────────┘ │
└──────────────────────────────────────┘
详细架构说明请查看 架构说明
📖 文档
| 文档 | 说明 |
|---|---|
| 快速开始 | 5 分钟上手 |
| 安装指南 | Mac / Windows / Linux |
| CLI 命令 | 命令详解 |
| 配置说明 | 配置文件参考 |
| 桌面端使用 | 面板操作 |
| 架构说明 | 工作原理 |
| 适配器体系 | Agent 适配 |
| 常见问题 | 排错指南 |
| 开发者指南 | 参与开发 |
🤝 参与贡献
欢迎提交 Pull Request 或 Issue!
📄 开源协议
MIT License
Copyright (c) 2026 Jerry Wei
⭐ Star 历史
如果你觉得这个工具有用,欢迎点亮 Star ⭐
Metadata
Release files for aihouse 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| aihouse-0.1.1.tar.gz | 36.0 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| aihouse-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 86.7 kB
Release files / aihouse-0.1.1.tar.gz
| Download URL | aihouse-0.1.1.tar.gz |
|---|---|
| Size | 36.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
21bf8241443554da2d9ac2371585126b06aa4dfa6dd40826cbe335526b766cf8
|
|
BLAKE2b-256 checksum How to use checksums |
d9a00f9d7ed3a7cf182a38b39424be5940ad39c89485179eb434a69912634376
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 25, 2026.
Transparency logRelease files / aihouse-0.1.1-py3-none-any.whl
| Download URL | aihouse-0.1.1-py3-none-any.whl |
|---|---|
| Size | 50.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b48de42d4efdd2cdeb41bb164b760c063a4028cc7529aef901d5c40dc3b2d6c1
|
|
BLAKE2b-256 checksum How to use checksums |
8adbb31dee1136edbcd921a24eec05f67dc5c38db440ec924937433f718051bf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 25, 2026.
Transparency logSecurity for aihouse 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for aihouse-0.1.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 25, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.