danielmiessler / LifeOS

The AI-Powered Life Operating System Website · Install · Walkthrough · Docs · Releases

LifeOS is a General Purpose AI Harness for doing anything you want to do in life and work with AI. It captures who you are, what you care about, and where you’re trying to go, then uses AI that knows you to help you get there. And because it has your full context, it makes everything you do more efficient and effective, from building apps, to starting a business, to creative projects…basically anything. LifeOS 是一个通用 AI 操作系统，旨在帮助你利用 AI 完成生活和工作中的任何事情。它会捕捉你的身份、关注点以及目标，然后利用了解你的 AI 来帮助你实现这些目标。由于它掌握了你的完整背景信息，它能让你的所有工作（从构建应用、创业到创意项目，基本上涵盖任何领域）变得更加高效。

Note: The whole system works on one central concept: moving from your Current State to your Ideal State — in pursuit of Euphoric Surprise. 注意： 整个系统基于一个核心概念：从你的“当前状态”迈向“理想状态”——以追求“欣喜若狂的惊喜”。

⭐ If LifeOS is useful to you, star the repo. Stars help more people find the project and keep it moving. It takes one click. ⭐ 如果 LifeOS 对你有帮助，请给仓库点个星标。星标能让更多人发现这个项目并推动其持续发展。只需轻轻一点。

Install

安装

Give it to your AI. LifeOS is installed by an AI, so the install is just a prompt. Paste this into your AI coding harness — Claude Code, Cursor, Codex, Hermes, or any capable agent — and it does the whole setup for you: 交给你的 AI。LifeOS 是由 AI 安装的，所以安装过程只需一条提示词。将其粘贴到你的 AI 编程助手（如 Claude Code、Cursor、Codex、Hermes 或任何功能强大的智能体）中，它就会为你完成整个设置：

Read https://ourlifeos.ai/install and install LifeOS for me.

Your AI reads the install page and walks the setup, asking permission before it touches anything. 你的 AI 会读取安装页面并引导设置过程，在进行任何操作前都会征求你的许可。

Prefer the terminal? There’s a one-line shortcut for Claude Code on macOS/Linux: 更喜欢终端操作？macOS/Linux 上的 Claude Code 有一个单行快捷指令：

curl -fsSL https://ourlifeos.ai/install.sh | bash

Either path needs a capable AI coding harness — we build and run on Claude Code — and bun. 无论哪种方式，都需要一个功能强大的 AI 编程助手（我们基于 Claude Code 构建和运行）以及 bun 环境。

Core Components

核心组件

The unique features — the parts you won’t find anywhere else. Anything a good harness already provides on its own (built-in subagents, for example) isn’t listed; this is only what LifeOS adds. See them live and click through on ourlifeos.ai. 这些是你在其他地方找不到的独特功能。任何优秀助手本身已具备的功能（例如内置子智能体）不会在此列出；这里仅展示 LifeOS 新增的内容。你可以在 ourlifeos.ai 上查看实时演示并点击了解。

🧩 Skills LifeOS installs as one self-contained skill that bundles the whole library — research, security, writing, art, and more. Browse them all on the site. 🧩 技能 LifeOS 以一个自包含的技能包形式安装，集成了整个库——包括研究、安全、写作、艺术等。你可以在网站上浏览所有技能。

Browse all skills → 浏览所有技能 →

❓ FAQ

常见问题解答

How is LifeOS different from using an AI harness on its own? LifeOS 与单独使用 AI 助手有什么不同？

Your harness gives you raw capability. LifeOS is the layer on top that makes it yours — a system that knows your goals, people, and context, and keeps working toward them: 你的助手为你提供原始能力。而 LifeOS 是叠加在上面的层，使其真正属于你——这是一个了解你的目标、人脉和背景，并持续为之努力的系统：

• Persistent memory — Your DA remembers past sessions, decisions, and learnings
• 持久记忆 — 你的数字助手（DA）会记住过去的会话、决策和学习成果
• Custom skills — Specialized capabilities for the things you do most
• 自定义技能 — 针对你最常做的事情提供的专业能力
• Your context — Goals, contacts, preferences—all available without re-explaining
• 你的背景信息 — 目标、联系人、偏好——无需重复解释即可随时调用
• Intelligent routing — Say “research this” and the right workflow triggers automatically
• 智能路由 — 说一句“研究这个”，正确的工作流就会自动触发
• Self-improvement — The system modifies itself based on what it learns
• 自我提升 — 系统会根据所学内容进行自我优化

Your harness is the engine. LifeOS is everything else that makes it your car. 你的助手是引擎，而 LifeOS 是让它成为你专属座驾的所有其他部件。

What harness does LifeOS run on? LifeOS 在什么助手上运行？

Any high-end one. LifeOS is harness-agnostic by design — it’s built on universal primitives (hooks, skills, context files, agentic routing), not one vendor’s features. The code is TypeScript and Bash, and the core ideas — TELOS, the Algorithm, skills, memory — port to any capable agent. Daniel builds and runs it on Claude Code, so that’s the most-tested path today. But LifeOS isn’t locked to it, and it’s designed to run wherever your AI does. 任何高端助手都可以。LifeOS 在设计上是与助手无关的——它基于通用的原语（钩子、技能、上下文文件、智能体路由）构建，而非依赖某个厂商的特定功能。代码采用 TypeScript 和 Bash 编写，核心理念（TELOS、算法、技能、记忆）可以移植到任何功能强大的智能体上。Daniel 目前在 Claude Code 上构建和运行它，因此这是目前测试最充分的路径。但 LifeOS 并不局限于此，它旨在随你的 AI 一起运行。

How is this different from fabric? 这与 fabric 有什么不同？

Fabric is a collection of AI prompts (patterns) for specific tasks. It’s focused on what to ask AI. LifeOS is infrastructure for how your DA operates—memory, skills, routing, context, self-improvement. They’re complementary. Many LifeOS users integrate Fabric patterns into their skills. Fabric 是针对特定任务的 AI 提示词（模式）集合，侧重于“如何向 AI 提问”。而 LifeOS 是关于你的数字助手如何运作的基础设施——包括记忆、技能、路由、上下文和自我提升。它们是互补的，许多 LifeOS 用户会将 Fabric 模式集成到他们的技能中。

What if I break something? 如果我弄坏了怎么办？

Recovery is straightforward: 恢复非常简单：

• Back up first — Before any upgrade: cp -r ~/.claude ~/.claude-backup-$(date +%Y%m%d)
• 先备份 — 升级前执行：cp -r ~/.claude ~/.claude-backup-$(date +%Y%m%d)
• USER/ is safe — Your customizations in USER/ are never touched by the installer or upgrades
• USER/ 目录是安全的 — 安装程序或升级永远不会触碰你在 USER/ 中的自定义设置
• Settings merge, not overwrite — The installer only updates identity and version fields; your hooks, statusline, and custom config are preserved
• 设置合并而非覆盖 — 安装程序仅更新身份和版本字段；你的钩子、状态栏和自定义配置会被保留
• Git-backed — Version control everything, roll back when needed
• Git 支持 — 一切皆可版本控制，需要时随时回滚
• History is preserved — Your DA’s memory survives mistakes
• 历史记录保留 — 你的数字助手的记忆不会因错误而丢失
• DA can fix it — Your DA helped build it, it can help repair it
• 数字助手可以修复它 — 既然是它协助构建的，它也能协助修复
• Re-install — Run the installer again; it detects existing installations and merges intelligently
• 重新安装 — 再次运行安装程序；它会自动检测现有安装并进行智能合并

🎯 Roadmap

路线图

Feature	Description
Local Model Support	Run LifeOS with local models (Ollama, llama.cpp) for privacy and cost control
Granular Model Routing	Route different tasks to different models based on complexity
Remote Access	Access your LifeOS from anywhere—mobile, web, other devices
Outbound Phone Calling	Voice capabilities for outbound calls
External Notifications	Robust notification system for Email, Discord, Telegram, Slack

功能	描述
本地模型支持	使用本地模型（Ollama, llama.cpp）运行 LifeOS，以实现隐私和成本控制
细粒度模型路由	根据任务复杂度将不同任务路由到不同模型
远程访问	从任何地方（手机、网页、其他设备）访问你的 LifeOS
外呼电话	用于拨打电话的语音功能
外部通知	为电子邮件、Discord、Telegram、Slack 提供强大的通知系统

🌐 Community

社区

• GitHub Discussions: Join the conversation
• GitHub 讨论： 加入对话
• Community Discord: LifeOS is discussed in the community Discord along with other AI projects
• 社区 Discord： 在社区 Discord 中与其它 AI 项目一起讨论 LifeOS
• Twitter/X: @danielmiessler
• Blog: danielmiessler.com
• Star History: View

🤝 Contributing

贡献

We welcome contributions! See our GitHub Issues for open tasks. 我们欢迎贡献！请查看我们的 GitHub Issues 以获取待办任务。

1. Fork the repository

2. Make your changes — Bug fixes, new skills, documentation improvements

3. Test thoroughly — Install in a fresh system to verify

4. Submit a PR with examples and testing evidence

5. Fork 本仓库

6. 进行修改——包括修复 Bug、添加新技能、改进文档

7. 彻底测试——在全新的系统中安装以验证

8. 提交包含示例和测试证据的 PR

📜 License

许可证

MIT License - see LICENSE for details. MIT 许可证 - 详情请参阅 LICENSE 文件。

🙏 Credits

致谢

• Anthropic and the Claude Code team — First and foremost. You are moving AI further and faster than anyone right now. Claude Code is the foundation that makes all of this possible.
• Anthropic 和 Claude Code 团队 — 首先要感谢你们。你们目前推动 AI 发展的速度和深度无人能及。Claude Code 是这一切得以实现的基础。
• IndyDevDan — For great videos on meta-prompting and custom agents that have inspired parts of LifeOS.
• IndyDevDan — 感谢你关于元提示词（meta-prompting）和自定义智能体的精彩视频，它们启发了 LifeOS 的部分设计。

Contributors 贡献者

LifeOS is built in the open, and the community’s pull requests, forensic bug reports, and fresh-install writeups directly shape every release. The public repo is generated from a private source tree, so community PRs are ported into source with credit rather than merged directly — same fix, durable across releases. LifeOS 是公开构建的，社区的 PR、深入的 Bug 报告和新安装心得直接塑造了每一个版本。公共仓库是从私有源码树生成的，因此社区的 PR 是在署名后移植到源码中，而不是直接合并——同样的修复，在各个版本中持续有效。

The 28 highest-commit contributors — see all on the contributors graph. Avatars are committers only, so the lists below carry everyone the graph can’t see. 提交次数最多的 28 位贡献者——请在贡献者图表中查看全部名单。头像仅显示提交者，因此下方的列表包含了图表中未显示的所有人。

• fayerman-source — Google Cloud TTS provider integration and Linux audio support for the voice system.
• fayerman-source — Google Cloud TTS 提供商集成以及语音系统的 Linux 音频支持。
• Matt Espinoza — Extensive testing, ideas, and feedback, plus roadmap contributions.
• Matt Espinoza — 大量的测试、想法和反馈，以及路线图贡献。

Code contributions (merged or ported PRs): 代码贡献（已合并或移植的 PR）： adamlevoy · anikinsasha · asdf86753