holaOS：开源一体化 AI Agent 工作空间

为你和你的 Agent 而打造的计算机

在一个本地优先的工作空间中运行任何 Agent——Claude Code、Codex 或 holaOS——并让它们访问你的工具、文件以及同一份共享记忆。内置前沿模型，或使用你自己的密钥。

---

✨ 有何不同

🔀 运行任意 Agent，一个工作空间

Claude Code、Codex 与内置 holaOS Agent 可并排运行，无须切换。无论运行哪一个 Agent，它们都共享相同的记忆、工具、技能和应用。为不同工作选择最合适的 Agent，而无须每次重建你的配置。

• 没有锁定——带来你已经信任的 Agent。
• 一切共享——一份上下文、一套工具、一个工作空间。
• 结果一致——无论由谁驱动，均使用相同的技能和集成。

🧠 一份记忆，每个 Agent 都能使用

上下文、偏好和项目历史存放在单一的共享记忆中——**以你可以读取和编辑的纯文本文件形式保存在本地。**切换 Agent、关闭应用、一周后再回来：它依然知道你上次进行到哪里。

• 不再从零开始——跨会话和跨 Agent 的持久记忆。
• 本地优先，归你所有——数据在你的机器上，可见、可编辑，而不是被锁在他人的云端。
• 真正可召回——记忆经过结构化和嵌入处理，可在需要时返回正确上下文。

💸 按你的方式使用模型——内置或自带密钥

一个账户，使用所有模型——无需密钥、无需配置、无需在服务商之间切换。最新前沿模型已内置：适合日常高频使用、成本效率更高的 Kimi K3 和 GLM 5.2，以及用于棘手问题的顶级 GPT 5.6、Claude Opus 5 和 Fable 5。更倾向于自己的服务商？可为 OpenAI、Anthropic 或任意兼容 OpenAI、Anthropic 的端点自带密钥（BYOK）——这些请求使用的是你的账户，而非你的 holaOS 套餐。

• 零配置默认方案——一个账户即可使用所有 SOTA 模型，无需管理 API 密钥。
• 按需 BYOK——你的密钥、你的服务商、你的费率。
• 每项任务选择合适模型——可按工作、按 Agent 选择。

🪟 HolaApps——应用与 Agent 并排协作

从工作空间内的市场安装应用后，它们会作为**真实、可交互的界面，直接在你的 Agent 旁边打开。**你可以在应用内观看 Agent 工作，随时介入，结果会直接落在相应位置——不是一堵聊天文本墙，而是由 Agent 驱动、位于 Agent 旁边的真实应用。

• 真实界面，而非聊天——每个应用都是实时 UI（Notion、浏览器或你自己的应用），而不是文字记录。
• 原生并排设计——应用和 Agent 共享屏幕，因此你始终能看到发生了什么，并可随时接手。
• 一键安装——浏览工作空间内市场，立即打开任意应用。
• 接入你自己的应用——将 HolaApp 指向任意 URL 和 MCP 服务器；它运行在你的机器上，由你打开和操控。

🧩 技能、集成与 MCP——教一次，到处复用

• 集成——通过一键 OAuth 连接 Gmail、Notion、Slack、GitHub、Linear 及其他 50 多项服务。Agent 可跨你的工具读取和执行操作，无须胶水代码；每个 Agent 都会继承相同连接。
• MCP——接入任意 Model Context Protocol 服务器，为 Agent 提供新工具。可使用自己的服务器，或一键安装社区 MCP 服务器。
• 技能——将一个工作流打包一次；任意 Agent 都能按需运行它。
• 组合包——将技能和集成捆绑为一个一键安装包。

🛠️ 整个工作站均可由 Agent 操作

• 🌐 由 Agent 驱动的真实浏览器——Agent 可操作已登录的浏览器进行浏览、点击和提取，且始终在你的控制之下。
• 🎨 内置前沿生成能力——每个 Agent 内均集成最新图像、视频和音频模型。用一条提示词即可为视频绘制分镜、设计海报、为脚本配音。
• 📄 真实交付物——将报告、电子表格和幻灯片保存为可发送的真实 .xlsx、.pptx 和 .docx 文件，而不是困在聊天中的文本。
• 💬 从你使用的任何聊天工具访问——飞书、微信、Slack、Telegram。可从任意对话线程发送任务；结果将返回同一线程。
• ⏰ 自动化——按计划或触发条件运行。摘要、监控和报告可自行完成并归档。

---

🖥️ 桌面应用	下载即可使用。无须配置——内置前沿模型，可免费开始。
🔓 开源	可自行托管。采用修改版 Apache 2.0 许可证；自带密钥，完全在你的机器上运行。
🏢 企业版	为每个 Agent、技能和应用提供带按角色权限的 SSO。连接内部系统而不暴露它们。每项操作均有审计日志。支持本地部署或部署至你自己的云。

---

如需在 macOS、Linux 或 WSL 的全新机器上进行初始化，请使用仓库安装脚本：

curl -fsSL https://raw.githubusercontent.com/holaboss-ai/holaOS/refs/heads/main/scripts/install.sh | bash -s -- --launch

如果你希望控制每一个配置步骤，也可以选择手动安装路径。

如果 holaOS 对你有用或让你感兴趣，非常感谢你为项目点一个 GitHub Star。

你很可能不需要本节，因为“一行安装”会运行相同的配置流程。当你希望检查或控制每一个步骤时，请使用“手动安装”。如果使用手动路径，请先验证常规前置条件：

git --version node --version npm --version

如果你使用 Codex、Claude Code、Cursor、Windsurf 或其他编程 Agent，可以用一句话把安装说明交给它：

Run the holaOS install script from https://raw.githubusercontent.com/holaboss-ai/holaOS/refs/heads/main/scripts/install.sh. It should install git and Node.js 24.14.1/npm if they are missing, clone or update the repo into ~/holaboss-ai unless I specify another --dir, run desktop:install, create apps/desktop/.env from apps/desktop/.env.example if needed, run desktop:prepare-runtime:local and desktop:typecheck, and only run desktop:dev if I ask for --launch. If Electron cannot open, stop after verification and tell me the next manual step.

这种交接方式使安装流程保持自包含，同时将详细的引导步骤保留在仓库本地的 INSTALL.md 操作手册中。

这是用于本地桌面端开发的基础安装流程。

1. 从仓库根目录安装桌面端依赖：

2. 创建本地环境文件：

cp apps/desktop/.env.example apps/desktop/.env

如果你完全按照仓库结构操作，请让该文件尽量接近模板，仅修改服务商或机器所需的值。规范路径为 apps/desktop/.env。现有的旧版 desktop/.env 文件目前仍可使用，但新的配置应使用 apps/desktop/.env。

3. 准备本地运行时包：

npm run desktop:prepare-runtime:local

4. 如果希望在启动 Electron 前快速执行一次验证，请运行：

npm run desktop:typecheck

5. 以开发模式启动桌面应用：

predev 钩子会验证环境、重新构建原生模块，并确保已存在暂存的运行时包。

如果希望在打开桌面应用之前暂存运行时，有两种常用路径：

从本地运行时构建：

npm run desktop:prepare-runtime:local

获取最新发布的运行时：

npm run desktop:prepare-runtime

当你正在积极修改运行时代码时，使用本地路径。当你希望基于已知的发布版本构件验证桌面端时，使用已发布的运行时包。

希望以最快路径获得可用的本地桌面环境时，请使用“一行安装”。需要自行检查或控制每个配置步骤时，请使用“手动安装”。

• 许可证：修改版 Apache 2.0，附带额外的商业分发和品牌使用条件。参见 LICENSE。
• 安全问题：请私下报告至 admin@holaboss.ai。参见 SECURITY.md。

The Computer for You and Your Agent

Run any agent — Claude Code, Codex, or holaOS — in one local-first workspace, over your tools, your files, and one shared memory. Frontier models built in, or bring your own keys.

Website · Docs · Sign in · Quick Start

⭐ If holaOS is useful, a star helps more builders find it.

---

✨ What makes it different

🔀 Run any agent, one workspace

Claude Code, Codex, and the built-in holaOS agent — side by side, no switching. Whichever you run, it shares the same memory, tools, skills, and apps. Use the best agent for the job without rebuilding your setup every time.

• No lock-in — bring the agent you already trust.
• Shared everything — one context, one set of tools, one workspace.
• Consistent results — the same skills and integrations, whatever's driving.

🧠 One memory, every agent

Context, preferences, and project history live in a single shared memory — stored locally, as plain files you can read and edit. Switch agents, close the app, come back next week: it already knows where you left off.

• Never start from zero — durable memory across sessions and agents.
• Local-first & yours — on your machine, visible and editable, not locked in someone else's cloud.
• Actually recallable — structured and embedded, so the right context returns when it's needed.

💸 Models your way — built in, or bring your own

One account, every model — no keys, no setup, no switching between providers. The latest frontier models are built in : cost-efficient Kimi K3 and GLM 5.2 for everyday volume, plus top-tier GPT 5.6 , Claude Opus 5 , and Fable 5 for the hard problems. Prefer your own provider? Bring your own keys for OpenAI, Anthropic, or any OpenAI- or Anthropic-compatible endpoint — those run on your account, not your holaOS plan.

• Zero-setup default — one account, every SOTA model, no API keys to manage.
• BYOK when you want it — your keys, your providers, your rates.
• Right model per task — pick per job, per agent.

🪟 HolaApps — apps and agent, side by side

Install apps from the in-workspace marketplace and they open as real, interactive surfaces right beside your agent. Watch it work inside the app, step in whenever you want, and the result lands in place — not a wall of chat text, but the actual app, driven by the agent, next to the agent.

• Real surfaces, not chat — every app is a live UI (Notion, a browser, your own app), not a transcript.
• Side-by-side by design — app and agent share the screen, so you always see what's happening and can take over.
• One click to install — browse the in-workspace marketplace and open any app instantly.
• Bring your own — point a HolaApp at any URL and MCP server; it lives on your machine, yours to open and drive.

🧩 Skills, Integrations & MCP — teach it once, reuse everywhere

• Integrations — connect Gmail, Notion, Slack, GitHub, Linear and 50+ more with one-click OAuth. Agents read and act across your tools, no glue code — and every agent inherits the same connections.
• MCP — plug in any Model Context Protocol server to give your agents new tools. Bring your own, or install community MCP servers in one click.
• Skills — package a workflow once; any agent runs it on demand.
• Combos — bundle skills and integrations into a single one-click install.

🛠️ Your entire workstation, agent-operable

• 🌐 A real browser, driven by agents — signed-in browsers your agents drive to browse, click, and extract — under your control.
• 🎨 Frontier generation built in — the latest image, video, and audio models inside every agent. Storyboard a video, design a poster, voice a script — one prompt.
• 📄 Real deliverables — reports, spreadsheets, and slides saved as real .xlsx, .pptx, and .docx files you can send, not text stuck in a chat.
• 💬 Reach it from anywhere you chat — Feishu, WeChat, Slack, Telegram. Send a task from any thread; the result comes back to the same thread.
• ⏰ Automation — run on a schedule or a trigger. Digests, monitors, and reports finish and file themselves.

---

|
---|---
🖥️ Desktop app | Download and go. Nothing to set up — frontier models built in, free to start.
🔓 Open source | Self-host it. Modified Apache 2.0, bring your own keys, run it entirely on your machine.
🏢 Enterprise | SSO with per-role permissions for every agent, skill, and app. Connect internal systems without exposing them. Audit logs on every action. On-prem or your own cloud.

---

For a fresh-machine bootstrap on macOS, Linux, or WSL, use the repository installer:

curl -fsSL https://raw.githubusercontent.com/holaboss-ai/holaOS/refs/heads/main/scripts/install.sh | bash -s -- --launch

You can also follow the manual path if you want to control each setup step.

If holaOS is useful or interesting, a GitHub Star would be greatly appreciated.

You likely will not need this section because One-Line Install runs the same setup. Use Manual Install when you want to inspect or control each step. If you use the manual path, verify the usual prerequisites first:

git --version
node --version
npm --version

If you use Codex, Claude Code, Cursor, Windsurf, or another coding agent, you can hand it the setup instructions in one sentence:

Run the holaOS install script from https://raw.githubusercontent.com/holaboss-ai/holaOS/refs/heads/main/scripts/install.sh. It should install git and Node.js 24.14.1/npm if they are missing, clone or update the repo into ~/holaboss-ai unless I specify another --dir, run desktop:install, create apps/desktop/.env from apps/desktop/.env.example if needed, run desktop:prepare-runtime:local and desktop:typecheck, and only run desktop:dev if I ask for --launch. If Electron cannot open, stop after verification and tell me the next manual step.

That handoff keeps the installation flow self-contained while leaving the detailed bootstrap steps in the repo-local INSTALL.md runbook.

This is the baseline installation flow for local desktop development.

1. Install the desktop dependencies from the repository root:

2. Create your local environment file:

cp apps/desktop/.env.example apps/desktop/.env

If you are following the repo exactly, keep the file close to the template and only change the values that your provider or machine needs. The canonical path is apps/desktop/.env. Existing legacy desktop/.env files are still accepted for now, but new setups should use apps/desktop/.env.

3. Prepare the local runtime bundle:

npm run desktop:prepare-runtime:local

4. If you want a quick validation pass before launching Electron, run:

npm run desktop:typecheck

5. Start the desktop app in development mode:

The predev hook will validate the environment, rebuild native modules, and make sure a staged runtime bundle exists.

If you want to stage the runtime before opening the desktop app, there are two common paths:

Build from local runtime:

npm run desktop:prepare-runtime:local

Fetch the latest published runtime:

npm run desktop:prepare-runtime

Use the local path when you are actively changing runtime code. Use the published bundle when you want to verify the desktop against a known release artifact.

Use One-Line Install when you want the fastest path to a working local desktop environment. Use Manual Install when you need to inspect or control each setup step yourself.

• License: modified Apache 2.0 with additional commercial-distribution and branding conditions. See LICENSE.
• Security issues: report privately to admin@holaboss.ai. See SECURITY.md.