# E2B Desktop — Headless Linux Desktop for AI Computer Use

> E2B Desktop is a managed cloud Linux desktop with X11, browser, file manager, terminal. Plug into Claude Computer Use or OpenAI's CUA without local Docker.

## Install

Copy the content below into your project:

## Quick Use

1. `pip install e2b-desktop`
2. `Sandbox.create()` returns a desktop with `desktop.stream.get_url()` for VNC
3. Drive with `desktop.left_click(x, y)`, `desktop.write(...)`, `desktop.screenshot()`

---

## Intro

E2B Desktop is a managed cloud Linux desktop — full X11 environment, Firefox, terminal, file manager — exposed via VNC and an SDK. Drop in as the target environment for Claude Computer Use or OpenAI's CUA without setting up Docker / X11 locally. Best for: production deployments of computer-using AI agents, multi-tenant SaaS where each user gets an isolated desktop. Works with: Python SDK, Claude Computer Use, any agent that drives a screen+keyboard+mouse. Setup time: 5 minutes.

---

### Spawn a desktop sandbox

```python
from e2b_desktop import Sandbox

with Sandbox.create() as desktop:
    # Get the live VNC URL (embed in iframe or watch via VNC viewer)
    print(desktop.stream.get_url())

    # Take a screenshot
    screenshot = desktop.screenshot()
    with open("screenshot.png", "wb") as f:
        f.write(screenshot)

    # Drive mouse + keyboard
    desktop.left_click(500, 300)
    desktop.write("hello world")
    desktop.press("Enter")

    # Launch an app
    desktop.launch("firefox", "https://news.ycombinator.com")
```

### Use with Claude Computer Use

```python
from anthropic import Anthropic
from e2b_desktop import Sandbox

desktop = Sandbox.create()

response = anthropic.beta.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=4096,
    tools=[
        {
            "type": "computer_20241022",
            "name": "computer",
            "display_width_px": desktop.width,
            "display_height_px": desktop.height,
        }
    ],
    messages=[{"role": "user", "content": "Find the top story on HN, screenshot it"}],
    extra_headers={"anthropic-beta": "computer-use-2024-10-22"},
)

# Each tool call from Claude — execute against desktop:
for content in response.content:
    if content.type == "tool_use" and content.input.get("action") == "screenshot":
        ss = desktop.screenshot()
        # ... return base64 to Claude
    elif content.input.get("action") == "left_click":
        x, y = content.input["coordinate"]
        desktop.left_click(x, y)
    # ... handle other actions
```

### Multi-tenant pattern

```python
# Each user gets their own sandbox
def get_user_desktop(user_id):
    sandbox = Sandbox.create(timeout=3600)
    sandbox.set_metadata("user_id", user_id)
    return sandbox

# Reconnect to a running sandbox by ID
sandbox = Sandbox.connect(sandbox_id)
```

Sessions persist across calls — useful for "agent did some work, returned to the user, now resumes" flows.

---

### FAQ

**Q: How is this different from Open Interpreter OS Mode?**
A: Open Interpreter OS Mode runs on YOUR machine — your screen, your keyboard. E2B Desktop runs in the cloud — agent gets an isolated cloud desktop, your machine is uninvolved. Use OS Mode for personal automation; E2B Desktop for production / multi-tenant SaaS.

**Q: Can I install custom apps in the desktop?**
A: Yes — E2B Desktops use Ubuntu under the hood. Run `desktop.commands.run('apt install --yes <package>')` or build a custom image with `e2b template build` for fast cold starts.

**Q: Does it support audio / video?**
A: VNC streams the visual desktop in real time. Audio is not yet supported; video apps work for visual-only output. For audio interactions, layer a separate audio pipeline.

---

## Source & Thanks

> Built by [E2B](https://github.com/e2b-dev). Licensed under Apache-2.0.
>
> [e2b-dev/desktop](https://github.com/e2b-dev/desktop) — ⭐ 1,500+

---

<!-- ZH -->

## 快速使用

1. `pip install e2b-desktop`
2. `Sandbox.create()` 返回一个桌面，`desktop.stream.get_url()` 拿 VNC URL
3. 用 `desktop.left_click(x, y)` / `desktop.write(...)` / `desktop.screenshot()` 驱动

---

## 简介

E2B Desktop 是托管的云 Linux 桌面 —— 完整 X11 环境、Firefox、终端、文件管理器 —— 通过 VNC 和 SDK 暴露。直接作为 Claude Computer Use 或 OpenAI CUA 的目标环境，不用本地搭 Docker / X11。适合用电脑的 AI agent 的生产部署、每个用户拿到独立桌面的多租户 SaaS。兼容 Python SDK / Claude Computer Use / 任何驱动屏幕+键盘+鼠标的 agent。装机时间 5 分钟。

---

### 起一个桌面 sandbox

```python
from e2b_desktop import Sandbox

with Sandbox.create() as desktop:
    # 拿实时 VNC URL（嵌 iframe 或用 VNC viewer 看）
    print(desktop.stream.get_url())

    # 截屏
    screenshot = desktop.screenshot()
    with open("screenshot.png", "wb") as f:
        f.write(screenshot)

    # 驱动鼠标 + 键盘
    desktop.left_click(500, 300)
    desktop.write("hello world")
    desktop.press("Enter")

    # 启动应用
    desktop.launch("firefox", "https://news.ycombinator.com")
```

### 配 Claude Computer Use

```python
from anthropic import Anthropic
from e2b_desktop import Sandbox

desktop = Sandbox.create()

response = anthropic.beta.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=4096,
    tools=[
        {
            "type": "computer_20241022",
            "name": "computer",
            "display_width_px": desktop.width,
            "display_height_px": desktop.height,
        }
    ],
    messages=[{"role": "user", "content": "Find the top story on HN, screenshot it"}],
    extra_headers={"anthropic-beta": "computer-use-2024-10-22"},
)

# Claude 每个 tool 调用 —— 在 desktop 上执行：
for content in response.content:
    if content.type == "tool_use" and content.input.get("action") == "screenshot":
        ss = desktop.screenshot()
        # …把 base64 返给 Claude
    elif content.input.get("action") == "left_click":
        x, y = content.input["coordinate"]
        desktop.left_click(x, y)
    # …处理其他动作
```

### 多租户模式

```python
# 每个用户独立 sandbox
def get_user_desktop(user_id):
    sandbox = Sandbox.create(timeout=3600)
    sandbox.set_metadata("user_id", user_id)
    return sandbox

# 通过 ID 重连到运行中的 sandbox
sandbox = Sandbox.connect(sandbox_id)
```

会话跨调用保留 —— 适合「agent 干了点活，返回给用户，现在恢复」这种流。

---

### FAQ

**Q: 跟 Open Interpreter OS Mode 啥区别？**
A: Open Interpreter OS Mode 跑在你的机器上 —— 你的屏幕、你的键盘。E2B Desktop 跑在云上 —— agent 拿到隔离的云桌面，你的机器不参与。OS Mode 适合个人自动化；E2B Desktop 适合生产 / 多租户 SaaS。

**Q: 能在桌面里装自定义应用吗？**
A: 能 —— E2B Desktop 底层是 Ubuntu。跑 `desktop.commands.run('apt install --yes <package>')`，或用 `e2b template build` 构建自定义镜像加速冷启动。

**Q: 支持音频 / 视频吗？**
A: VNC 实时流可视桌面。音频还没支持；视频应用可视输出能用。要音频交互就叠一条独立的音频管道。

---

## 来源与感谢

> Built by [E2B](https://github.com/e2b-dev). Licensed under Apache-2.0.
>
> [e2b-dev/desktop](https://github.com/e2b-dev/desktop) — ⭐ 1,500+


---
Source: https://tokrepo.com/en/workflows/e2b-desktop-headless-linux-desktop-for-ai-computer-use
Author: E2B