# Open Interpreter OS Mode — Natural-Language Computer Control

> Open Interpreter OS Mode adds full computer control via screenshots + clicks. Drives any GUI app — terminal, browser, Photoshop — with natural language.

## Install

Save as a script file and run:

## Quick Use

1. `pip install open-interpreter`
2. `interpreter --os` (the OS-control flag)
3. Type natural-language commands; confirm prompts before destructive ops

---

## Intro

Open Interpreter's OS Mode extends the natural-language CLI into full computer control. The agent takes screenshots, sees the screen, and drives any GUI app via clicks, keystrokes, and shell commands. Best for: research / experimentation / one-off automation that touches GUI apps you can't script (Photoshop, Excel macros, Zoom, third-party desktop tools). Works with: macOS, Windows, Linux. Setup time: 5 minutes.

---

### Install + start

```bash
pip install open-interpreter
interpreter --os
```

The first run prompts for your LLM API key (OpenAI default; use `--model claude-3-5-sonnet-20241022` for Claude).

### Sample session

```
> Open Photoshop, create a new 1200x630 document, fill it with a navy-to-orange
  gradient, and add the text "Q3 Report" centered in white.

[OS Mode takes a screenshot, identifies the dock, clicks Photoshop]
[Wait for app launch...]
[Clicks File > New, types dimensions, creates document]
[Selects gradient tool, picks colors, drags from top-left to bottom-right]
[Adds text layer, types "Q3 Report", aligns center]
> Done. Want me to save the file?
```

### Safety prompts

OS Mode asks for confirmation before destructive actions:

```
About to: Empty Trash (irreversible). Confirm? [y/N]
```

You can preset auto-approve for whitelisted tools:

```bash
interpreter --os --auto_run --safe_mode high
```

`safe_mode high` rejects file deletion, network calls to unknown hosts, and shell commands containing `rm`, `dd`, etc.

### When NOT to use OS Mode

- Production automation — use Browser Use (browser only) or platform APIs instead
- Time-critical work — OS Mode latency is ~5-15s per click
- Anything sensitive — the screenshots leave your machine to the LLM

OS Mode shines for one-off, exploratory, "I'd rather describe this than learn the GUI" tasks.

---

### FAQ

**Q: Is Open Interpreter free?**
A: Yes — Apache-2.0 open-source. You bring your own LLM API key (OpenAI / Anthropic / local). Inference cost depends on the model and how visual the task is (vision-capable models are more expensive).

**Q: How does this differ from Browser Use?**
A: Browser Use is browser-only (clicks inside Chrome). OS Mode is whole-OS (any GUI app, terminal, dock). Use Browser Use for web scraping; OS Mode for desktop-app automation. Different latency and reliability profiles.

**Q: Will it work on a remote server?**
A: Limited — OS Mode needs a screen and input devices. For headless / server contexts, use Open Interpreter's standard mode (no `--os`) which is shell-only and works on any Linux box.

---

## Source & Thanks

> Built by [Open Interpreter](https://github.com/OpenInterpreter). Licensed under Apache-2.0.
>
> [OpenInterpreter/open-interpreter](https://github.com/OpenInterpreter/open-interpreter) — ⭐ 60,000+

---

<!-- ZH -->

## 快速使用

1. `pip install open-interpreter`
2. `interpreter --os`（OS 控制 flag）
3. 输入自然语言指令；破坏性操作前确认

---

## 简介

Open Interpreter 的 OS Mode 把自然语言 CLI 扩展成完整的电脑控制。agent 截屏看屏幕、用点击、键盘、shell 命令驱动任何 GUI 应用。适合接触你写不了脚本的 GUI 应用（Photoshop、Excel 宏、Zoom、第三方桌面工具）的研究 / 实验 / 一次性自动化。兼容 macOS / Windows / Linux。装机时间 5 分钟。

---

### 装 + 启动

```bash
pip install open-interpreter
interpreter --os
```

首次运行要你的 LLM API key（默认 OpenAI；用 `--model claude-3-5-sonnet-20241022` 接 Claude）。

### 示例会话

```
> Open Photoshop, create a new 1200x630 document, fill it with a navy-to-orange
  gradient, and add the text "Q3 Report" centered in white.

[OS Mode 截屏，识别 Dock，点 Photoshop]
[等应用启动…]
[点 File > New，输入尺寸，创建文档]
[选渐变工具，挑颜色，从左上拖到右下]
[加文字图层，输入 "Q3 Report"，居中对齐]
> Done. Want me to save the file?
```

### 安全提示

OS Mode 在破坏性动作前会请求确认：

```
About to: Empty Trash (irreversible). Confirm? [y/N]
```

可以预设白名单工具自动批准：

```bash
interpreter --os --auto_run --safe_mode high
```

`safe_mode high` 拒绝文件删除、对未知主机的网络请求、含 `rm` / `dd` 的 shell 命令。

### 什么时候不该用 OS Mode

- 生产自动化 —— 用 Browser Use（仅浏览器）或平台 API
- 时间敏感 —— OS Mode 每次点击约 5-15s 延迟
- 任何敏感内容 —— 截屏会离开你的机器到 LLM

OS Mode 适合一次性、探索性、「我宁愿描述也不想学 GUI」的任务。

---

### FAQ

**Q: Open Interpreter 免费吗？**
A: 免费 —— Apache-2.0 开源。用自己的 LLM API key（OpenAI / Anthropic / 本地）。推理成本看模型和任务视觉密度（视觉模型更贵）。

**Q: 跟 Browser Use 啥区别？**
A: Browser Use 只在浏览器里（Chrome 内点击）。OS Mode 是全 OS（任何 GUI app、终端、Dock）。爬网用 Browser Use；桌面应用自动化用 OS Mode。延迟和可靠性都不一样。

**Q: 远程服务器能用吗？**
A: 受限 —— OS Mode 需要屏幕和输入设备。无头 / 服务器场景用 Open Interpreter 标准模式（不加 `--os`），shell-only，任何 Linux 机器都能跑。

---

## 来源与感谢

> Built by [Open Interpreter](https://github.com/OpenInterpreter). Licensed under Apache-2.0.
>
> [OpenInterpreter/open-interpreter](https://github.com/OpenInterpreter/open-interpreter) — ⭐ 60,000+


---
Source: https://tokrepo.com/en/workflows/open-interpreter-os-mode-natural-language-computer-control
Author: Open Interpreter