Computer Use (Claude 3.5 Sonnet)Anthropic 的 API 功能，允许 Claude 控制桌面以自动化屏幕任务。

4.5 (6)

审阅者 Daniel Nikulshyn·更新 2026年7月

API Developer Tools AI Agents Automation Experimental Desktop Automation LLM

概览

Computer Use 是 Claude 3.5 Sonnet 提供的一项功能，允许模型与计算机交互，就像人类一样。通过 Anthropic API，Claude 可以查看屏幕截图、移动光标、点击按钮、输入文本和导航应用程序，使其能够在缺乏专用 API 的软件上执行多步骤任务。该功能面向正在为表单填写、数据提取、质量保证测试和例行桌面自动化等工作流构建代理的开发人员。由于该功能仍在成熟中，Anthropic 将其定位为实验性功能，并建议在具有人为监督的沙盒虚拟环境中运行。

主要功能

基于截图的屏幕理解
通过 API 进行鼠标和键盘控制
多步骤任务规划和执行
与 Claude 3.5 Sonnet 推理集成
在虚拟机或容器内工作
面向开发者的工具使用框架

价格

模型: Freemium
分类: Task automation
评分: 4.5 / 5 (6)

使用场景

跨旧应用的自动表单填写

开发人员可以构建代理，读取屏幕表单并将数据输入到缺乏 API 的桌面或 Web 应用程序中，减少手动数据录入工作。

基于 GUI 的 QA 测试

使用 Claude 导航应用程序界面，点击用户流程，并验证预期行为，从而对没有脚本测试钩子的软件进行探索性 QA。

跨应用程序数据提取

代理可以打开多个程序，捕获屏幕截图，并从仪表板或旧系统中提取结构化数据到统一输出。

例行桌面工作流程自动化

在沙盒虚拟机中自动执行重复的多步骤任务，如报告生成或文件组织，并由人工监督以确保安全。

优点 & 缺点

优点

在应用程序之间自动执行任务，无需自定义集成
与现有的 GUI 和旧软件配合使用
以 Claude 3.5 Sonnet 的推理能力为后盾
用于构建自定义代理的灵活 API

缺点

实验性，复杂任务容易出错
比专用自动化脚本慢
需要沙盒环境以确保安全
需要开发人员设置；不是最终用户应用程序

评测

4.5

6 个评分的平均值。

登录以留下评测。

Beatriz Costa

Dec 5, 2025

Use it every day

Honestly didn't expect to like it this much. Mouse and keyboard control via API is exactly what I needed, and works with existing GUIs and legacy software. I do wish requires sandboxing for safety, but I reach for it almost every day now and it just clicks.

Leila Hassan

Nov 2, 2025

Use it every day

Honestly didn't expect to like it this much. Screenshot-based screen understanding is exactly what I needed, and backed by Claude 3.5 Sonnet's reasoning ability. but I reach for it almost every day now and it just clicks.

Pierre Dubois

Oct 14, 2025

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on mouse and keyboard control via API, and flexible API for building custom agents caught me off guard. Developer setup needed; not an end-user app is why this isn't a perfect score, still, I'd recommend giving it a real trial.

Elena Rossi

Aug 21, 2025

Use it every day

Honestly didn't expect to like it this much. Screenshot-based screen understanding is exactly what I needed, and works with existing GUIs and legacy software. I do wish slower than purpose-built automation scripts, but I reach for it almost every day now and it just clicks.

Frank Müller

Jun 20, 2025

Compared a few options

Evaluated this against two competitors. Where it wins: multi-step task planning and execution and flexible API for building custom agents. Where it lags: slower than purpose-built automation scripts. On balance the feature set — especially tool-use framework for developers — justifies the 4 stars for our use case.

Victor Nguyen

Jun 1, 2025

Use it every day

Honestly didn't expect to like it this much. Screenshot-based screen understanding is exactly what I needed, and automates tasks across apps without custom integrations. I do wish requires sandboxing for safety, but I reach for it almost every day now and it just clicks.