Record important information to long-term memory for learning user preferences, successful patterns, and error lessons. When you need to remember user preferences, save successful patterns, or record lessons from errors.
中文简介正在准备中。当前显示原文说明。
Control desktop software (GIMP, Blender, LibreOffice, etc.) through CLI-Anything generated command-line interfaces. Calls real application backends — much more reliable than GUI automation via desktop_* tools.
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
通过 CLI-Anything 生成的 CLI 接口控制桌面软件。 直接调用软件后端 API,比 pyautogui/UIA 的 GUI 自动化可靠得多。
--json 和 --help 标准支持| 场景 | 推荐工具 | 原因 |
|---|---|---|
| 操作有 CLI 的桌面软件 | cli_anything_run | 确定性,JSON 输出 |
| 无 CLI 的桌面软件 | desktop_* 工具 | 降级到 GUI 自动化 |
| 查看可用工具 | cli_anything_discover | 扫描 PATH |
| 了解命令参数 | cli_anything_help | 获取 --help 文档 |
cli_anything_discover()
cli_anything_run(app="gimp", subcommand="image resize", args=["--width", "800", "input.png"])
cli_anything_run(app="libreoffice", subcommand="document export-pdf", args=["report.docx"])
cli_anything_help(app="gimp")
cli_anything_help(app="gimp", subcommand="image resize")
# 从 CLI-Hub 安装已有的 CLI
pip install cli-anything-gimp
pip install cli-anything-blender
pip install cli-anything-libreoffice
# 为新软件生成 CLI(需要 Claude Code)
/cli-anything ./your-software
CLI-Anything 社区已支持 9+ 软件:
需要控制桌面软件?
├─ 有 cli-anything CLI → cli_anything_run(首选)
├─ 无 CLI + Windows → desktop_* 工具(GUI 自动化)
└─ 无 CLI + 非 Windows → run_shell 尝试命令行工具
desktop_click / desktop_type — 无 CLI 时的降级 GUI 方案run_shell — 直接执行命令行还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Record important information to long-term memory for learning user preferences, successful patterns, and error lessons. When you need to remember user preferences, save successful patterns, or record lessons from errors.
中文简介正在准备中。当前显示原文说明。
Click page elements by CSS selector or text content. When you need to click buttons, links, or select options. PREREQUISITE - must use browser_navigate to open target page first.
中文简介正在准备中。当前显示原文说明。
Extract page content and element text from current webpage. When you need to read page information, get element values, scrape data, or verify page content.
中文简介正在准备中。当前显示原文说明。
List all open browser tabs with their index, URL and title. When you need to check what pages are open, manage multiple tabs, or find a specific tab to switch to.
中文简介正在准备中。当前显示原文说明。
Navigate browser to specified URL to open a webpage. When you need to open webpages or start web automation. PREREQUISITE - must call before browser_click/type operations. Auto-starts browser if not running.
中文简介正在准备中。当前显示原文说明。
Open new browser tab and navigate to URL (keeps current page open). When you need to open additional page without closing current, or multi-task across pages. PREREQUISITE - must confirm browser is running first.
中文简介正在准备中。当前显示原文说明。