dsh-hos-scrcpy
Control a HarmonyOS phone from the DSH web UI with AI: live H.264 screen mirroring, mouse touch and system keys, hilog streaming, and agentic tools that let the model read the screen, locate UI controls, then tap, long-press, press keys, or type.
在 DSH 网页中用 AI 操控鸿蒙手机：实时 H.264 投屏、触控与系统按键、hilog 日志，并让模型读屏、定位 UI 控件，再执行点击/长按/按键/输入。
How to install
dsh plugin add github:ns-zzj/dsh-hos-scrcpy About
dsh-hos-scrcpy — DSH 鸿蒙投屏控制插件 开发手机软件时总在手机和电脑之间来回切换，太麻烦了。这个插件让你在 DeepSeek Harness 网页里**直接操作鸿蒙手机**： 实时投屏、鼠标触控、系统按键、hilog 日志，**AI 助手还能"看到"手机屏幕**——截屏识别、读页面、找按钮、看报错，开发调试不用再两头跑。 它能做什么 **电脑上操作手机**：网页内实时投屏鸿蒙（HarmonyOS NEXT）手机，鼠标点击/拖动即触摸，返回/主页/音量键一键可按，无需在手机和电脑屏幕之间切换 **AI 也能识别屏幕**：开启「允许截图」后，AI 可用 hos_scrcpy_screenshot 工具截取手机屏幕并识别画面内容（每次截图前二次确认），例如"当前页面是什么应用？界面上有哪些按钮？屏幕上显示了什么错误？" **截图入聊天框**：一键截取当前屏幕，像粘贴图片一样加进聊天输入框 **hilog 实时日志**：设备日志滚动查看（限速 60 行/秒，保留最近 500 行），排查问题不用开 DevEco 功能特性 | 功能 | 说明 | |---|---| | 设备发现 | USB / 局域网无线调试，hdc 已连接设备自动列出 | | 实时投屏 | H.264 视频流，网页播放（jmuxer.js） | | 触控操作 | 鼠标点击/拖动 = 手机触摸，坐标自动换…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 3
- mo. downloads
- –
- Last push
- 2026-09-24
- Created
- 2026-08-18
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, developer-tools, dsh-plugin, harmonyos, mirror, phone-control, scrcpy, screen-mirroring, vision
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-web
zhu1090093659/dsh-web-ui/tree/main/packages/dsh-tool-describe-image
A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.
dsh-vision-router
ysr666/dsh-vision-router
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.