<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet href="/rss.xsl" type="text/xsl"?><rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>视觉 | 折腾啥</title><description>Power Users/Automators 折腾/讨论/分享各种开源工具/脚本/自动化工作流👥 @zhetengsha_group📌 合集 https://t.me/zhetengsha/2🎁 恰饭 https://t.me/zhetengsha/957📢 广告投放 @xream @xream_botBuy ads: https://telega.io/c/zhetengshafeedId:55438372655431680+userId:62307599601855488</description><link>http://telegram.zhetengsha.eu.org</link><item><title>auge: 本地视觉工具，一键 OCR 与图像分析• 支持 OCR、图像分类、条码与人脸检测，全部在 macOS 本地运行  • 完全零网络、零 API Key，直接通过终端调用，适配管道与脚本  • Homebrew 一键安装，Swift 代码轻量编译，兼容 macOS 10.15+  </title><link>http://telegram.zhetengsha.eu.org/posts/5835</link><guid isPermaLink="true">http://telegram.zhetengsha.eu.org/posts/5835</guid><pubDate>Sun, 31 May 2026 11:05:13 GMT</pubDate><content:encoded>&lt;div class=&quot;image-list-container image-list-odd&quot;&gt;
      &lt;button type=&quot;button&quot; class=&quot;image-preview-button image-preview-wrap&quot; popovertarget=&quot;modal-5835-0&quot; popovertargetaction=&quot;show&quot; aria-label=&quot;Open image preview: auge: 本地视觉工具，一键 OCR 与图像分析• 支持 OCR、图像分类、条码与人脸检测，全部在 macOS 本地运行  • 完全零网络、零 API Key，直接通过终端调用，适配管道与脚本  • Homebrew 一键安装，Swift 代码轻量编译，兼容 macOS 10.15+  &quot;&gt;
        &lt;img src=&quot;/static/https://cdn5.telesco.pe/file/oLofkIi1K1F2gnYhTwO_C90jh6N9Rddwl3EnMECVzXL70FStHCCMWzoR5RwJhpRjtFf8Nb5l37nptoOEH2YiCvaHdM_42DvbglO8xxSaeDm_Mg5ueqLg-49D6xZHeMwtWEK7jm8l510O6Spihw2-B1-SpbJLMNid_w3heTiBfGiI4Z-2Lzt1ZJ7RUnWgtkuAB5BIv61oTb46Jwl7T6FVJQdFfSZQtL_yxmRA3wuDQhnlao6_aOnpfeEbHwum1ML6gBfVx4NFqaDqzDih41gfQANwZf80Au9M32OBQLEIE018MeyqYuXrBLTrQeWSSqMdX1TR2o888K-yyWHK1rMS2Q.jpg&quot; alt=&quot;auge: 本地视觉工具，一键 OCR 与图像分析• 支持 OCR、图像分类、条码与人脸检测，全部在 macOS 本地运行  • 完全零网络、零 API Key，直接通过终端调用，适配管道与脚本  • Homebrew 一键安装，Swift 代码轻量编译，兼容 macOS 10.15+  &quot; width=&quot;800&quot; height=&quot;535&quot; loading=&quot;eager&quot; /&gt;
      &lt;/button&gt;
      &lt;div class=&quot;modal&quot; id=&quot;modal-5835-0&quot; popover=&quot;auto&quot; aria-label=&quot;Image preview&quot;&gt;
        &lt;button type=&quot;button&quot; class=&quot;modal__backdrop&quot; popovertarget=&quot;modal-5835-0&quot; popovertargetaction=&quot;hide&quot; aria-label=&quot;Close image preview&quot;&gt;&lt;/button&gt;
        &lt;button type=&quot;button&quot; class=&quot;modal__close&quot; popovertarget=&quot;modal-5835-0&quot; popovertargetaction=&quot;hide&quot; aria-label=&quot;Close image preview&quot;&gt;×&lt;/button&gt;
        &lt;div class=&quot;modal__surface&quot;&gt;
          
        &lt;/div&gt;
      &lt;/div&gt;
    &lt;/div&gt;&lt;u&gt;auge: 本地视觉工具，一键 OCR 与图像分析&lt;/u&gt;&lt;br /&gt;&lt;br /&gt;• 支持 OCR、图像分类、条码与人脸检测，全部在 macOS 本地运行  &lt;br /&gt;&lt;br /&gt;• 完全零网络、零 API Key，直接通过终端调用，适配管道与脚本  &lt;br /&gt;&lt;br /&gt;• Homebrew 一键安装，Swift 代码轻量编译，兼容 macOS 10.15+  &lt;br /&gt;&lt;br /&gt;&lt;a href=&quot;https://github.com/Arthur-Ficial/auge&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot; title=&quot;https://github.com/Arthur-Ficial/auge&quot;&gt;https://github.com/Arthur-Ficial/auge&lt;/a&gt;  &lt;br /&gt;&lt;br /&gt;&lt;img class=&quot;tg-emoji&quot; src=&quot;/static/https://telegram.me/i/emoji/6327880277607583303.webp&quot; alt=&quot;&quot; loading=&quot;lazy&quot; width=&quot;20&quot; height=&quot;20&quot; /&gt; &lt;a href=&quot;https://t.me/zhetengsha/2&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot; title=&quot;合集&quot;&gt;合集&lt;/a&gt; &lt;img class=&quot;tg-emoji&quot; src=&quot;/static/https://telegram.me/i/emoji/6021860481923288796.webp&quot; alt=&quot;&quot; loading=&quot;lazy&quot; width=&quot;20&quot; height=&quot;20&quot; /&gt; &lt;a href=&quot;https://t.me/zhetengsha_group&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot; title=&quot;群组&quot;&gt;群组&lt;/a&gt; &lt;img class=&quot;tg-emoji&quot; src=&quot;/static/https://telegram.me/i/emoji/6327792445526380187.webp&quot; alt=&quot;&quot; loading=&quot;lazy&quot; width=&quot;20&quot; height=&quot;20&quot; /&gt; &lt;a href=&quot;https://t.me/zhetengsha/957&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot; title=&quot;恰饭&quot;&gt;恰饭&lt;/a&gt; &lt;img class=&quot;tg-emoji&quot; src=&quot;/static/https://telegram.me/i/emoji/6330367862535884142.webp&quot; alt=&quot;&quot; loading=&quot;lazy&quot; width=&quot;20&quot; height=&quot;20&quot; /&gt;&lt;a href=&quot;https://t.me/xream_bot&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot; title=&quot;联系推广&quot;&gt;联系推广&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;&lt;img class=&quot;tg-emoji&quot; src=&quot;/static/https://telegram.me/i/emoji/6327836885552991740.webp&quot; alt=&quot;&quot; loading=&quot;lazy&quot; width=&quot;20&quot; height=&quot;20&quot; /&gt;&lt;a href=&quot;/search/result?q=%23%E8%A7%86%E8%A7%89&quot; title=&quot;#视觉&quot;&gt;#视觉&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23OCR&quot; title=&quot;#OCR&quot;&gt;#OCR&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23macOS&quot; title=&quot;#macOS&quot;&gt;#macOS&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23CLI&quot; title=&quot;#CLI&quot;&gt;#CLI&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23AppleVision&quot; title=&quot;#AppleVision&quot;&gt;#AppleVision&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23%E5%BC%80%E6%BA%90&quot; title=&quot;#开源&quot;&gt;#开源&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23GitHub&quot; title=&quot;#GitHub&quot;&gt;#GitHub&lt;/a&gt;</content:encoded></item><item><title>Midscene.js: 视觉模型驱动的全平台 UI 自动化 SDK• 基于 pure-vision 路线进行 UI 定位与交互，仅依赖截图即可覆盖 Web、Android、iOS、桌面应用与 Canvas 场景  • 支持自然语言编排任务，可使用 Javascript SDK 或 YAML 编写脚本，并无缝集成 Puppeteer、Playwright、adb、WebDriverAgent  • 提供可视化报告、Playground 与 MCP 能力，便于调试回放、提升执行效率，并支持开源模型自托管</title><link>http://telegram.zhetengsha.eu.org/posts/4935</link><guid isPermaLink="true">http://telegram.zhetengsha.eu.org/posts/4935</guid><pubDate>Sat, 28 Feb 2026 10:03:02 GMT</pubDate><content:encoded>&lt;u&gt;Midscene.js: 视觉模型驱动的全平台 UI 自动化 SDK&lt;/u&gt;&lt;br /&gt;&lt;br /&gt;• 基于 pure-vision 路线进行 UI 定位与交互，仅依赖截图即可覆盖 Web、Android、iOS、桌面应用与 Canvas 场景  &lt;br /&gt;• 支持自然语言编排任务，可使用 Javascript SDK 或 YAML 编写脚本，并无缝集成 Puppeteer、Playwright、adb、WebDriverAgent  &lt;br /&gt;• 提供可视化报告、Playground 与 MCP 能力，便于调试回放、提升执行效率，并支持开源模型自托管&lt;br /&gt;&lt;br /&gt;&lt;a href=&quot;https://github.com/web-infra-dev/midscene&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot; title=&quot;https://github.com/web-infra-dev/midscene&quot;&gt;https://github.com/web-infra-dev/midscene&lt;/a&gt;&lt;br /&gt;&lt;br /&gt;&lt;a href=&quot;/search/result?q=%23%E8%87%AA%E5%8A%A8%E5%8C%96%E6%B5%8B%E8%AF%95&quot; title=&quot;#自动化测试&quot;&gt;#自动化测试&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23%E8%A7%86%E8%A7%89%E8%AF%AD%E8%A8%80%E6%A8%A1%E5%9E%8B&quot; title=&quot;#视觉语言模型&quot;&gt;#视觉语言模型&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23%E8%B7%A8%E5%B9%B3%E5%8F%B0&quot; title=&quot;#跨平台&quot;&gt;#跨平台&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23UI&quot; title=&quot;#UI&quot;&gt;#UI&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23JavaScript&quot; title=&quot;#JavaScript&quot;&gt;#JavaScript&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23GitHub&quot; title=&quot;#GitHub&quot;&gt;#GitHub&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23MCP&quot; title=&quot;#MCP&quot;&gt;#MCP&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23Android&quot; title=&quot;#Android&quot;&gt;#Android&lt;/a&gt; &lt;a href=&quot;/search/result?q=%23iOS&quot; title=&quot;#iOS&quot;&gt;#iOS&lt;/a&gt;&lt;a class=&quot;tgme_widget_message_link_preview&quot; href=&quot;https://github.com/web-infra-dev/midscene&quot; target=&quot;_blank&quot; rel=&quot;noopener&quot; title=&quot;AI-powered, vision-driven UI automation for every platform. - web-infra-dev/midscene&quot;&gt;
  
  &lt;div class=&quot;link_preview_site_name accent_color&quot;&gt;GitHub&lt;/div&gt;
  &lt;img class=&quot;link_preview_image&quot; alt=&quot;GitHub - web-infra-dev/midscene: AI-powered, vision-driven UI automation for every platform.&quot; src=&quot;/static/https://cdn4.telesco.pe/file/vtjLtFbhoe5Ut34X0WLJaLgZMAME1-mTCoLUrGqL12cy-J0VBa445l5gDngcubr12-GV_MA31j9fpqIfas1cRFFCBGtHNo2VQ0G4SmZqrGjtT3_3g52rKPsx7393L2oRzx1UYOblPJ-AjOklZ9m4FAjkcVA-D_CK-8gnCHNDt0URzwJrAjVCTsintGDOUfy5Yp1G7Ao-gH0lHA65RaqIpjlMMyXzWF0ADS-mqtLnbSKWCWTuWGsTxyo4BRPgSeArTl7KVa4lG1jPH5fK9gM3BdD4_f0aGbrjPMOq9u3ooUEUyqYBtUtOICyb_qAqW12zTfH9W9RL44rCAL89ohuucA.jpg&quot; width=&quot;1200&quot; height=&quot;630&quot; loading=&quot;eager&quot; /&gt;
  &lt;div class=&quot;link_preview_title&quot;&gt;GitHub - web-infra-dev/midscene: AI-powered, vision-driven UI automation for every platform.&lt;/div&gt;
  &lt;div class=&quot;link_preview_description&quot;&gt;AI-powered, vision-driven UI automation for every platform. - web-infra-dev/midscene&lt;/div&gt;
&lt;/a&gt;</content:encoded></item></channel></rss>