secretxuan/dsh-computer-use-win

secretxuan★ 0TypeScript最后同步: 2026-08-21

在 GitHub 打开

Native-vision Windows computer-use for DeepSeek Harness: screenshots, UIA, OCR, and approval-gated input

README 摘要

dsh-computer-use-win 中文 English Windows computer-use bundle for DeepSeek Harness (dsh): screenshots, window and UI Automation element discovery, OCR/visual observation for text-only models, mouse/keyboard control, and direct Windows Settings launch. With DSH 0.1.1-rc.2 or newer, the built-in deepseek-v4-flash-vision-exp route receives computer screenshot captures as native image content. DSH normalizes each screenshot to the route's pixel and byte budget, then uses the DeepSeek Files API with an inline fallback. Text-only routes keep the OCR-compatible saved-file flow. The macOS-first sibling is Anionex/dsh-computer-use; this plugin fills the Windows gap. What It Adds Tool Purpose computer screenshot Capture the full screen or a specific window. Vision-capable routes receive an image; text-only routes receive a saved PNG path. computer list windows List visible top-level windows with process, pid, title, screen rectangle, and active state. computer list elements Search controls exposed through Windows UI Automation and return names, types, physical-pixel rectangles, click=(x,y) centers, and diagnostics when UIA cannot see inside custom UI. computer ocr image Run Windows OCR on an e…

在 GitHub 查看完整 README →
内容/媒体automationcomputer-usedeepseek-harnessdeepseek-v4dsh-pluginmultimodalocroh-my-dsh

分类