dsh-screen-reader
by cbg33695 · cbg33695/dsh-screen-reader
★ 0 Stars
⑂ 0 Forks
◎ 2 Open issues
Updated: Sep 12, 2026
MIT
JavaScript
Original language: English
About
Let a text-only model see the screen: capture desktop/window/region, vision transcription, a few minutes of rolling screen memory, exact local pixel diff, and vision self-calibration. Windows only. Experimental - the README states what is measured and what is not.
Similar plugins
Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and
★ 0
dsh plugin --profile web add dsh-omni-visionWindows-only computer use for DeepSeek Harness: captures the virtual screen and drives mouse & keyboard through 9 tools built on PowerShell and Win32 SendInput; pairs with picturereader so text-only m
★ 0
dsh plugin --profile web add computer-userby Altairpaca
Windows Computer Use for DeepSeek Harness (DSH): window-bound screenshot/OCR/click with verification loop, pure-OCR mode, pluggable vision models.
★ 3
MIT
PowerShell
Sep 3, 2026
dsh plugin --profile web add dsh-computer-use-windowsby PerryLink
Cross-platform native desktop control for DeepSeek Harness (Windows first): screen_shot, screen_read, click/type/scroll/key, app_list/app_launch - approval-gated, never stealing foreground focus
★ 7
↓ 687/wk
Apache-2.0
TypeScript
Sep 12, 2026
dsh plugin --profile web add dsh-clickDual-engine screen capture for DSH: inside the SSiD desktop shell, a global hotkey or tray opens a fullscreen box-select overlay (all monitors, per-display pixel-perfect frames) with in-place red-box
★ 0
↓ 299/wk
dsh plugin --profile web add @max-null/dsh-captureby ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command
★ 1.1k
↓ 8.7k/wk
MIT
JavaScript
Sep 13, 2026
dsh plugin --profile web add dsh-vision-router