GUI agent plugin for DeepSeek Harness
xiaozhengdeng/dsh_omnivision · model-adapters
GUI agent plugin for DeepSeek Harness: OmniParser screen recognition, desktop automation, and an OmniVision vision dock.
★ 2GitHub stars
0Forks
2026-08-25Last updated
TypeScriptLanguage
MITLicense
Key features
- Screen recognitionCapture the desktop (or parse an image) and get interactive elements with pixel coordinates via OmniParser
- OmniVision — OmniParser-powered GUI agent plugin for DeepSeek Harness
- OmniVision is an OmniParser-powered GUI agent plugin for DeepSeek Harness.
- gui_capture — capture the desktop screen and run OmniParser to extract interactive elements (text + icons with pixel coordinates), refreshing the shared vision state and saving the SOM-annotated overlay
- Desktop automationClick, double-click, right-click, drag, type (unicode-safe), key, hotkey, scroll — by element id or raw x/y
Requirements
- Windows with an OmniParser FastAPI server on (e.g.
Install command
dsh plugin --profile web add github:xiaozhengdeng/dsh_omnivision