Local OCR for DeepSeek Harness
uknowmyface/locallens · model-adapters
Stays local: image files and screen captures are read by Vision in a local process and never uploaded.
★ 2GitHub stars
0Forks
2026-08-15Last updated
JavaScriptLanguage
MITLicense
Key features
- OCR output is untrusted input.
- ModLens and similar cloud-vision plugins provide genuine image understanding (scene description, layout reasoning, chart interpretation) that OCR cannot cover.
- The image never leaves your Mac.
Requirements
- macOS 13 (Ventura) or later.
- Below 13, recognitionLanguages is unavailable, the languages option is ignored, and Chinese accuracy degrades.
Install command
dsh plugin --profile web add github:uknowmyface/locallens