OCR is much more feature complete.

distro-packages/Arch-Linux/PKGBUILD

@@ -31,7 +31,6 @@ depends=(
   python-dasbus
   
   # AI Assistant dependencies (for screenshots, HTTP requests, and actions)
-  python-pillow
   python-requests
   python-pyautogui
   
@@ -58,6 +57,12 @@ optdepends=(
   'openai-codex: ChatGPT AI provider support' 
   'gemini-cli: Gemini AI provider support'
   'ollama: Local AI model support'
+  
+  # OCR plugin dependencies (optional)
+  'python-pillow: Image processing for OCR and AI Assistant'
+  'python-pytesseract: Python wrapper for Tesseract OCR engine'
+  'tesseract: OCR engine for text recognition'
+  'tesseract-data-eng: English language data for Tesseract'
 )
 makedepends=(
   git