AI Agent Hub
Back to plugins
locallens preview

locallens

Model Inference Updated 2026.08.15

Run the following command in DeepSeek Harness:

dsh plugin install uknowmyface/locallens

Paste the following prompt into your AI chat to install this plugin:

Please run the installation command `dsh plugin install uknowmyface/locallens` in DeepSeek Harness, with the source code at https://github.com/uknowmyface/locallens.

About this plugin

Traditional vision models, while powerful, often require uploading images to the cloud, raising privacy concerns and potentially incurring API costs. For users who simply need to extract text from screenshots or images, these solutions often feel overly complex and indirect.

LocalLens leverages macOS's built-in Vision framework to provide a purely local OCR solution. It does not rely on external vision models, API keys, or network connections; image processing happens entirely on your Mac. Whether from clipboard captures, desktop image files, or screen content, it quickly and accurately extracts the text contained within.

This plugin is ideal for macOS users who prioritize data privacy and seek fast, on-device processing. It is the perfect choice for those who want to treat the vision model as a "reading tool" rather than an "understanding tool." By seamlessly injecting recognized text into the conversation context, LocalLens allows agents to easily handle document scans, UI text, or screenshot information, ensuring your sensitive data never leaves your local machine.

Screenshots

Use Cases

  • Quickly extract text from screenshots
  • OCR images from clipboard and extract text
  • Recognize readable text in desktop or document images

Best For

  • Users who need to process documents or screenshots but refuse to upload data
  • Developers using macOS and relying on DeepSeek Harness
  • AI Agent users who prioritize privacy and want local visual processing