yurijmikhalevich/rclip

grep for images – local, offline image search for the terminal

What it solves

rclip is a command-line tool that allows you to search through local image folders using natural language descriptions, example images, or a combination of both. It eliminates the need for manual tagging, uploading files to cloud services, or importing images into a specialized photo library to make them searchable.

How it works

The tool uses the OpenCLIP ViT-B/32 AI model to generate embeddings for both images and text. By converting images and search queries into a shared mathematical space, it can find images that match a text description or are visually similar to another image entirely offline on your own machine.

Who it’s for

It is designed for users who are comfortable with the terminal and prefer local, private AI tools. It is particularly useful for photographers or anyone with large local image collections on Linux, macOS, or Windows who want a fast, grep-like search experience for their photos.

Highlights

  • Multi-modal Search: Search using text, images (via local path or URL), or arithmetic combinations (e.g., adding or subtracting concepts).
  • Local & Private: All processing happens offline; photos never leave the computer.
  • Terminal-native UI: Includes an interactive thumbnail grid and inline image previews for terminals supporting Kitty graphics.
  • Fast Indexing: Uses incremental indexing to only process new or changed images on subsequent runs.
  • Broad Format Support: Supports standard formats like JPG, PNG, and WebP, with native HEIC support on macOS/Windows and experimental RAW support.
  • Unix-friendly: Can be piped into other command-line tools for tasks like copying matching images to a new folder.

Related

  • Project
    julyx10/lap

    Lap is an open‑source, cross‑platform desktop photo manager that keeps all your images on your own disk. It offers folder‑first organization, local AI search (text‑prompt, similarity, face clustering) via ONNX Runtime, bulk editing, collage creation, and support for 60+ image, RAW and video formats. Built with Tauri + Rust, Vue, and SQLite, it runs on macOS, Windows and Linux and is released under GPL‑3.0.

  • Project
    chn-lee-yumi/MaterialSearch

    A natural language search tool for local photos and videos that enables text-based and image-based retrieval of visual assets.

  • Project
    greyovo/PicQuery

    PicQuery is an offline image search application that uses on-device AI models to let you find photos in your local library using text queries or image similarity.

  • Dispatch
    Image search with Hugging Face datasets

    Hugging Face demonstrates how to build an image search application by combining the datasets library, CLIP embeddings, and FAISS for efficient similarity search.

  • Project
    xushengfeng/eSearch

    A cross-platform screen search tool that integrates screenshotting, offline OCR, translation, and reverse image search to extract and act on screen information.