OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Search & Research AI

Memery

Memery is a Python application that searches local image folders using natural-language text and image queries, returning ranked results. It provides a browser GUI, command-line commands and a Python library, and uses CLIP for image-language search.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Memery — OpenViST project profile in Search & Research AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Memery when the images are in local folders and you want to search by visual description or a query image, rather than browsing thumbnails or relying on filenames.

Who it is for

  • People searching large local folders of memes, screenshots, product photos or inspiration images.
  • Python and shell users adding image search to an existing workflow.

Documented uses

  • Find an image by describing what it depicts rather than remembering its filename.
  • Search a folder using another image as a query.
  • Retrieve ranked image results from Python code or a command-line workflow.
Before you choose

Requirements & limits

The README lists Python 3.10, 3.11 and 3.12. The repository specifies the MIT license.

  • Memery offers three usage routes: browser GUI, command line and Python library.
  • The GUI is described as rough, and its directory field requires a path rather than a folder picker.
  • The README says performance is not yet optimized, despite describing use over thousands of images.
  • The documented installation defaults to GPU dependencies; a CPU-only PyTorch installation option is also provided.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run a local image search from the command line

Search an image folder using a text query and optionally an image query.

Before you start

  • Memery installed
  • A local image folder
  • A text query, an image-query file path, or both

Steps

  1. Run memery recall PATH/TO/IMAGE/FOLDER -t 'text_query' to search by text.

  2. Add -i 'PATH/TO/IMAGE.jpg' to include an image query, or use both query types.

  3. Use -n 20 to request 20 results; the documented default is 10.

Expected outcome

Memery returns image-search results for the specified folder and query.

Guide limitations

  • The guide follows the documented command syntax; it does not establish performance for a particular collection.
  • Image and text query paths must refer to local paths accessible to the command.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
deepfates/memery · Official homepage title · retained in its source language
How we review sourcesSuggest a correction