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

Meme Search

Meme Search is a self-hosted application that indexes memes by extracting image text and descriptions, generating vector embeddings, and retrieving matches through semantic and keyword search. Its default processing path is local; an OpenAI-compatible vision API can optionally generate descriptions while embeddings and search remain local.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Meme Search — 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 Meme Search when you want a self-hosted index for a meme collection and prefer local image processing and search, with an optional external service for description generation.

Who it is for

  • People who want to search a self-managed meme collection by visual content or text.
  • Operators comfortable running a local application with Docker Compose.

Documented uses

  • Add images to a local meme library through the web upload page.
  • Create searchable image descriptions and vector embeddings.
  • Retrieve memes using semantic or keyword queries.
  • Use an optional compatible vision API for description generation while keeping embeddings and search local.
Before you choose

Requirements & limits

Docker Compose is the recommended deployment route and requires Docker and Docker Compose. The web UI is unauthenticated and binds to 127.0.0.1 by default; direct public exposure is unsupported.

  • The default image-description, embedding and search pipeline runs locally; the first local generation downloads the selected model.
  • Florence-2-base is the default image-to-text model, and the README lists other model options of different sizes.
  • The optional OpenAI-compatible vision API is for description generation; embeddings and search remain local.
  • Local development requires Ruby 3.4.2, Rails 8.0.4, Python 3.12, Node.js 20 LTS, and PostgreSQL 17 with pgvector.
  • The web UI has no user authentication. API bearer tokens protect versioned integration endpoints, not the UI or settings.

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

Start Meme Search with Docker Compose

Launch the local web app and reach its upload page.

Before you start

  • Docker
  • Docker Compose

Steps

  1. Clone the meme-search/meme-search repository and enter the repository directory.

  2. Run docker compose up.

  3. Open http://localhost:3000 in a browser.

Expected outcome

The web app is available locally, with an upload page for adding images.

Guide limitations

  • The first local description generation downloads the selected model and takes longer than later generations.
  • The web UI binds to 127.0.0.1 by default and has no user authentication; direct public exposure is unsupported.
Documentation 1 ↗
Evidence and transparency

Sources & review

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