A Meme Search Engine built to self-host in Python, Ruby, and Docker

Use AI to index your memes by their content and text, making them easily retrievable for your meme warfare pleasures.

By default, processing from image-to-text extraction, to vector embedding, to search is performed locally. You can also use an OpenAI-compatible vision API for description generation while keeping embeddings and search local.

Visit the Meme Search project site for a visual feature overview, or continue below for installation and configuration details.

Search beyond the web app. Meme Search now includes a documented, token-authenticated Search API v1, a dependency-free local CLI, and an experimental unpacked Chromium popup. The API is read-only and officially supported on loopback; it also gives community integrations a stable boundary that does not expose your database.

Watch the 16-second app-and-CLI demo.

This repository contains the services and web app for indexing, searching, and retrieving your memes with semantic and keyword search.

Quick start

git clone https://github.com/neonwatty/meme-search.git
cd meme-search
docker compose up

Open http://localhost:3000, then drag, drop, or paste images on the upload page. The first local description generation downloads the selected model, so it takes longer than later generations.

The web UI binds to 127.0.0.1 by default because it does not include user authentication. Official support is loopback-only for API v1 and the included clients. API bearer tokens protect only the versioned integration endpoints; they do not protect the web UI or settings. Direct public exposure is unsupported. Proxy/VPN operation is advanced and unsupported; its authentication, TLS, and network controls are entirely the operator's responsibility.

A table of contents for the remainder of this README:

• Meme search

  • Features
  • Requirements
  • Installation instructions
  • Time to first generation / downloading models
  • Index your memes
  • Search API and local integrations
  • Custom bind address and app port
  • Building the app locally with Docker
  • Running tests

• Discord server

• Changelog

• Feature requests and contributing

Requirements

For Docker deployment (recommended):

• Docker and Docker Compose

For local development:

• Ruby 3.4.2
• Rails 8.0.4
• Python 3.12
• Node.js 20 LTS
• PostgreSQL 17 with pgvector extension

We recommend using mise for managing Ruby, Python, and Node.js versions. See CLAUDE.md for detailed setup instructions.

Installation instructions

From the repository root, start the server cluster with Docker Compose:

docker compose up

This pulls and starts containers for the app, database, Solid Queue job worker, and local auto description generator. The app runs on port 3000 and is available locally at:

http://localhost:3000

The Compose files store app data in local bind-mounted directories so upgrades keep using the same files:

• ./meme_search/db_data/meme-search-db for Postgres data
• ./meme_search/direct-uploads for drag-and-drop uploads
• ./meme_search/db_data/image_to_text_generator for generator queue data
• ./meme_search/models for model