Meme Search

Meme Search is a free, self-hosted web app for people who want to find memes in their own collection by image content or text. It runs locally through Docker and uses AI descriptions to make images searchable, even when their filenames aren't useful. The code uses the Apache 2.0 license.

You can search by meaning or by keyword, then filter results by tags or directory. The collection can span multiple folders. Automatic descriptions work on selected images or in bulk, and you can edit them manually when the model misses a joke or context. Directory rescans pick up added files; browser uploads accept drag-and-drop and clipboard images.

Local description models include Florence-2-base, the default, along with Florence-2-large, SmolVLM-256, SmolVLM-500 and Moondream2. Moondream2-INT8 provides a lower-memory choice for CPU-only machines. Models download on first use and stay cached locally.

By default, image-to-text processing, embeddings and search all stay on your machine. An optional OpenAI-compatible vision API can generate descriptions instead. That mode sends selected images to the configured endpoint while metadata, embeddings and search remain local.

A read-only, token-authenticated search API and a Python CLI let other local tools search the collection and retrieve media. The app is intended for access on the same machine: its web interface has no user authentication, and direct public exposure isn't supported. JPG, PNG, WEBP and GIF files are supported; GIFs play in results, but indexing uses their first frame.