Analysis updated 2026-05-18
Automatically sort a large, messy folder of memes into organized subfolders.
Rename image files descriptively based on what is actually in the picture.
Find and review exact duplicate images in a meme collection without using AI.
| whp199/memedrawer | 100/awesome-machine-learning | adam-s/car-diagnosis | |
|---|---|---|---|
| Stars | 8 | 8 | 8 |
| Language | Python | Python | Python |
| Last pushed | — | 2024-08-07 | — |
| Maintenance | — | Stale | — |
| Setup difficulty | easy | easy | moderate |
| Complexity | 2/5 | 1/5 | 3/5 |
| Audience | general | developer | researcher |
Figures from each repo's GitHub metadata at analysis time.
Needs a local multimodal AI model running through something like LM Studio or Ollama.
MemeDrawer is a command line tool for cleaning up a messy folder full of memes and reaction images. Instead of manually looking at each image and deciding where it belongs, MemeDrawer sends each picture to a local AI model that can understand images, and uses its judgment to sort and rename the file. It is designed to work with locally run AI models through tools like LM Studio, Ollama, or llama.cpp, so no images need to be sent to an outside company. Before sending an image, MemeDrawer shrinks and compresses it to keep things fast, and it can process several images at once, or one at a time if you are using a local model on a computer with a less powerful graphics card. A key feature is that MemeDrawer can be told to only use folders that already exist, rather than inventing new ones every time it runs. In this mode, it looks at your current folder names, case sensitivity aside, and files that do not clearly match a folder are simply left alone rather than creating clutter. It also avoids obviously redundant subfolders that just repeat their parent folder's name. For safety, every sort can be previewed first with a dry run option, and if you run the real sort and are not happy with the result, a single undo command puts every file back exactly where and as it was. There is also a stats command that shows a breakdown of your sorted collection and can find exact duplicate files by comparing their content, without needing the AI at all. The tool has a playful side too: a cartoon maid character named Mimi narrates the process in the terminal, and after each run it shows a folder tree along with fun statistics like sorting speed and a lifetime count of memes organized. Setup and running both go through a Python packaging tool called uv, which handles installing the right Python version and dependencies automatically.
A command line tool that uses a local AI model to automatically sort and rename messy folders of memes and reaction images.
Mainly Python. The stack also includes Python, uv, LM Studio.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.