Ubaida-M-Yusuf

Ubaida-M-Yusuf / Makimus-AI

Public

AI-powered media search — find images and videos using natural language or visual queries

ai clip gallery local-ai offline-ai
58
6
100% credibility
Found Feb 20, 2026 at 39 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Makimus-AI is a cross-platform desktop app that indexes local image folders and enables searching them via natural language descriptions or example images using AI-powered visual similarity.

How It Works

1
🔍 Discover Makimus-AI

You find this handy photo search tool online and download it to your computer.

2
🚀 Launch the App

Double-click the easy starter file, and the friendly dark-themed window opens up ready to help.

3
📁 Pick Your Photo Folder

Click the folder button to choose the directory full of your pictures, and it checks for any saved info.

4
⚡ Let It Learn Your Photos

The app quickly scans and remembers your images so searches are super fast next time.

5
🔤 Describe What You Want

Type simple words like 'girl in red dress' or pick a similar photo, and hit search.

6
🖼️ Browse Matching Pictures

Thumbnails of the best matches appear with scores, and you can tweak sliders for more or better results.

🎉 Found Your Photos!

Easily select, open, or copy your perfect matches and smile at how simple it was.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 39 to 58 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Makimus-AI?

Makimus-AI is a Python desktop app for local AI-powered image search, letting you query entire folders with natural language like "dog playing in grass" or by dropping a reference image to find visually similar ones. It indexes your library once—handling thousands of JPGs, PNGs, and WebPs—then caches embeddings for instant offline searches, turning chaotic local file organizers into searchable archives. Cross-platform on Windows, Linux, and macOS, it auto-adjusts for your GPU via CUDA, Metal, or DirectML.

Why is it gaining traction?

It stands out for running fully local with no cloud dependency, delivering GPU-accelerated searches that feel instant even on large collections, plus searchable indexing without waiting. Features like adjustable similarity thresholds, thumbnail previews, multi-select export, and smart caching make it a practical local AI-powered alternative to web tools. Developers dig the one-time setup via pip and bat files, with refresh scans for updated folders.

Who should use this?

Photo hoarders drowning in unsorted drives, game devs hunting sprites in asset folders, or designers querying mockups by description. Ideal for researchers with experiment image sets or anyone building local AI-powered file organizers without uploading to the cloud. Skip if you need mobile sync or enterprise scale.

Verdict

Solid prototype for local AI-powered image search—great README, easy install—but 22 stars and 1.0% credibility score signal early maturity with no tests or open contributions. Fork it for personal use; don't bet production workflows yet.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.