Ubaida-M-Yusuf/Makimus-AI

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

43
/ 100
Emerging

Leverages CLIP embeddings via `open_clip_torch` to encode both media and queries into a unified vector space, enabling cross-modal search across images, videos, RAW files, and text. Supports GPU acceleration across NVIDIA (CUDA), Apple Silicon (MPS), and AMD (DirectML/ROCm) with automatic CPU fallback, while caching embeddings locally to avoid re-indexing on updates. Features a tkinter GUI with drag-and-drop image search, negative term filtering, and background video indexing via FFmpeg.

No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 11 / 25

How are scores calculated?

Stars

65

Forks

7

Language

Python

License

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/Ubaida-M-Yusuf/Makimus-AI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.