The database of free AI tools on GitHub
23,066 open-source AI repos. Find a free alternative to any paid AI tool, or see what developers are talking about.
70 repos · showing 31–60
LightGlue is a fast local feature matcher for image pairs.
Remove backgrounds from portrait images and videos in OBS Studio.
A Python library for self-supervised learning on images.
Self-hosted AI software for home and office surveillance.
AI-assisted data labeling tool with YOLO and Segment Anything.
Converts images and PDFs into Markdown with text, tables, and math formulas.
Analyze and extract text and tables from documents using OCR and deep learning.
Optimized machine learning functions for Arm CPUs and GPUs.
AI-powered manga translation tool with OCR and text replacement.
AI-powered security camera system with local video analysis and LLM-driven alerts.
Enhances OCR output by using LLMs for error correction and formatting.
A C++ framework for video analysis and structuring using computer vision and multimodal large language models.
End-to-end Chinese scene-text detection and recognition with CTPN, CRNN, and CTC.
OCR tool for recognizing text in Japanese manga images.
OCR tool for capturing text from screenshots
A Python package for fast and robust image stitching.
Turn any device into a computer vision command center with Workflows.
Interactive semi-automatic image segmentation tool using Segment Anything models.
Handwritten text recognition using TensorFlow.
Rust OCR engine with multiple backends and an OpenAI-compatible server.
Unified face analysis library for detection, recognition, and more in Python.
Fast CPU OCR: line detection, CTC recognition, reading order, markdown
🦀 Low-level 3D Computer Vision library in Rust
Search over large image datasets with natural language and computer vision
Image augmentation for computer vision. AGPL-3.0-only or commercial licensing.
AI-powered fitness assistant for real-time pose estimation, exercise counting, and workout feedback.
FASHN VTON v1.5: Efficient Maskless Virtual Try-On in Pixel Space
Local AI photo scoring, culling, and gallery — score, organise, and explore your library with face recognition and semantic search. No cloud, no subscriptions.
A highly extensible and customizable framework for building OCR systems.
Model-agnostic state layer for world models — turn any detector (YOLO · VLM · DINO) into one standard, queryable stream of events + latent state. numpy-only, runs on CPU at the edge.