71,865 visible repositories in the index
361–384 of 1,073 · Most stars
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Stable diffusion for real-time music generation
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
The repository host gives no description.
GitHub repository for the SecureDrop whistleblower platform. Do not submit tips here!
SRE Agent - CNCF Sandbox Project
3D visualization and mesh analysis for science and engineering
An AI-powered web suite for advanced image processing and generation. VisioCraft integrates state-of-the-art computer vision models; including YOLO, SAM, and LaMa; to provide seamless object extraction, content-aware fill, and image generation through an interactive canvas UI.
Official upstream for the cloud-init: cloud instance initialization
OpenMMLab Pre-training Toolbox and Benchmark
Release for Improved Denoising Diffusion Probabilistic Models
The Pants Build System
A python library for self-supervised learning and latent world models on images.
Pony Object Relational Mapper
A test fixtures replacement for Python
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
Self-hosted, local only NVR and AI Computer Vision software. With features such as object detection, motion detection, face recognition and more, it gives you the power to keep an eye on your home, office or any other place you want to monitor.
[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
Library and command-line utility for rendering projects templates.
Serverless Python
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
The repository host gives no description.
[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System