Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
Repository Index
76,356 visible repositories in the index
673–696 of 3,798 · Most stars
A Keras implementation of YOLOv3 (Tensorflow backend)
TranslatedChinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models
Open-source, self-hosted alternative to Grok Bot, Claude Duet, OpenAI Dots, Meta Muse, Instinct, Manus Cue: AI coworkers (named agents) with instructions, memory, routines, their own isolated computer, and your approval before they act.
- agentic-ai
- ai-agent
- ai-assistant
- ai-workspace
Framework for evaluating and improving agents
- evals
- rl-environments
- terminal-bench
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
- segment-anything
- video-object-segmentation
- interactive-tracking
- track-anything
MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency; instead, she values warmth, authenticity, and genuine connection.
- chat
- llm
- python
- qq-bot
An open source library for deep learning end-to-end dialog systems and chatbots.
TranslatedMusicdl: A lightweight music downloader written in pure python. (A lightweight lossless music downloader that supports dozens of music/audiobook platforms, such as 网易云音乐 (Wangyi Yun Yinyue, "NetEase Cloud Music"), QQ音乐 (QQ Yinyue, "QQ Music"), 酷狗音乐 (Kugou Yinyue, "Kugou Music"), 酷我音乐 (Kuwo Yinyue, "Kuwo Music"), 咪咕音乐 (Migu Yinyue, "Migu Music"), 千千静听 (Qianqian Jingting, "Qianqian Quiet Listening"), 汽水音乐 (Qishui Yinyue, "Soda Music"), Bilibili, 街声 (Jiesheng, "Street Sound"), 喜马拉雅 (Ximalaya, "Himalaya"), 懒人听书 (Lanren Tingshu, "Lazy People Listen to Books"), 荔枝FM (Lizhi FM, "Lychee FM"), 蜻蜓FM (Qingting FM, "Dragonfly FM"), JOOX, TIDAL, YouTube, Apple Music, Spotify, Qobuz, SoundCloud and other mainstream music platforms)
- music-downloader
- kuwo
- qqmusic
- kugou-music
An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.
- claude-code
- geoguessr
- geolocation
- osint
Official PyTorch implementation of StyleGAN3
MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
- lip-sync
- virtualhumans
ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution
- version-control
- experiment-manager
- version
- control
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
- document-ai
- eccv-2022
- multimodal-pre-trained-model
- ocr
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
Unified real-time search engine skill for AI agents. Supports general web search, vertical domain search, parallel batch search, and full-page content extraction.
TranslatedE-book "Large Models and Agents" (《大模型与智能体》) with 6 programming tasks: Transformer, mini-GPT, SFT/DPO, RAG, tool calling, and coding agents.
Python binding for curl-impersonate fork via cffi. A http client that can impersonate browser tls/ja3/http2 fingerprints.
- curl
- http-client
- curl-impersonate
- http
Open-source and AI-powered cybersecurity tools for offensive security, vulnerability management, and autonomous pentesting. Built by hackers in Latin America, used worldwide.
- devops
- penetration-testing
- vulnerability
- vulnerability-scanners
One place for all the default credentials to assist the Blue/Red teamers identifying devices with default password 🛡️
- infosec
- default-password
- pentesting
- bugbounty
Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
- deep-learning
- deep-reinforcement-learning
- game
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
- multi-object-tracking
- real-time
- deployment
- pytorch
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI
This is a repository for collecting global custom management extensions for the Django Framework.