Stay updated with the latest and most popular GitHub repositories. We fetch data from the official GitHub API, analyze it in-house, and update our listings every hour to bring you the freshest trends.
使用ai生成多章节的长篇小说,自动衔接上下文、伏笔
An open-source implementaion for fine-tuning Qwen2-VL and Qwen2.5-VL series by Alibaba Cloud.
Make Mac apps accessible for AI agents
Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]
MCP Server to interact with Google Gsuite prodcuts
FlareSolverr drop-in replacement with FastAPI and nodriver
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
AWX provides a web-based user interface, REST API, and task engine built on top of Ansible. It is one of the upstream projects for Red Hat Ansible Automation Platform.
Automatic headphone equalization from frequency responses
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
A framework for managing and maintaining multi-language pre-commit hooks.
[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Retrying library for Python
ModelScope: bring the notion of Model-as-a-Service to life.
A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
The recursive internet scanner for hackers. 🧡
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Take potentially dangerous PDFs, office documents, or images and convert them to safe PDFs
Prometheus-based Kubernetes Resource Recommendations
Transformer: PyTorch Implementation of "Attention Is All You Need"
Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具,输出json、srt字幕、纯文字格式
A library for mechanistic interpretability of GPT-style language models
[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion
AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation
Synapse: Matrix homeserver written in Python/Twisted.
《大模型白盒子构建指南》:一个全手搓的Tiny-Universe
Real-time multi-camera multi-object tracker using YOLO varients
A project to improve skills of large language models
This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three TTS models: CosyVoice, Edge-TTS, and pyttsx3
RL Extension Library for Robots, Based on IsaacLab.
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation
A lightweight data processing framework built on DuckDB and 3FS.
Open-source generalized AI agent for everyday task automations.
Amazon Nova Act is a research preview of a new AI model for developers to build agents that take actions in web browsers
Efficient controlnet for DiTs
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
A little bit about a linux kernel
Deep Learning for humans
Open source UI framework written in Python, running on Windows, Linux, macOS, Android and iOS
A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.
Typer, build great CLIs. Easy to code. Based on Python type hints.
The little ASGI framework that shines. 🌟
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Lutris desktop client
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.