Wilber

AI-fundamentals. AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识。

gfwlist. The one and only one gfwlist here

llm-compressor. Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

lm-evaluation-harness. A framework for few-shot evaluation of language models.

Agent-Learning-Hub. AI Agent 学习路线与资料库收集

claude-code. Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

codex. Lightweight coding agent that runs in your terminal

zstd. Zstandard - Fast real-time compression algorithm

tilelang. Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

k3s. Lightweight Kubernetes

llm-d. Achieve state of the art inference performance with modern accelerators on Kubernetes

CUDA-Agent. CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

hello-agents. 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

tinygrad. You like pytorch? You like micrograd? You love tinygrad! ❤️

free-llm-api-resources. A list of free LLM inference resources accessible via API.

locust. Write scalable load tests in plain Python 🚗💨

opencode. The open source coding agent.

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

mini-sglang. A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

cutile-python. cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Foundations-of-LLMs. A book for Learning the Foundations of LLMs

neutrino. C

llama.cpp. LLM inference in C/C++

fzf. :cherry_blossom: A command-line fuzzy finder

BettaFish. 微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

EAGLE. Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

dynamo. A Datacenter Scale Distributed Inference Serving Framework

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Rectangle. Move and resize windows on macOS with keyboard shortcuts and snap areas

NVBit.

500-AI-Agents-Projects. The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education, retail, and more.

infisical. Infisical is the open-source platform for secrets, certificates, and privileged access management.

remotely-save. Sync notes between local and cloud with smart conflict: S3 (Amazon S3/Cloudflare R2/Backblaze B2/...), Dropbox, webdav (NextCloud/InfiniCLOUD/Synology/...), OneDrive, Google Drive (GDrive), Box, pCloud, Yandex Disk, Koofr, Azure Blob Storage.

MediaCrawler. 小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

WSL. Windows Subsystem for Linux

ZeroOmega. Manage and switch between multiple proxies quickly & easily.

SwitchyOmega. No longer maintained, see pinned issues

DeepGEMM. DeepGEMM: clean and efficient BLAS kernel library on GPU

uv. An extremely fast Python package and project manager, written in Rust.

firefly-iii. Firefly III: a personal finances manager

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

folly. An open-source C++ library developed and used at Facebook.

VILA. VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Folo. 🧡 Folo is the AI RSS Reader

minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

crawl4ai. 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

project-based-learning. Curated list of project-based tutorials

End-to-end-Autonomous-Driving. [IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving

lectures. Material for gpu-mode lectures

DeepSeek-V3. Python

AISystem. AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

system-design-101. Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.

maigret. 🕵️‍♂️ Collect a dossier on a person by username from 3000+ sites

compiler-explorer. Run compilers interactively from your web browser and interact with the assembly

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Plash. 💦 Make any website your Mac desktop wallpaper

every-programmer-should-know. A collection of (mostly) technical things every software developer should know about

spotube. 🎧 Open source music streaming app! Available for both desktop & mobile!

ab-download-manager. A Download Manager that speeds up your downloads

chatbox. Powerful AI Client

gpgpu-sim_distribution. GPGPU-Sim provides a detailed simulation model of contemporary NVIDIA GPUs running CUDA and/or OpenCL workloads. It includes support for features such as TensorCores and CUDA Dynamic Parallelism as well as a performance visualization tool, AerialVisoin, and an integrated energy model, GPUWattch.

svelte. web development for the rest of us

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

ImageNet. This implements training of popular model architectures, such as AlexNet, ResNet and VGG on the ImageNet dataset(Now we supported alexnet, vgg, resnet, squeezenet, densenet)

PasteBarApp. PasteBar - Limitless, Free Clipboard Manager for Mac and Windows

Vane. Vane is an AI-powered answering engine.

excalidraw. Virtual whiteboard for sketching hand-drawn like diagrams

lively. Free and open-source software that allows users to set animated desktop wallpapers and screensavers powered by WinUI 3.

exo. Run frontier AI locally.

LeetCUDA. 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

reactive-resume. A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

localsend. An open-source cross-platform alternative to AirDrop

resume. An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git

Motrix. A full-featured download manager.

awesome-mac.  This project is dedicated to collecting high-quality macOS software and organizing them systematically by different categories for easy search and use.

Hyprland. Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.

MifareClassicTool. An Android NFC app for reading, writing, analyzing, etc. MIFARE Classic RFID tags.

weekly. 科技爱好者周刊，每周五发布

expert_readed_books. 2021年最新总结，推荐工程师合适读本，计算机科学，软件技术，创业，思想类，数学类，人物传记书籍

pomatez. Stay Focused. Take a Break.

sniffnet. Comfortably monitor your Internet traffic 🕵️‍♂️

open-gpu-kernel-modules. NVIDIA Linux open GPU kernel module source

LLM101n. LLM101n: Let's build a Storyteller

xtensor. C++ tensors with broadcasting and lazy computing

godot. Godot Engine – Multi-platform 2D and 3D game engine

pi-hole. A black hole for Internet advertisements

system-design-primer. Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

developer-roadmap. Interactive roadmaps, guides and other educational content to help developers grow in their careers.

immich. High performance self-hosted photo and video management solution.

niri. A scrollable-tiling Wayland compositor.

aimoneyhunter. ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English version for more insights.

maybe. The personal finance app for everyone

bazel-compile-commands-extractor. Goal: Enable awesome tooling for Bazel users of the C language family.

Ice. Powerful menu bar manager for macOS

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

generative-ai-for-beginners. 21 Lessons, Get Started Building with Generative AI

ChatTTS. A generative speech model for daily dialogue.

amber. 💎 Amber the programming language compiled to Bash/Ksh/Zsh

geektime-books. :books: 极客时间电子书

perfetto. Production-grade client-side tracing, profiling, and analysis for complex software systems.

homepage. A highly customizable homepage (or startpage / application dashboard) with Docker and service API integrations.

TranslucentTB. A lightweight utility that makes the Windows taskbar translucent/transparent.

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

llama3. The official Meta Llama 3 GitHub site

MoneyPrinter. Automate Creation of YouTube Shorts using MoviePy.

MoneyPrinterTurbo. 利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

free-programming-books. :books: Freely available programming books

aria2. aria2 is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.

warp. A Python framework for GPU-accelerated simulation, robotics, and machine learning.

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

grok-1. Grok open release

gpt-pilot. The first real AI developer

hello-algo. 《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持简中、繁中、English、日本語，提供 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 等代码实现

AI-Papers-of-the-Week. 🔥Highlighting the top ML papers every week.

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

wandb. The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

minbpe. Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

gemma_pytorch. The official PyTorch implementation of Google's Gemma models

my-tv. 我的电视 电视直播软件，安装即可使用

grpcurl. Like cURL, but for gRPC: Command-line tool for interacting with gRPC servers

pot-desktop. 🌈一个跨平台的划词翻译和OCR软件 | A cross-platform software for text translation and recognition.

pomotroid. :tomato: Simple and visually-pleasing Pomodoro timer

vscode-blockman. VSCode extension to highlight nested code blocks

Megatron-LM. Ongoing research training transformer models at scale

torchgpipe. A GPipe implementation in PyTorch

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

deep-rl-class. This repo contains the Hugging Face Deep Reinforcement Learning Course.

cuCollections. Cuda

act-plus-plus. Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

mobile-aloha. Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

CopyQ. Clipboard manager with advanced features

cuda-api-wrappers. Thin, unified, C++-flavored wrappers for the CUDA APIs

onnx_bench. onnx benchmark and tools

gpt-fast. Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

WeChatMsg.

Modern-CPP-Programming. Modern C++ Programming Course (C++03/11/14/17/20/23/26)

libjpeg-turbo. Main libjpeg-turbo repository

CUDALibrarySamples. CUDA Library Samples

AppFlowy. Bring projects, wikis, and teams together with AI. AppFlowy is the AI collaborative workspace where you achieve more without losing control of your data. The leading open source Notion alternative.

CV-CUDA. CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

OpenDDS. OpenDDS is an open source C++ implementation of the Object Management Group (OMG) Data Distribution Service (DDS). OpenDDS also supports Java bindings through JNI.

Fast-DDS. The most complete DDS - Proven: Plenty of success cases. Looking for commercial support? Contact info@eprosima.com

Tonic. An autonomous vehicle written in python

FFmpeg. Mirror of https://git.ffmpeg.org/ffmpeg.git

torchsparse. [MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

flash-attention. Fast and memory-efficient exact attention

spconv. Spatial Sparse Convolution Library

TensorRT-LLM. TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

libnpy. C++ library for reading and writing of numpy's .npy files

cnpy. library to read/write .npy and .npz files in C/C++

cmake_format. Source code formatter for cmake listfiles.

grafana. The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.

prometheus. The Prometheus monitoring system and time series database.

flatbuffers. FlatBuffers: Memory Efficient Serialization Library

jsoncpp. A C++ library for interacting with JSON.

c-ares. A C library for asynchronous DNS requests

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

lttng-ust. This repo is a mirror of the official lttng-ust git found at git://git.lttng.org/lttng-ust.git. LTTng-UST, the Linux Trace Toolkit Next Generation Userspace Tracer, is port of the low-overhead tracing capabilities of the LTTng kernel tracer to user-space. The library "liblttng-ust" enables tracing of applications and libraries.

lttng-tools. The lttng-tools project provides a session daemon (lttng-sessiond) that acts as a tracing registry, the "lttng" command line for tracing control, a lttng-ctl library for tracing control and a lttng-relayd for network streaming.

codellama. Inference code for CodeLlama models

onnx-mlir-serving. ONNX Serving is a project written with C++ to serve onnx-mlir compiled models with GRPC and other protocols.Benefiting from C++ implementation, ONNX Serving has very low latency overhead and high throughput. ONNX Servring provides dynamic batch aggregation and workers pool to fully utilize AI accelerators on the machine.

Ros. 机器人操作系统ROS 语音识别 语义理解 视觉控制 gazebo仿真 雷达建图导航

argparse. Argument Parser for Modern C++

onnxsim. Simplify your onnx model

mit-deep-learning. Tutorials, assignments, and competitions for MIT Deep Learning related courses.

ChatGLM2-6B. ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

OI-wiki. :star2: Wiki of OI / ICPC for everyone. （某大型游戏线上攻略，内含炫酷算术魔法）

WebServer. A C++ High Performance Web Server

WebBench. Webbench是Radim Kolar在1997年写的一个在linux下使用的非常简单的网站压测工具。它使用fork()模拟多个客户端同时访问我们设定的URL，测试网站在压力下工作的性能，最多可以模拟3万个并发连接去测试网站的负载能力。官网地址:http://home.tiscali.cz/~cz210552/webbench.html

ChatGLM-6B. ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

FasterTransformer. Transformer related optimization, including BERT, GPT

FindTheChatGPTer. ChatGPT爆火，开启了通往AGI的关键一步，本项目旨在汇总那些ChatGPT的开源平替们，包括文本大模型、多模态大模型等，为大家提供一些便利

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

openmlsys. 《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

newspaper. newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:

the-algorithm. Source code for the X Recommendation Algorithm

ps-lite. A lightweight parameter server interface

cppnow_presentations_2012. C++

taskflow. A General-purpose Task-parallel Programming System in C++

llama. Inference code for Llama models

sourcegraph-public-snapshot. Code AI platform with Code Search & Cody

oneflow. OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

gpu-runtime. C++

slam_in_autonomous_driving. 《自动驾驶中的SLAM技术》对应开源代码

runtime. A performant and modular runtime for TensorFlow

triton. Development repository for the Triton language and compiler

nnfusion. A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

relax. Python

mlc-zh. Python

xla. A machine learning compiler for GPUs, CPUs, and ML accelerators

TTSAndroid. TTS Android demo of PaddleSpeech, merged into https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos