Research on Coding Agents

A multilingual research document collection analyzing how Claude Code works internally, covering its telemetry, internal codenames, agent loop architecture, remote configuration controls, and upcoming features based on publicly available observations.

If you can read ~100 lines of Python, you understand agents.

计算机基础、人工智能学习工具、技巧合集 | A collection of ComputerScience and DeepLearning tutorial and tools.

使用 AI Agent 在单 GPU 上自动训练并调优大语言模型

西瓜书南瓜书学习的相关资料

陈希孺 概率论与数理统计基础

🏛️ Directive · OpenClaw Multi-Agent Orchestration System — 10 AI agents modeled after the U.S. Federal Executive Branch. Dual independent veto layers (White House Counsel + OMB), per-department Inspector General auditing, inter-agency task forces, and a real-time Situation Room dashboard. Separation of powers, by design.

If you can read ~200 lines of Python, you understand MCP.

与Datawhale组织的现有仓库以及学习内容对话——快速找到你想学习的内容和贡献内容！

A mini assistant to help you read paper quickly

Collection of image and video datasets for generative AI and multimodal visual AI

ComfyUI Workflow Collection | ComfyUI 工作流合集

If you can read ~100 lines of Python, you understand Skills.

A free tool that helps you transcribe, translate, and summarize videos in any language.

Collected the world's best computer vision labs and lecture materials.

If you can read ~200 lines of Python, you understand agent memory.

一分钟上手zotero7

有关 PyTorch Conference 的全会议中文转录摘要，结构化笔记

基于AutoDL快速部署开源大模型，更适合中国宝宝的部署教程

Fine-tuning LLM for Chinese Prose: A Practical Guide

A simple tool helps you trace python program.

No description.

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

ComfyUI Workflow to run audioldm pipeline

从 0 到 1 学会 vibe coding，项目制学习

该项目旨在通过输入文本描述来检索与之相匹配的图片。

Easy Use ComfyUI CLIPSEG

a custom node for ComfyUI that integrates the StepVideo text-to-video generation model

Learn agent engineering by building: ClaudeCode agent, industry agents & OpenCrawl, all from scratch | 动手学 Agent 工程：从零实现 ClaudeCode Agent、行业 Agent 与 OpenCrawl

天数智芯 GPGPU 常见环境配置、信息收集

hands on model tuning with TVM and profile it on a Mac M1, x86 CPU, and GTX-1080 GPU.

用文本编辑器剪视频💐利用GPT改善结果 (新特性开发及日常维护)

给女朋友做的微信小程序！情侣自己的任务和商城系统！

有关高性能计算与边缘计算部署相关的资料

AI tool to generate standard investment banking editable PPT outputs.

使用ONNXRuntime部署CodeFormer图像清晰修复，包含C++和Python两个版本的程序

No description.

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

Analyze the unstructured data with Towhee, such as reverse image search, reverse video search, audio classification, question and answer systems, molecular search, etc.

No description.

Segment Anything Web demo

Use whisper to turn any audio & video into a full summary

农业岛智慧农业系统Java版，基于Java+Vue+Uni-app开发，在微信公众号、小程序、H5移动端都能使用，代码开源，独立部署，二开很方便，能满足智慧农业气象站监控系统、智慧农业温棚监控系统、智慧农业高标准农田系统、智慧农业仓库系统、报表统计、智慧农业设备控制系统、设备物模型、大屏展示等多种经营需求，自用、做二开项目都很合适，MQTT、NETTY、EMQX。

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

No description.

AI-Powered Desktop / CLI Translation Application | AI 驱动的桌面/ CLI翻译应用程序

Open-source orchestration for zero-human companies

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

研知科研助手

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

Code Convert to PaddlePaddle Toolkit

[CVPR-2023] Towards Any Structural Pruning; LLMs / Diffusion / Transformers / YOLOv8 / CNNs

一个存放垃圾的地方

DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm.

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions

一个推理库的实现, A DIY deep learning inference framework.

Demonstration of MobileSAM in the browser enabled through ONNX runtime web

ONNX-Powered Inference for State-of-the-Art Face Upscalers

No description.

No description.

记录近期的 1) 图像/视频的超分增强等low level vision任务; 2) 图像生成 等任务相关论文, 主要为18年以后的DL based方法.

A set of simple tools for splitting, merging, OP deletion, size compression, rewriting attributes and constants, OP generation, change opset, change to the specified input order, addition of OP, RGB to BGR conversion, change batch size, batch rename of OP, and JSON convertion for ONNX models.

an experimental project for paddle python IR.

A beautiful stack trace pretty printer for C++

NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.

nanobind: tiny and efficient C++/Python bindings

Hugging StableDiffusion, Hugging Future.

CUDA Library Samples

中文nlp解决方案(大模型、数据、模型、训练、推理)

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

neosr is a framework for training real-world single-image super-resolution networks.

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

Solve puzzles. Improve your pytorch.

PaddlePaddle Developer Community

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, Axolotl, etc.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.

📚 Jupyter notebook tutorials for OpenVINO™

A curated list of OpenVINO based AI projects

No description.

No description.

GPT based autonomous agent that does online comprehensive research on any given topic

:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

一个创建comfyui自定义节点的指南(guide to write comfyui custom node，tutorial)

:gear: Just a template for quickly creating a python library.

A curated list of awesome research papers, projects, code, dataset, workshops etc. related to virtual try-on.

🤖 Components Library for Quickly Building LLM Chat Interfaces.

Experiments with local as well as models available through an api

【HACKATHON 预备营】飞桨启航计划集训营

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

No description.

No description.

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

something for paper AI

No description.

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Train VAE like a boss

A cross-platform app for batch conversion of video/audio to subtitles and text. 用于快速批量将视频/音频转换为字幕和文本，跨平台使用

从零学习，制作懂人情世故的大语言模型

多模态 MM +Chat 合集

AI Outpainting (AI扩图)网站源码

Datawhale Repository Template

use any caption model you want

无人机智能巡检平台——后端服务模块

无人机智慧巡检平台_前端

Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding

A minimalistic AI-powered search engine that helps you find information on the internet. Powered by Vercel AI SDK! Search with models like Grok 2.0.

Context parallel attention that accelerates DiT model inference with dynamic caching

NanoGPT (124M) in 3 minutes

implement of srcnn super resolution network

CVPR2023 - Activating More Pixels in Image Super-Resolution Transformer Arxiv - HAT: Hybrid Attention Transformer for Image Restoration

This package contains the original 2012 AlexNet code.

FULL v0, Cursor, Manus, Same.dev, Lovable, Devin & Replit Agent System Prompts, Tools & AI Models.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

📚 从零开始的大语言模型原理与实践教程

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

AI 图像编辑 Web 应用，使用 **FLUX.1 Kontext [pro]** 前沿模型提供强大的图像编辑功能，支持Stripe支付，注册登录，积分系统等，代码100%开源。

Penpot: The open-source design tool for design and code collaboration

一个现代化、生产就绪的 AI SaaS 应用模板。 基于 Next.js 15 构建，集成了用户认证、支付系统、AI 功能、国际化、文档系统和完整的管理后台。

Free AI SaaS Starter Template Kit, A full-stack starter template kit for building AI-driven SaaS applications, crafted using Next.js and Tailwind CSS.

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.

本项目是基于dify开源项目实现的dsl工作流脚本合集

Open Source realtime backend in 1 file

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

一个强大的、由 AI 驱动的演示文稿（PPt）自动化生成工具，真正生产化的工具，全流程可控，帮助用户快速制作出符合需求的 PPt。

Super Magic. The first open-source all-in-one AI productivity platform (Generalist AI Agent + Workflow Engine + IM + Online collaborative office system)

Easy to maintain open source documentation websites.

Public repository for Skills

Web service for web page to Markdown conversion

A powerful browser assistant for vibe surfing

AgentScope: Agent-Oriented Programming for Building LLM Applications

🍎 🖥 🎆 A curated list of screensavers for Mac OS X

A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.

快速测试

Sutskever 30 implementations inspired by https://papercode.vercel.app/

👾 Fast and simple video download library and CLI tool written in Go

The First Systematic Vibe Coding Open-Source Tutorial | From Zero to Full-Stack, Empowering Everyone to Build Products with AI | Live at: www.vibevibe.cn ；首个系统化 Vibe Coding 开源教程 | 零基础到全栈实战，让人人都能用 AI 开发产品 | 在线地址：www.vibevibe.cn

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

"DeepTutor: AI-Powered Personalized Learning Assistant"

Production-ready platform for agentic workflow development.

Minimal reproduction of DeepSeek R1-Zero

Long-term memory for your 24/7 OpenClaw agents across LLMs and platforms.

Open-source Agent Teams system with IM-based multi-Agent collaboration and human-in-the-loop oversight.

🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.

Make Claws Great Again

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

MBA AI Agent课程：2天集中培训，从LLM基础到多智能体系统

No description.

A curated list of open-source tools for systematic reviews, meta-analysis, and evidence synthesis.

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。

One Line of Code, Access to 100+ AI Models | 一行代码，访问100个AI模型

A curated list of awesome C frameworks, libraries, resources and other shiny things. Inspired by all the other awesome-... projects out there.

个人练习，自编码器及其变形（理论+实践）

No description.

汇编语言学习：使用王爽写的《汇编语言》第三版

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

An ultra lightweight inference performance optimization library for HuggingFace Diffusers on NVIDIA GPUs.

🤗 smolagents: a barebones library for agents that think in code.

CodeGeeX: An Open Multilingual Code Generation Model

Tensor library for machine learning

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

中学历史学科作为培养学生综合素质和历史意识的重要学科，对于学生的发展具有深远的影响。为了提升中学生对历史学科的学习效果，开发基于InternLM大模型的中学历史学习助手。

🌩最好的中文README模板⚡️Best README template

A self-learning tutorail for CUDA High Performance Programing.

No description.

Search photos on Unsplash using natural language

image deblur framework,base on opencv 2.4.9

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

对人像抠图模型MODNet进行滤波器级别的剪枝，结合自适应与固定比例策略。

Study parallel programming - CUDA, OpenMP, MPI, Pthread

CUDA 6大并行计算模式 代码与笔记

TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

自己实现一个tensor add 计算图,并对其结果

An imperative deep learning framework with customized GPU and CPU backend

B站Efficient-Neural-Network学习分享的配套代码

An open source library for face detection in images. The face detection speed can reach 1000FPS.

Convolutional Neural Network with CUDA (MNIST 99.23%)

No description.

C++ Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, OpenVINO, ncnn, MNN, SNPE, Arm NN, NNabla, ONNX Runtime, LibTorch, TensorFlow

TensorRT 2022 亚军方案，tensorrt加速mobilevit模型

:poodle: :poodle: :poodle: TensorRT 2022复赛方案： 首个基于Transformer的图像重建模型MST++的TensorRT模型推断优化

Blog friends link & latest post RSS present

A General-purpose Parallel and Heterogeneous Task Programming System

A Bytecode level Implementation of Symbolic OpCode Translator For PaddlePaddle

:fire: Linux下C++轻量级WebServer服务器

This repository is a sample implementation of frontend/backend using SAM code from meta.

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

This sample shows how to use the OpenVINO C++ 2.0 API to deploy Paddle PP-OCRv3 model

This sample shows how to use the oneAPI Video Processing Library (oneVPL) to perform a single and multi-source video decode and preprocess and inference using OpenVINO to show the device surface sharing (zero copy)

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

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

No description.

how to optimize some algorithm in cuda.

PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.