AI 开源项目榜。

代码 -《深度学习之PyTorch物体检测实战》

The standard .claude/ folder structure for everyday development.

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Pythonic tool for orchestrating machine-learning/high performance/quantum-computing workflows in heterogeneous compute environments.

Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.

Generate subtitles, summaries, and chapters from videos in seconds

An Eigen-based, light-weight C++ Interface to Nonlinear Programming Solvers (Ipopt, Snopt)

这是一个金融领域相关的mcp,本项目通过集成 Tushare API 和 Binance API 为语言模型（如Claude）提供全面的实时金融数据访问能力，支持股票、基金、债券、宏观经济指标、稳定币、虚拟货币等多维度金融数据分析。其中也包含了金融数据查询、财经新闻查询、国家统计局数据查询等

Claw-Admin 是一个基于 Vue 3 构建的现代化 AI 智能体管理平台，同时支持 OpenClaw Gateway 和 Hermes Agent 两大 AI 智能体网关提供完整的 Web 管理界面。通过直观的可视化操作，用户可以轻松管理 AI 智能体、会话、模型、频道、技能等核心功能。

A cross-platform desktop client for the jailbroken New Bing AI Copilot (Sydney ver.) built with Go and Wails (previously based on Python and Qt).

Agent Skill for AI-assisted manuscript writing review, based on Dr. Kristin Sainani's "Writing in the Sciences" methodology.

Search for the agentic web.

A curated list of awesome LLM frameworks, libraries and software.

xpander.ai is the runtime and control plane to build, run, and ship reliable AI agents fast and anywhere

这是一个基于SpringBoot和Telegrambot-Api的多功能Telegram群管机器人，Powered By DeepSeek And Google Cloud Vision。

🔥机器学习/深度学习/Python/大模型/多模态/LLM/deeplearning/Python/Algorithm interview/NLP Tutorial

Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"

Chat and Ask on your own data. Accelerator to quickly upload your own enterprise data and use OpenAI services to chat to that uploaded data and ask questions

EVAL(Elastic Versatile Agent with Langchain) will execute all your requests. Just like an eval method!

[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

Everything-Reactivity in ComfyUI (audio, MIDI, motion, proximity, and more). Animate and manipulate images, masks, videos, audio, and more. Native ACEStep extensions

oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.

A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models

PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows

DexiNed: Dense EXtreme Inception Network for Edge Detection

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure

TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.