An open-source AI agent that brings the power of Gemini directly into your terminal.

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 workflo…

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

Brand new TTS solution

"PhD-Level AI Agents: Fully-Automated Scientific Discovery with Our AI-Researcher Powered by LLMs"

Question and Answer based on Anything.

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

芋道管理后台，基于 Vue3 + Element Plus 实现，支持 RBAC 动态权限、数据权限、SaaS 多租户、Flowable 工作流、三方登录、支付、短信、商城、CRM、ERP、AI 大模型等功能。

Data annotation toolbox supports image, audio and video data.

"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos"

MNN is a lightweight deep neural network inference engine.

"RAG-Anything: All-in-One RAG System"

vits2 backbone with multilingual-bert

[CIKM'2024] "RecDiff: Diffusion Model for Social Recommendation"

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

"AI-Creator: Multi-Modal Agents for Video Production"

"RecGPT: A Foundation Model for Sequential Recommendation"

CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge techniques in sparse architecture, speculative sampling and qua…

[WSDM'2025] "DiffGraph: Heterogeneous Graph Diffusion Model"

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

trying to be a hackable music player

A PyTorch-based Speech Toolkit

Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

10 Lessons to Get Started Building AI Agents

12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

12 Weeks, 24 Lessons, AI for All!

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

This open-source curriculum is designed to teach the concepts and fundamentals of the Model Context Protocol (MCP), with practical examples in .NET, Java, TypeScript, JavaScript and Python.