MemoryOS alternatives for AI 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

A modular graph-based Retrieval-Augmented Generation (RAG) system

Give AI agents the context to query business data correctly through the open context layer that gives AI agents grounded, governed memory, context, SQL across 20+ data sources, that helps you build agentic GenBI, text-to-sql, dashboards, and agentic analytics.

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

Structured data extraction and instruction calling with ML, LLM and Vision LLM

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

OpenKB: Open LLM Knowledge Base

A simple, easy-to-hack GraphRAG implementation

Dynamiq is an orchestration framework for agentic AI and LLM applications

The NVIDIA VSS Blueprint is a suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications.

[KDD'2026] "VideoRAG: Chat with Your Videos"

Everything you need to know to build your own RAG application

📚 从零开始构建大模型