Best rag and knowledge skills for AI agents

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

Excellent quality, 44K stars, and a 30 use-case fit score.

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Excellent quality, 15K stars, and a 29 use-case fit score.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Excellent quality, 13K stars, and a 29 use-case fit score.

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Excellent quality, 78K stars, and a 28 use-case fit score.

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Excellent quality, 32K stars, and a 27 use-case fit score.

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Excellent quality, 25K stars, and a 27 use-case fit score.

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

Excellent quality, 38K stars, and a 26 use-case fit score.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

Excellent quality, 22K stars, and a 26 use-case fit score.

Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

Excellent quality, 18K stars, and a 26 use-case fit score.

High accuracy RAG for answering questions from scientific documents with citations

Excellent quality, 8.5K stars, and a 25 use-case fit score.

Claude + Obsidian knowledge companion. Persistent, compounding wiki vault based on Karpathy's LLM Wiki pattern. /wiki /save /autoresearch

Excellent quality, 5.4K stars, and a 25 use-case fit score.

Build document intelligence and RAG workflows for agents

Excellent quality, 81K stars, and a 25 use-case fit score.

Postgres with GPUs for ML/AI apps.

Excellent quality, 6.8K stars, and a 25 use-case fit score.

TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

Excellent quality, 3.9K stars, and a 25 use-case fit score.

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

Excellent quality, 52K stars, and a 24 use-case fit score.

Connect agents to private data and retrieval workflows

Excellent quality, 50K stars, and a 24 use-case fit score.

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

Excellent quality, 47K stars, and a 24 use-case fit score.

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Excellent quality, 36K stars, and a 24 use-case fit score.

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Excellent quality, 35K stars, and a 24 use-case fit score.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Excellent quality, 30K stars, and a 24 use-case fit score.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Excellent quality, 28K stars, and a 24 use-case fit score.

Build Real-Time Knowledge Graphs for AI Agents

Excellent quality, 26K stars, and a 24 use-case fit score.

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

Excellent quality, 39K stars, and a 23 use-case fit score.

An open-source RAG-based tool for chatting with your documents.

Excellent quality, 25K stars, and a 23 use-case fit score.

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Excellent quality, 16K stars, and a 23 use-case fit score.

The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.

Excellent quality, 11K stars, and a 23 use-case fit score.

🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

Excellent quality, 7.8K stars, and a 22 use-case fit score.

AI + Data, online. https://vespa.ai

Excellent quality, 6.9K stars, and a 22 use-case fit score.

Open-source framework for building AI-powered apps in JavaScript, Go, and Python, built and used in production by Google

Excellent quality, 6.0K stars, and a 22 use-case fit score.

Convert documents into Markdown for agent-readable context

Excellent quality, 125K stars, and a 22 use-case fit score.