Best rag and knowledge skills for AI agents

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Excellent quality, 33K stars, and a 36 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 36 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, 16K stars, and a 35 use-case fit score.

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Excellent quality, 16K stars, and a 35 use-case fit score.

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

Excellent quality, 13K stars, and a 35 use-case fit score.

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

Excellent quality, 11K stars, and a 35 use-case fit score.

21 Lessons, Get Started Building with Generative AI

Excellent quality, 112K stars, and a 34 use-case fit score.

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Excellent quality, 63K stars, and a 33 use-case fit score.

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

Excellent quality, 58K stars, and a 33 use-case fit score.

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

Excellent quality, 34K stars, and a 33 use-case fit score.

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

Excellent quality, 27K stars, and a 33 use-case fit score.

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

Excellent quality, 26K stars, and a 33 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 32 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 32 use-case fit score.

🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.

Excellent quality, 10K stars, and a 32 use-case fit score.

Incremental engine for long horizon agents 🌟 Star if you like it!

Excellent quality, 10K stars, and a 32 use-case fit score.

Retrieval and Retrieval-augmented LLMs

Excellent quality, 12K stars, and a 32 use-case fit score.

The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.

Excellent quality, 10K stars, and a 32 use-case fit score.

Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.

Excellent quality, 9.3K stars, and a 31 use-case fit score.

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

Excellent quality, 9.2K stars, and a 31 use-case fit score.

MariaDB server is a community developed fork of MySQL server. Started by core members of the original MySQL team, MariaDB actively works with outside developers to deliver the most featureful, stable, and sanely licensed open SQL server in the industry.

Excellent quality, 7.7K stars, and a 31 use-case fit score.

The AI search platform

Excellent quality, 7.0K stars, and a 31 use-case fit score.

Free and Open Source, Distributed, RESTful Search Engine

Excellent quality, 77K stars, and a 31 use-case fit score.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Excellent quality, 71K stars, and a 31 use-case fit score.

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

Excellent quality, 45K stars, and a 30 use-case fit score.

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

Excellent quality, 32K stars, and a 30 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, 26K stars, and a 30 use-case fit score.

🦔 Fast, lightweight & schema-less search backend. An alternative to Elasticsearch that runs on a few MBs of RAM.

Excellent quality, 21K stars, and a 29 use-case fit score.

Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

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

Next-generation full-text search library for Browser and Node.js

Excellent quality, 14K stars, and a 29 use-case fit score.