LightRAG
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Written mainly in Python. Released under the MIT licence.
Free plan
github.com/HKUDS/LightRAG
What each tool is actually for, described plainly. No ratings, no scores, no invented benchmarks.
RAG and memory: Vector databases, retrieval pipelines and the memory layers that let an agent recall things between sessions.
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Written mainly in Python. Released under the MIT licence.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
Written mainly in Jupyter Notebook.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
AnythingLLM is an application for chatting with your own documents. You drop in PDFs, notes, spreadsheets or links, it indexes them, and then you ask questions and get answers drawn from those files rather than from the model's general training. It runs as a desktop app or in Docker, and it can point at a local model or at a commercial one, which is the reason many people choose it: the documents can stay on your own machine. It supports separate workspaces, so a set of client files does not bleed into a set of personal notes. Setting it up takes more than opening a website, and the quality of the answers depends heavily on how clean the source documents are, which is true of every tool in this category and is worth knowing before you judge it.
Search infrastructure for AI
Written mainly in Rust. Released under the Apache-2.0 licence.
A library for efficient similarity search and clustering of dense vectors.
Written mainly in C++. Released under the MIT licence.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Written mainly in Python. Released under the MIT licence.
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.
Written mainly in Python. Released under the AGPL-3.0 licence.
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Written mainly in Python. Released under the Apache-2.0 licence.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Written mainly in Go. Released under the Apache-2.0 licence.
Open-source vector similarity search for Postgres
Written mainly in C.
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/
Written mainly in Rust. Released under the Apache-2.0 licence.
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.
Written mainly in Python.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Written mainly in Go. Released under the Apache-2.0 licence.
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.
Written mainly in Go.
Zep | Examples, Integrations, & More
Written mainly in Python. Released under the Apache-2.0 licence.