2,002 offers
Free RAG & Memory — open-source & self-hostable
Vector stores, RAG pipelines, agent memory
Scores rate free-tier value on a 1–10 scale. How scores work →
-
RAGFlow RAG & Memory 8.4 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 84.2k★1.5k/90d27 devs/90d -
Mem0 RAG & Memory 8.2 Universal memory layer for AI Agents 60k★351/90d32 devs/90d -
Milvus RAG & Memory 8.1 Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search 45.1k★640/90d33 devs/90d -
Cognee RAG & Memory 8.1 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. 26.8k★1.9k/90d13 devs/90d -
Onyx RAG & Memory 7.9 Open Source AI Platform - AI Chat with advanced features that works with every LLM 30.7k★1.7k/90d13 devs/90d -
Supermemory RAG & Memory 7.8 Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era. 28.1k★260/90d21 devs/90d -
LightRAG RAG & Memory 7.7 [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation" 37.3k★1.6k/90d7 devs/90d -
Weaviate RAG & Memory 7.6 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. 16.5k★1.9k/90d11 devs/90d -
Qdrant RAG & Memory 7.5 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/ 32.9k★517/90d16 devs/90d -
Graphiti RAG & Memory 7.5 Build Real-Time Knowledge Graphs for AI Agents 28.3k★72/90d10 devs/90d -
Chroma RAG & Memory 7.3 Search infrastructure for AI 28.7k★261/90d6 devs/90d -
Vespa RAG & Memory 7.3 The AI search platform 7k★2.3k/90d11 devs/90d -
LanceDB RAG & Memory 7.2 Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less. 10.8k★226/90d26 devs/90d -
pgvector RAG & Memory 7.0 Open-source vector similarity search for Postgres 22.1k★78/90d4 devs/90d -
MemOS RAG & Memory 7.0 Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings 10.1k★506/90d17 devs/90d -
RAG-Anything RAG & Memory 6.8 "RAG-Anything: All-in-One RAG Framework" 21.9k★81/90d17 devs/90d -
txtai RAG & Memory 6.7 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows 12.7k★80/90d3 devs/90d -
Zep RAG & Memory 6.7 Zep | Examples, Integrations, & More 4.7k★27/90d6 devs/90d -
FalkorDB RAG & Memory 6.4 A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG). 4.7k★87/90d10 devs/90d -
GraphRAG RAG & Memory 6.3 A modular graph-based Retrieval-Augmented Generation (RAG) system 34.2k★7/90d3 devs/90d -
HelixDB RAG & Memory 6.1 HelixDB is an OLTP graph-vector database built in Rust. 5.5k★95/90d2 devs/90d -
kotaemon RAG & Memory 5.8 An open-source RAG-based tool for chatting with your documents. 25.5k★1/90d1 devs/90d -
Verba RAG & Memory 5.8 Retrieval Augmented Generation (RAG) chatbot powered by Weaviate 7.7k★4/90d3 devs/90d -
Morphik RAG & Memory 5.7 The most accurate document search and store for building AI apps 3.6k★13/90d2 devs/90d -
NebulaGraph RAG & Memory 5.6 A distributed, fast open-source graph database featuring horizontal scalability and high availability 12.3k★2/90d2 devs/90d -
Marqo RAG & Memory 5.6 Ecommerce Search and Discovery - marqo.ai 5k★8/90d3 devs/90d -
Memvid RAG & Memory 5.4 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. 15.7k★3/90d1 devs/90d -
FlashRAG RAG & Memory 5.3 ⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource) 3.5k★6/90d2 devs/90d -
Vanna RAG & Memory 5.1 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄. 23.7k★0/90d0 devs/90d -
AutoRAG RAG & Memory 4.9 AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation 4.9k★0/90d0 devs/90d -
Cognita RAG & Memory 4.5 RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry 4.4k★0/90d0 devs/90d -
R2R RAG & Memory 4.3 SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API. 7.9k★0/90d0 devs/90d -
nano-graphrag RAG & Memory 4.3 A simple, easy-to-hack GraphRAG implementation 3.9k★0/90d0 devs/90d -
Infinity RAG & Memory 4.2 Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali 2.9k★0/90d0 devs/90d -
Memobase RAG & Memory 4.2 User Profile-Based Long-Term Memory for AI Chatbot Applications. 2.8k★0/90d0 devs/90d -
fastRAG RAG & Memory 4.1 Efficient Retrieval Augmentation and Generation Framework 1.8k★0/90d0 devs/90d -
Fast GraphRAG RAG & Memory 3.9 RAG that intelligently adapts to your use case, data, and queries 3.8k★0/90d0 devs/90d -
MiniRAG RAG & Memory 3.7 [ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models" 2k★0/90d0 devs/90d -
Memary RAG & Memory 3.5 The Open Source Memory Layer For Autonomous Agents 2.6k★0/90d0 devs/90d