Open-source vector-database software
233 open-source libraries, tools and applications tagged vector-database, ranked by how closely vector-database is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
233 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| thedotmack/claude-mem Claude-Mem (Grok Mem) is an open‑source memory engine that captures, compresses, and stores observations from AI agents across sessions. It… | 82 | 101435 | active |
| RAGFlow RAGFlow is an open‑source Retrieval‑Augmented Generation engine that combines vector search, BM25 and custom scoring with integrated AI age… | 94 | 92343 | active |
| Elasticsearch Elasticsearch is a free and open source, distributed, RESTful search and analytics engine built on Apache Lucene. It stores structured, uns… | 95 | 78300 | stable |
| mem0ai/mem0 Mem0 provides a drop‑in memory infrastructure for AI agents and applications, enabling persistent, token‑efficient context across sessions.… | 89 | 65721 | active |
| upstash/context7 Context7 is a platform that provides up-to-date, version‑specific code documentation and examples directly to LLMs and AI code editors. It … | 81 | 62588 | active |
| MemPalace/mempalace MemPalace is a local‑first AI memory system that stores conversation and project data verbatim and makes it searchable via semantic search.… | 82 | 59621 | active |
| Meilisearch Meilisearch is a fast, open-source search engine that provides typo-tolerant full-text search, semantic and hybrid AI-powered search, and v… | 91 | 59352 | stable |
| LlamaIndex LlamaIndex is an open‑source framework for building LLM‑powered applications that ingest, parse, and index documents. It provides tools for… | 93 | 52325 | active |
| ClickHouse ClickHouse is an open-source column‑oriented OLAP database management system designed for real‑time analytics on massive datasets. It provi… | 96 | 50464 | active |
| Milvus Milvus is a high‑performance, cloud‑native vector database designed for scalable approximate nearest neighbor (ANN) search. It provides har… | 94 | 46356 | active |
| vectorize-io/hindsight Hindsight is an open-source agent memory system that gives AI agents persistent long-term memory that learns and consolidates knowledge ove… | 78 | 44347 | active |
| facebookresearch/faiss Faiss is a C++ library (with Python wrappers) for efficient similarity search and clustering of dense vectors, supporting indexes that scal… | 94 | 41147 | stable |
| TiDB TiDB is an open‑source, cloud‑native distributed SQL database with strong ACID guarantees. It supports hybrid transactional/analytical proc… | 96 | 40589 | active |
| HKUDS/LightRAG LightRAG is a Python library that implements a simple and fast Retrieval-Augmented Generation framework using graph structures and vector e… | 84 | 40153 | active |
| volcengine/OpenViking OpenViking is an open-source context database designed for AI agents. It provides a virtual filesystem interface for storing, retrieving, a… | 77 | 39101 | active |
| Qdrant Qdrant is a high‑performance, open‑source vector similarity search engine and database written in Rust. It provides a production‑ready API … | 96 | 34906 | active |
| SurrealDB SurrealDB is a scalable, distributed, multi‑model database that combines document, graph, relational and vector storage in a single ACID en… | 93 | 33087 | active |
| SurrealDB SurrealDB is a multi-model database written in Rust that combines document, graph, vector, and relational data models in a single ACID engi… | 93 | 33087 | stable |
| Cognee Cognee is an open‑source AI memory platform that provides persistent, long‑term memory for AI agents. It builds a knowledge graph from docu… | 90 | 31294 | active |
| Cognee Cognee is an open-source Python library and platform that gives AI agents persistent long-term memory by ingesting data in any format and b… | 90 | 31294 | active |
| Supermemory Supermemory is a fast, scalable memory and context engine for AI agents, offered as a hosted API with self‑hosted options. It provides auto… | 89 | 31077 | active |
| GBrain GBrain is a self-hosted 'brain layer' for AI agents that combines a knowledge graph, vector search, and a synthesis engine to return cited … | 79 | 30972 | active |
| Chroma Chroma is an open-source search and retrieval database for AI applications, supporting dense vector, sparse (BM25/SPLADE), full-text, regex… | 87 | 29471 | active |
| Chroma Chroma is an open‑source data infrastructure that provides fast, scalable vector and full‑text search for AI applications. It can be self‑h… | 87 | 29471 | active |
| rohitg00/agentmemory AgentMemory is a TypeScript library that provides persistent, local‑first memory for AI coding agents. It captures, compresses, and recalls… | 78 | 28900 | active |
| mongodb/mongo MongoDB is a high‑performance, document‑oriented NoSQL database that stores JSON‑like documents. It provides a flexible schema, built‑in re… | 77 | 28650 | active |
| TencentCloud/TencentDB-Agent-Memory TencentDB Agent Memory is a team-level memory hub that stores and serves conversational, document, and code embeddings for AI agents. It pr… | 79 | 27532 | active |
| Typesense Search Engine Typesense is an open-source, in-memory search engine written in C++ that provides fast, typo-tolerant full-text search with sub-50ms latenc… | 85 | 26616 | stable |
| Typesense Search Engine Typesense is an open‑source, typo‑tolerant search engine written in C++. It provides fast full‑text, faceted, and vector search with a simp… | 85 | 26616 | active |
| Turso Database Turso is a lightweight, SQLite‑compatible database that can run embedded on devices or as a fully managed cloud service. It adds modern fea… | 96 | 24810 | active |
| timescale/timescaledb TimescaleDB is an open-source PostgreSQL extension that adds native time‑series capabilities and high‑performance analytics. It provides au… | 98 | 23629 | active |
| HKUDS/RAG-Anything RAG-Anything is a Python-based, all‑in‑one Retrieval‑Augmented Generation framework that supports text, images, tables, and math. It provid… | 86 | 23584 | active |
| pgvector pgvector is an open-source PostgreSQL extension that adds vector data types and vector similarity search, supporting exact and approximate … | 76 | 23171 | active |
| Neon Serverless Postgres Neon is an open-source serverless PostgreSQL platform that separates storage and compute for autoscaling and instant branching. It can be r… | 71 | 23123 | active |
| Neo4j Neo4j is the leading open-source native graph database, storing and querying connected data as nodes and relationships using the Cypher que… | 66 | 17253 | stable |
| Turso Database libSQL is an open source, open contribution fork of SQLite maintained by Turso, adding features like vector search, concurrent writes, asyn… | 77 | 17247 | active |
| RyanCodrai/turbovec turbovec is a Rust vector index with Python bindings implementing Google's TurboQuant algorithm for 2-4 bit vector quantization with SIMD-a… | 57 | 17244 | active |
| Elysia Weaviate is an open-source, cloud-native vector database written in Go that stores both objects and vector embeddings, combining vector sim… | 94 | 16860 | stable |
| memvid/memvid Memvid is a single-file memory layer for AI agents that packages data, embeddings, and search indexes into one portable .mv2 file. It repla… | 72 | 16550 | active |
| electric-sql/pglite PGlite is a WASM build of PostgreSQL packaged as a TypeScript client library that runs a full Postgres database in the browser, Node.js, Bu… | 89 | 16142 | active |
| Apache Doris Apache Doris is an open-source MPP-based real-time analytical database that delivers sub-second queries over massive datasets, combining a … | 98 | 16078 | stable |
| GraphScope Zvec is an open-source, in-process vector database by Alibaba that embeds directly into applications with no server or daemon required. It … | 80 | 16070 | active |
| scylladb/scylladb ScyllaDB is an open-source, high-performance NoSQL wide-column data store built in C++ on the shared-nothing Seastar framework. It is API-c… | 76 | 15784 | stable |
| spotify/annoy Annoy is a C++ library with Python (and other language) bindings for approximate nearest neighbor search over high-dimensional vectors. It … | 41 | 14304 | stable |
| ArangoDB ArangoDB is a native multi-model database server written in C++ that unifies graph, document (JSON), key-value, full-text, and vector searc… | 77 | 14283 | stable |
| opensearch-project/OpenSearch OpenSearch is an open-source, distributed, RESTful search and analytics suite for full-text search, log analytics, application monitoring, … | 94 | 13813 | stable |
| EverMind-AI/EverOS EverOS is a Python library and local-first memory runtime that gives AI agents a portable, user-owned memory layer across apps, tools, and … | 83 | 13408 | active |
| txtai txtai is an all-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows, built around an embedd… | 95 | 12978 | active |
| StarTrail-org/LEANN LEANN is a low-storage vector index that enables retrieval-augmented generation (RAG) on personal devices by recomputing embeddings on the … | 85 | 12966 | active |
| Manticore Search Manticore Search is an open-source search database written in C++ that provides fast full-text, vector, and hybrid search with real-time in… | 98 | 12064 | stable |
| LanceDB LanceDB is an open-source embedded vector database and multimodal AI lakehouse built on the Lance columnar format, written in Rust with Pyt… | 94 | 11706 | active |
| MemTensor/MemOS MemOS is a memory operating system for LLMs and AI agents that unifies storing, retrieving, and managing long-term, multi-modal memory thro… | 83 | 11513 | active |
| bleve Bleve is a full-text indexing and search library for Go supporting text, numeric, datetime, geo-spatial, and vector fields. It provides ric… | 92 | 11230 | active |
| xerj-org/xerj XERJ is a Rust-based, single-binary search engine built for AI agents, offering BM25, kNN vector, and hybrid search with Elasticsearch-comp… | 77 | 10576 | active |
| oramasearch/orama Orama is a lightweight (~2kb) search engine and RAG pipeline library written in TypeScript that runs in the browser, server, or edge networ… | 81 | 10561 | active |
| FalkorDB FalkorDB is an ultra-fast, multi-tenant property graph database built on GraphBLAS sparse adjacency matrices, queryable via OpenCypher with… | 92 | 10490 | active |
| oceanbase/oceanbase OceanBase is a distributed relational database engine developed by Ant Group, offering MySQL compatibility, Paxos-based high availability, … | 98 | 10300 | stable |
| databendlabs/databend Databend is an open-source, cloud-native data warehouse built in Rust that runs entirely on object storage (S3, Azure, GCS). It unifies BI … | 90 | 9471 | active |
| ParadeDB ParadeDB is a Postgres extension (pg_search) that adds a custom index for fast full-text search, vector search, BM25 scoring, filtering, an… | 93 | 9424 | active |
| Deep Lake Deep Lake is an open-source database for AI that stores multimodal data (images, video, audio, text, embeddings, annotations) in a format o… | 75 | 9249 | active |
| reorproject/reor Reor is a local-first, AI-powered desktop note-taking app that automatically links related notes, answers questions over your notes via RAG… | 10 | 8549 | active |
| MariaDB Server MariaDB Server is a widely deployed open-source relational database (SQL server) forked from MySQL by its original developers, licensed und… | 98 | 8394 | stable |
| zilliztech/deep-searcher DeepSearcher is an open-source deep research tool that combines LLMs (DeepSeek, OpenAI, Claude, Qwen, etc.) with vector databases like Milv… | 55 | 8292 | active |
| asg017/sqlite-vec sqlite-vec is a vector search extension for SQLite written in pure C with no dependencies, supporting float, int8, and binary vectors in ve… | 71 | 8168 | active |
| Honcho Honcho is an open-source memory infrastructure service for building stateful AI agents that maintain understanding of users, agents, groups… | 82 | 7327 | active |
| Lance Lance is an open lakehouse data format (file format, table format, and catalog spec) for multimodal AI, implemented in Rust with Python and… | 95 | 7182 | active |
| Vespa Vespa is an open-source, distributed AI search platform and serving engine that combines full-text search, vector/tensor search, and machin… | 93 | 7117 | stable |
| SuanmoSuanyangTechnology/MemoryBear MemoryBear is an AI memory management system that gives LLM agents and chatbots human-like long-term memory across a full lifecycle of perc… | 83 | 7009 | active |
| postgresml/postgresml PostgresML is a PostgreSQL extension that brings machine learning and AI inference directly into the database, with GPU acceleration and pg… | 32 | 6823 | active |
| HelixDB/helix-db HelixDB is an open-source OLTP graph-vector database written in Rust that combines labeled property graphs with native vector, full-text, a… | 85 | 6205 | active |
| alibaba/AliSQL AliSQL is Alibaba Cloud's open-source MySQL branch based on MySQL 8.0.44, adding a DuckDB columnar analytical storage engine and native HNS… | 80 | 5986 | active |
| volcengine/MineContext MineContext is an open-source, proactive context-aware AI partner that captures and understands your screen activity to surface relevant in… | 61 | 5534 | active |
| microsoft/SPTAG SPTAG is a C++ library from Microsoft for large-scale approximate nearest neighbor (ANN) vector search, offering kd-tree/balanced k-means t… | 75 | 5019 | active |
| YDB YDB is an open-source distributed SQL DBMS written in C++ that combines horizontal scalability, high availability, and strict consistency w… | 98 | 4781 | stable |
| openai/chatgpt-retrieval-plugin A FastAPI-based retrieval backend that provides semantic search over personal or organizational documents using natural language queries, w… | 31 | 21249 | maintenance |
| infiniflow/infinity Infinity is an AI-native database built for LLM applications, offering high-performance hybrid search across dense vectors, sparse vectors,… | 99 | 4740 | active |
| NateBJones-Projects/OB1 Open Brain is a self-hosted personal memory infrastructure combining a vector-search database, an AI gateway, and an MCP server so any AI t… | 58 | 4632 | active |
| Memgraph Memgraph is a high-performance, in-memory graph database written in C++ that is Cypher-compatible and ACID-compliant, with built-in vector,… | 96 | 4579 | stable |
| ssrajadh/sentrysearch SentrySearch is a Python CLI tool that provides semantic search over video footage by embedding video chunks with Gemini Embedding, Alibaba… | 64 | 4560 | active |
| RuVector RuVector is a Rust-native vector database and memory substrate for AI agents, combining persistent semantic embeddings, graph relationships… | 83 | 4554 | active |
| FlowElement-xinliuyuansu/m_flow M-flow is a Python bio-inspired cognitive memory engine that treats graph topology as the retrieval scoring engine rather than a supportive… | 58 | 4511 | active |
| TypeDB TypeDB is a strongly-typed, polymorphic general-purpose database written in Rust, with its own declarative query language TypeQL, unifying … | 97 | 4475 | active |
| memory-lancedb-pro A LanceDB-backed long-term memory plugin for OpenClaw agents that stores preferences, decisions, and project context, then automatically re… | 72 | 4453 | active |
| CrateDB CrateDB is a distributed, horizontally scalable SQL database built on Lucene, designed for real-time analytics on massive datasets. It supp… | 95 | 4444 | active |
| unum-cloud/USearch USearch is a fast, single-file similarity search and clustering engine for vectors and arbitrary objects, supporting spatial, binary, proba… | 89 | 4325 | active |
| CozoDB CozoDB is a transactional, relational-graph-vector database written in Rust that uses Datalog as its query language. It runs embedded or as… | 23 | 4135 | active |
| RavenDB RavenDB is an open-source (AGPLv3) ACID NoSQL document database written in C#, featuring full-text search, vector search, time series, shar… | 92 | 4000 | stable |
| aiming-lab/SimpleMem SimpleMem is a Python library and MCP server that provides efficient lifelong memory for LLM agents, storing, compressing, and retrieving l… | 65 | 3821 | active |
| morphik-org/morphik-core Morphik Core is an open-source, source-available multimodal retrieval engine for building RAG applications over unstructured data like PDFs… | 65 | 3711 | active |
| documentdb/documentdb DocumentDB is an open-source, MongoDB-compatible document database engine built as PostgreSQL extensions, providing native BSON support, CR… | 83 | 3462 | active |
| mnemosyne-oss/mnemosyne Mnemosyne is a local-first, SQLite-backed memory layer for AI agents, exposing remember/recall APIs via a Python SDK and 30+ tools over MCP… | 82 | 3407 | active |
| pashpashpash/vault-ai OP Vault is a self-hosted application combining a Go backend with a React frontend that lets users upload documents (PDF, txt, epub) into a… | 40 | 3389 | active |
| giancarloerra/SocratiCode SocratiCode is a codebase context engine distributed as an MCP server, Claude Code plugin, and VS Code extension that indexes code, depende… | 82 | 3336 | active |
| zilliztech/attu Attu is an AI-native management GUI for the Milvus vector database, available as a web app (Docker/Kubernetes) or desktop app. It lets user… | 97 | 3186 | active |
| SeekDB seekdb is an AI-native search database from OceanBase that unifies relational, vector, full-text, JSON, and GIS data in a single MySQL-comp… | 78 | 3142 | active |
| timescale/pgvectorscale pgvectorscale is a PostgreSQL extension written in Rust that complements pgvector with a StreamingDiskANN index, statistical binary quantiz… | 87 | 3136 | active |
| docarray/docarray DocArray is a Python library for representing, transmitting, storing, and retrieving multimodal data such as text, images, audio, and video… | 10 | 3125 | active |
| MemMachine/MemMachine MemMachine is an open-source memory layer for AI agents and LLM applications, providing episodic, profile, and working memory that persists… | 85 | 3071 | active |
| maxpert/marmot Marmot is a leaderless, distributed SQLite replication system built on a gossip-based protocol with distributed transactions and eventual c… | 83 | 2819 | active |
| rom1504/clip-retrieval A Python toolkit for computing CLIP embeddings for images and text and building a semantic search/retrieval system on top of them. It inclu… | 52 | 2797 | active |
page 1 / 3 next →