Open-source vector databases in 2026

30 open-source projects, ranked by GitHub stars and how recently each was worked on. Milvus leads with 47k stars, ahead of Qdrant. 27 had code pushed in the last three months. Most common licenses: Apache-2.0 (22), MIT (4) and AGPL-3.0 (3). Commercial vector databases are listed separately.

All open-source vector databases, ranked

Complete systems you can adopt 2

1
AutoFlow pingcap
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

Complete system Experimental You want a self-hosted Q&A chatbot over product docs and are happy to use TiDB as the store.
★ 3k Apache-2.0 TypeScript Active, pushed today
2
JustHireMe vasu-devs
Local-first AI job intelligence workbench for scraping roles, ranking fit, and generating tailored application materials.

Complete system Experimental You are job hunting and want AI help ranking roles and drafting applications on your own machine.
★ 2.3k AGPL-3.0 Python Active, pushed 24 days ago

Frameworks and platforms to build on 4

1
LangChain4j langchain4j
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.

Framework or platform Production-ready You are adding LLM features to a Java or Kotlin application and want to stay on the JVM.
★ 13k Apache-2.0 Java Active, pushed today
2
Txtai neuml
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Framework or platform Usable You want one Python library to build semantic search and RAG locally with few external services.
★ 13k Apache-2.0 Python Active, pushed today
3
Genkit genkit-ai
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

Framework or platform Production-ready You are building AI features on Firebase or Google Cloud, especially in TypeScript or Go.
★ 6.6k Apache-2.0 TypeScript Active, pushed today
4
Neuron AI neuron-core
The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that interact with your data and UI.

Framework or platform Usable Your application is in PHP or Laravel and you want to add agents without a separate Python service.
★ 2.2k MIT PHP Active, pushed today

Building blocks for your own system 19

1
Milvus milvus-io
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

Building block Production-ready You need vector search over hundreds of millions of embeddings or more and have the people to run a distributed system.
★ 47k Apache-2.0 Go Active, pushed today
2
Qdrant qdrant
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/

Building block Production-ready You are building semantic search, RAG or recommendations and want a dedicated vector store that is simple to self-host.
★ 35k Apache-2.0 Rust Active, pushed today
3
Cognee topoteretes
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

Building block Usable You build agents that need long-term memory across sessions and want graph-based retrieval rather than plain vector RAG.
★ 33k Apache-2.0 Python Active, pushed today
4
Chroma chroma-core
Search infrastructure for AI

Building block Production-ready You are building retrieval for an LLM app and want something simple to start with locally.
★ 30k Apache-2.0 Rust Active, pushed 3 days ago
5
Zvec alibaba
A lightweight, lightning-fast, in-process vector database

Building block Usable You want SQLite-style embedded vector search inside an app or agent without a separate server.
★ 16k Apache-2.0 C++ Active, pushed today
6
LEANN StarTrail-org
[MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

Building block Experimental You want to search your own files, email or chat history with RAG on a laptop and storage is the constraint.
★ 14k MIT Python Active, pushed yesterday
7
LanceDB lancedb
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

Building block Usable You want serverless vector search embedded in a Python, TypeScript or Rust app, with data kept in files on S3 or disk.
★ 12k Apache-2.0 Rust Active, pushed today
8
OceanBase oceanbase
OceanBase is the unified distributed database for the AI era — open-source, multi-model, one engine for your most demanding workloads.

Building block Production-ready You need a scale-out MySQL-compatible database with high availability, especially in finance or large Chinese enterprise settings.
★ 10k Apache-2.0 C++ Active, pushed 3 days ago
9
Databend databendlabs
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.

Building block Usable You want a Snowflake-style warehouse on your own object storage, self-hosted or via Databend Cloud.
★ 9.5k Apache-2.0 Rust Active, pushed today
10
ParadeDB paradedb
One Postgres for your application data, full-text search, vector retrieval, and aggregations. Home of the pg_search extension.

Building block Usable You want Elasticsearch-quality search on data already in Postgres without running a separate search cluster.
★ 9.5k AGPL-3.0 Rust Active, pushed today
11
MariaDB Server MariaDB
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.

Building block Production-ready You need a MySQL-compatible database under the GPL, or run software that targets MySQL or MariaDB.
★ 8.5k GPL-2.0 C++ Active, pushed today
12
Vespa vespa-engine
The AI search platform

Building block Production-ready You run large-scale search or recommendation where ranking quality and real-time updates matter more than simplicity.
★ 7.2k Apache-2.0 Java Active, pushed today
13
HelixDB HelixDB
HelixDB is an OLTP graph database with native vector and full-text search built in Rust on Object Storage.

Building block Usable You are building RAG or agent memory that needs graph relationships and vector search in one store.
★ 6.3k Apache-2.0 Rust Active, pushed today
14
Infinity infiniflow
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

Building block Experimental You need hybrid retrieval with tensor reranking for RAG and want it in a single engine.
★ 4.8k Apache-2.0 C++ Active, pushed today
15
LongMemory CaviraOSS
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Building block Experimental You want your AI assistants to share durable memory stored on your own machine.
★ 4.6k Apache-2.0 TypeScript Active, pushed 15 days ago
16
Crate crate
CrateDB is a distributed and scalable SQL database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is PostgreSQL-compatible, and based on Lucene.

Building block Production-ready You collect industrial or IoT data at volume and want SQL queries with full-text and vector search.
★ 4.5k Apache-2.0 Java Active, pushed today
17
Memvid memvid
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.

Building block Experimental You want offline, file-based retrieval memory for an agent and prefer one artifact to ship over a vector database.
★ 17k Apache-2.0 Rust Slowing, pushed 4 months ago
18
Knowhere Ontos-AI
Knowhere extracts, parses, and outputs structured chunks ready for AI Agents and RAG.

Building block Experimental Your agents need to work over large local collections of PDFs and office files.
★ 3.9k Apache-2.0 Python Active, pushed today
19
Deeplake activeloopai
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

Building block Usable You manage large multimodal training datasets and want versioned storage that streams straight to training jobs.
★ 9.3k Apache-2.0 C++ Slowing, pushed 6 months ago

Integrations 1

1
Claude Context zilliztech
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

Integration Usable Your coding agent struggles to find relevant code in a large repository.
★ 13k MIT TypeScript Slowing, pushed 4 months ago

Developer tools 1

1
SocratiCode giancarloerra
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.

Developer tool Experimental Your AI coding assistant struggles to find its way around a large codebase and you want a local index for it.
★ 3.4k AGPL-3.0 TypeScript Active, pushed today

Templates and starters 1

1
DeepSearcher zilliztech
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Template or starter Experimental You want a starting point for a deep-research style agent over your own documents.
★ 8.4k Apache-2.0 Python Active, pushed 41 days ago

Lists, courses and other material 2

1
Examples pinecone-io
Jupyter Notebooks to help you get hands-on with Pinecone vector databases

List, course or other material Usable You are learning Pinecone or want working code to adapt for a RAG prototype.
★ 3.1k MIT Jupyter Notebook Active, pushed 11 days ago
2
Bootcamp milvus-io
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

List, course or other material Usable You are evaluating or learning Milvus and want end-to-end examples to copy.
★ 2.5k Apache-2.0 Jupyter Notebook Active, pushed 12 days ago

Compared head to head

AutoFlow vs JustHireMe

Also under databases

Time-series databases

Open-source licenses

Permissive: 26. Use it anywhere, including in closed products. You keep the copyright notice; Apache-2.0 also grants patent rights.
Network copyleft: 3. Like GPL, and running a changed version as a web service counts as distributing it, so its users get the source too.
Strong copyleft: 1. If you distribute the program or anything built on it, you must release the whole source under the same license.

Languages

Rust 7, Python 6, C++ 5, TypeScript 5, Java 3, Jupyter Notebook 2, Go 1 and PHP 1.

Made software that belongs here? Add it. Listing is free.