Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

Milvus

milvus.io

  • Free plan
  • Linux
  • API
  • Self-hosted
7.4 Club score Visit milvus.io

What Milvus is

Milvus is a free, open-source vector database developed by Zilliz for GenAI applications and scalable vector search. It supports approximate nearest neighbor, filtered, range, hybrid, and full-text search, along with reranking, fetch, and query operations. Deployment options include Lite as a Python library, Standalone as a single-machine server, and Distributed for Kubernetes clusters. Documentation recommends Lite for up to a few million vectors, Standalone up to 100 million, and Distributed for 100 million to tens of billions. Lite can run on a device without a cloud service, including for local searches of private or sensitive data. Official APIs and SDKs cover REST, Python, Go, Java, Node.js, and C++; C# is contributed by Microsoft, while Rust is under development. Security features include user authentication, TLS for gRPC and REST traffic, and role-based access controls at collection, database, and instance levels. The documentation says a default Milvus 3.x deployment uses Woodpecker, etcd, and MinIO. Milvus is Apache 2.0 licensed and associated with the LF AI & Data Foundation under the Linux Foundation. Zilliz Cloud is linked as a fully managed offering.

Who it suits

Milvus suits developers building vector search into GenAI applications, from local demos to large Kubernetes deployments. Its Distributed option is described as suitable for enterprise users running large-scale vector search in production.

Good to know, and what to watch

  • Offers local, single-machine, and Kubernetes deployment options
  • Supports hybrid and full-text search
  • Lite can search private data without a cloud service
  • Includes TLS and role-based access control
  • Online upgrades from Standalone to a cluster are not supported
  • Rust SDK is still under development
  • Default Milvus 3.x uses three listed dependencies

Milvus (open-source software)

Free

Free plan

The verdict

Milvus offers multiple deployment paths and a broad set of search operations, with recommendations tied to dataset size. Plan deployment carefully: moving from Standalone to a cluster cannot currently be done through an online upgrade.

What the maker publishes

Access control
RBAC can control operations at collection, database, and instance levels. source
Dependencies
A default Milvus 3.x deployment uses Woodpecker for messaging, etcd for metadata, and MinIO for object storage. source
Deployment
Milvus offers Lite as a Python library, Standalone as a single-machine server, and Distributed for Kubernetes clusters. source
Deployment caveat
The documentation says an online upgrade from a standalone Milvus instance to a cluster is not currently supported. source
Deployment limits
The docs recommend Lite for up to a few million vectors, Standalone up to 100 million, and Distributed for 100 million to tens of billions. source
Deployment options
Milvus offers Lite as a Python library, Standalone as a single-machine server, and Distributed for Kubernetes clusters. source
Free plan
Yes source
Integrations
The integrations documentation lists tools including LangChain, LlamaIndex, Haystack, DSPy, Dify, Langflow, OpenAI, Cohere, and HuggingFace. source
Intended users
The documentation describes Distributed as suited to enterprise users running large-scale vector search systems in production. source
Local use
Milvus Lite can run on a device without a cloud service for local search of private or sensitive data. source
Maker
The documentation says Milvus was developed by Zilliz and is associated with the LF AI & Data Foundation under the Linux Foundation. source
Managed option
Milvus links to Zilliz Cloud as its fully managed offering and describes a free option on its documentation site. source
Product
Milvus is an open-source vector database built for GenAI applications. source
Scale
Milvus supports deployments from local notebook demos to Kubernetes clusters handling tens of billions of vectors. source
Scale limits by deployment
The documentation recommends Milvus Lite for up to a few million vectors, Standalone for up to 100 million, and Distributed for 100 million to tens of billions. source
SDKs
Milvus provides official REST, Python, Go, Java, Node.js, and C++ APIs or SDKs; C# is contributed by Microsoft and Rust is under development. source
Search
Milvus supports approximate nearest neighbor, filtering, range, hybrid, and full-text search, plus reranking, fetch, and query operations. source
Search features
Milvus supports approximate nearest neighbor, filtered, range, hybrid, and full-text search, as well as reranking and queries. source
Security
Milvus documents user authentication, TLS encryption for gRPC and REST traffic, and role-based access control. source
Support
The Milvus site lists community channels including Slack, Discord, GitHub, and Milvus Office Hours. source
What it does
Milvus is an open-source vector database developed by Zilliz for high-performance, scalable vector search. source

Checked against the maker's pages on 4 Oct 2026.