Milvus

Milvus is an open-source vector database for large-scale similarity search in AI apps, self-hostable as standalone or a distributed cluster, or via managed Zilliz Cloud.

AI Platforms & Generative AIOpen sourceSelf-hosted
Visit official website

Published Updated

CategoryAI Platforms & Generative AI
AccessSelf-hosted
PricingFreemium
APISee vendor
Overview

What is Milvus?

Milvus is an open-source vector database created by Zilliz in 2019 and donated to the LF AI & Data Foundation in 2020, where it is now a graduated project. It is licensed under Apache 2.0 and offers multiple deployment modes: Milvus Lite (embedded, for local development), Standalone (single machine), and a distributed cluster mode for billion-vector scale. Zilliz also offers Zilliz Cloud as a fully managed alternative.

Read the full overview

Sources checked 27 September 2026: official website, documentation, GitHub repository.

Why teams use it

Key capabilities

  • Multiple deployment modes: Lite, Standalone or distributed cluster, matching your scale.
  • Billion-scale ANN search: Built for high-throughput approximate nearest-neighbor queries.
  • Managed option: Zilliz Cloud for teams that don't want to operate a cluster.
Core areas

Vector database infrastructure for large-scale AI similarity search is the primary use case.

Positioning

Shortlist Milvus when you need to scale vector search beyond a single embedded database, with a growth path from local development (Milvus Lite) to a distributed production cluster or Zilliz's managed cloud.

Why it matters

Confirm which deployment mode matches your actual scale and compare the operational effort of self-hosting a cluster against Zilliz Cloud's usage-based pricing.

Deployment & technical details

Technical details

Access
Self-hosted
Source model
Open source
Founded
2019
Pricing model
Freemium
API
Not specified
Check with the publisher

Official resources

Before you shortlist

What to verify for your environment

Start from the users, systems and operating responsibilities the tool needs to support.

  • Confirm current features, licensing and support terms with the publisher.
  • Validate deployment, data location, access control, backup and recovery requirements.
  • Test integrations, export paths and a representative operational workflow before committing.
Community experience

Reviews of Milvus

No published reviews yet.

Loading review form…