Milvus

Name: Milvus
Author: Zilliz / LF AI & Data Foundation

by Zilliz / LF AI & Data Foundation · Database · also known as Milvus Lite, Zilliz Cloud

Open-source vector database from Zilliz with Lite, Standalone and Distributed deployments, many index types and GPU acceleration

Apache-2.0 licenseOpen sourceFreeUsage-basedEnterpriseSelf-hostedCloudLocalSelf-hostable

Visit official site Compare

Link verified Nov 2, 2026

Overview

Milvus is an open-source vector database created by Zilliz and governed under the LF AI & Data Foundation with an Apache 2.0 license. It is designed around a cloud-native, disaggregated architecture: in Distributed mode, query, data and index nodes scale independently over object storage and a message queue, while Standalone packs the components into one container and Milvus Lite runs as a Python library for notebooks and prototypes. The project offers a wide choice of index types (HNSW, IVF variants, DiskANN, GPU indexes), scalar filtering, hybrid dense-plus-sparse search, partitions and multi-tenancy, with SDKs for Python, Java, Go, Node.js and C# and a RESTful API. Zilliz Cloud is the managed service.

Milvus is aimed at large collections where horizontal scaling and index flexibility matter. The distributed deployment depends on etcd, MinIO or S3 and Pulsar or Kafka, which makes it heavier to operate than single-binary engines; smaller teams typically start with Lite or Standalone. The website redirects for non-browser clients, but loads normally in a browser.

Editorial note on uncertainty. Zilliz Cloud pricing was not reviewed, so no pricing_url is recorded; pricing_model reflects the existence of free, usage-based and enterprise managed tiers as described on the Milvus site.

Capabilities

Lite (library), Standalone and Distributed deployment modes
Many index types including HNSW, IVF, DiskANN and GPU indexes
Scalar filtering, partitions and multi-tenancy
Hybrid dense and sparse vector search
SDKs for Python, Java, Go, Node.js and C# plus REST
Managed Zilliz Cloud offering

Typical workflows

Large-scale semantic search over billions of vectors
RAG backend on Kubernetes
Local prototyping with Milvus Lite in a notebook

Strengths

Independent scaling of components
Broad index selection including GPU
Foundation governance and Apache 2.0

Limitations

Distributed mode requires etcd, object storage and a message queue
Operational complexity for small teams
Lite mode lacks some server features

Prerequisites

Docker or Kubernetes for server modes; Python for Milvus Lite

Who it is for

Platform teams running vector search at scale
ML engineers evaluating index types

Alternatives & comparison

Chroma
Open-source embedding database with a minimal Python and JavaScript API, usable in-process, as a server or through Chroma Cloud
Open sourceOpen source
Elasticsearch
Distributed search and analytics engine on Apache Lucene with full-text, aggregations, vector search and ES|QL; triple-licensed AGPL, SSPL and Elastic License
MixedOpen source
pgvector
PostgreSQL extension adding vector types, distance operators and HNSW/IVFFlat indexes for similarity search inside the database
Open sourceOpen source
Pinecone
Fully managed, proprietary vector database service with serverless indexes, namespaces, metadata filtering and integrated embedding and reranking
ProprietaryFreemium
Qdrant
Open-source vector search engine written in Rust with filterable HNSW indexes, sparse and multi-vector support, REST/gRPC APIs and a managed cloud
Open sourceOpen source
Weaviate
Open-source vector database in Go with pluggable vectorizer modules, hybrid BM25 and vector search, multi-tenancy and a managed cloud
MixedOpen source

Compare Milvus with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

License
Milvus LICENSE (Apache 2.0)
https://github.com/milvus-io/milvus/blob/master/LICENSE
Supports: license_spdx, source_model
checked Nov 1, 2026
Official documentation
Milvus documentation
https://milvus.io/docs
Supports: capabilities, languages
checked Nov 1, 2026
Official site
Milvus | High-Performance Vector Database Built for Scale
https://milvus.io/
Supports: name, summary, vendor
Returns HTTP 302 to itself for plain curl; loads in a browser-like fetcher
checked Nov 1, 2026
Repository
milvus-io/milvus
https://github.com/milvus-io/milvus
Supports: repo_url
checked Nov 1, 2026

Confidence: Medium
Reviewed: Nov 1, 2026
Links: Verified · Nov 2, 2026

Spotted an error?

Meilisearch

Meili SAS · Vector databases

Rust search engine for application search-as-you-type with typo tolerance, faceting and hybrid semantic search; MIT core plus BSL enterprise parts

MIT AND BUSL-1.1Open sourceFreeSelf-hostedNov 2, 2026

OpenSearch

OpenSearch Software Foundation (Linux Foundation) · Vector databases

Apache-2.0 search and analytics suite forked from Elasticsearch and Kibana, governed by the OpenSearch Software Foundation

Apache-2.0Open sourceFreeSelf-hostedBroken

Typesense

Typesense, Inc. · Vector databases

GPL-licensed in-memory search engine in C++ offering typo-tolerant instant search, faceting, vector and hybrid search, with Typesense Cloud hosting

GPL-3.0Open sourceFreeSelf-hostedNov 2, 2026