# Milvus

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

Repository: https://github.com/milvus-io/milvus
Canonical: https://ross.abutalabs.com/products/milvus
Homepage: https://milvus.io
Language: Go
License: Apache-2.0
License Family: permissive
Topics: anns, nearest-neighbor-search, faiss, vector-search, image-search, hnsw, vector-database, embedding-database, embedding-store, vector-store, vector-similarity, embedding-similarity, distributed, golang, llm, cloud-native, diskann, rag
Last push: 2026-08-26T23:48:41+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 84, longevity 100
- inputs: {"age_days": 2543, "days_push": 7, "days_rel": 30, "gap_med": 7.0, "n_releases_24m": 79}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 45808, forks 4199 (observed 2026-08-28T04:12:09.681068+00:00)

## What it is
Milvus is a high-performance, cloud-native vector database written in Go and C++ for scalable approximate nearest neighbor search over embeddings. It supports distributed and standalone deployments, GPU acceleration, and has official SDKs such as pymilvus.

## Use cases
- store and search embeddings for a RAG chatbot
- build semantic search over millions of documents
- image similarity search at scale
- recommendation system with nearest-neighbor retrieval
- deduplicate embeddings across billions of vectors
- power LLM long-term memory with a vector store

## When to choose
- you need horizontal scaling to billions of vectors with high query throughput
- you want a production-grade, Kubernetes-native vector database
- you need real-time streaming inserts alongside fast ANN search
- you want flexible deployment from laptop (Milvus Lite) to cluster

## When to avoid
- your dataset is small and fits in a simple in-process library like FAISS
- you only need exact k-NN on a few thousand vectors
- you want a fully managed service without operating infrastructure and prefer a lighter managed offering

## Facets
- artifact type: service
- maturity: stable
- function: vector-database, search-engine, database, rag
- domain: databases, artificial-intelligence, machine-learning, large-language-models
- platform: cloud, self-hosted, python, go
- tags: ann-search, embeddings, similarity-search, hnsw, distributed, cloud-native, llm-applications, search, retrieval-augmented-generation, linux, macos, docker, kubernetes

## Member repositories
- milvus-io/milvus (main) score 94
- milvus-io/bootcamp (examples) score 67
- milvus-io/pymilvus (sdk) score 97

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:09.681068+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:21:38.495652+00:00, confidence not recorded.
  - readme: https://github.com/milvus-io/milvus (fetched 2026-08-28T04:12:09.681068+00:00, sha b6449f5c6cca)
  - registry_pypi: https://pypi.org/pypi/pymilvus/json (fetched 2026-08-29T07:45:14.257953+00:00, sha 55653efb47a2)
- Data as of 2026-08-30T08:39:29.467469+00:00.