# Milvus

Milvus is a high-performance, cloud-native vector database built to store and search billions of vectors representing unstructured data such as text, images and other multi-modal information.

Written in Go and C++ with hardware acceleration for CPU and GPU, it uses a fully distributed, Kubernetes-native architecture that scales horizontally, handles tens of thousands of search queries against billions of vectors, and keeps data fresh through real-time streaming updates; a Standalone mode covers single-machine deployment, and Milvus Lite is a lightweight, pip-installable version for a quick local start in Python.

Queries can combine vector similarity search with metadata filtering or hybrid search, and a managed option, Zilliz Cloud, offers serverless, dedicated and bring-your-own-cloud deployment for teams that prefer not to self-host.

Governed under the LF AI and Data Foundation, Apache-2.0 licensed, with Zilliz as its major contributor.

Website: https://milvus.io