milvus-io/milvus

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

70
/ 100
Verified

Written in Go and C++, Milvus leverages hardware acceleration (CPU/GPU) and supports multiple vector index types (HNSW, IVF, SCANN, DiskANN) with quantization and memory-mapping for optimized search across different workloads. Its fully-distributed, Kubernetes-native architecture separates compute and storage layers, enabling independent scaling of query and data nodes, plus multi-tenancy isolation at database/collection/partition levels with hot/cold storage tiering. The SDK integrates seamlessly with Python (`pymilvus`) and supports hybrid search combining vector similarity with scalar metadata filtering and range queries.

43,332 stars. Actively maintained with 217 commits in the last 30 days.

No Package No Dependents
Maintenance 25 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

43,332

Forks

3,896

Language

Go

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

217

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/milvus-io/milvus"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.