Skip to main content
Submit

Milvus

Open-source vector database for billion-scale AI applications

Vector DBs & EmbeddingsFree

Milvus is an open-source vector database purpose-built for billion-scale similarity search. Developed by Zilliz, it supports multiple vector index types (IVF, HNSW, ANNOY, DiskANN), multimodal data (text, image, video), and hybrid search (dense + sparse). Used in production by companies like Salesforce, eBay, and NVIDIA for large-scale AI applications.

Visit site
Key specs
46,649 GitHub stars source
as of 2026-11-12

Maker of Milvus? Get your db.fyi badge

What we know

LicenseApache-2.0source, checked 2026-11-12
Open sourceYessource, checked 2026-11-12
PricingFreefrom our original listing, not yet re-checked
GitHub stars46,649source, checked 2026-11-12

Why it matters

  • Proven at billion-scale in production at companies like Salesforce and eBay — one of the few vector DBs with verified large-scale deployments.
  • 31K+ GitHub stars makes it the most starred open-source vector database.
  • Multiple index types allow optimizing for different scale/accuracy/latency tradeoffs.
  • Kubernetes-native architecture enables horizontal scaling for high-throughput production systems.

Key capabilities

  • Billion-scale vectors: Designed and tested for datasets with billions of vectors.
  • Multiple index types: FLAT, IVF, HNSW, ANNOY, DiskANN — choose based on scale and latency requirements.
  • Hybrid search: Combine dense vector search with sparse (BM25) keyword search.
  • Multimodal support: Store and search text, image, audio, and video embeddings.
  • Collection partitioning: Partition data by category for faster filtered search.
  • RBAC: Role-based access control for multi-tenant and enterprise deployments.
  • Python/Java/Go/Node SDK: Client SDKs for major languages.
  • Zilliz Cloud: Managed Milvus-as-a-service with autoscaling and enterprise SLA.

Technical notes

  • License: Apache 2.0 (open source)
  • GitHub: github.com/milvus-io/milvus (31K+ stars)
  • Architecture: Kubernetes-native; distributed; cloud-native storage separation
  • Indexes: FLAT, IVF_FLAT, IVF_SQ8, IVF_PQ, HNSW, ANNOY, DiskANN
  • Languages: Python, Java, Go, Node.js, C++
  • Deployment: Docker, Kubernetes; Zilliz Cloud (managed)
  • Pricing: Free (open source); Zilliz Cloud starts ~$65/mo

Ideal for

  • Applications with hundreds of millions to billions of vectors where smaller DBs struggle.
  • Enterprise ML teams with Kubernetes infrastructure who need production-grade vector search.
  • Multimodal AI applications requiring search across text, image, and other embedding types.

Not ideal for

  • Small to medium datasets (under 10M vectors) — Qdrant or Chroma are simpler to operate.
  • Teams without Kubernetes/DevOps expertise — Milvus's operational complexity is high for small teams.
  • Quick prototyping — Chroma or LanceDB are much faster to set up.

See also

  • Pinecone — Fully managed vector DB; no self-hosting; good for teams without DevOps.
  • Qdrant — Simpler self-hosted Rust vector DB with excellent performance.
  • Chroma — Simple embedded DB; best for development and small-scale production.

FAQ

What is Milvus?

Milvus is an open-source vector database designed for large-scale AI applications. It stores vectors and metadata, then performs fast approximate nearest-neighbor search at billion-vector scale. Built for production use with features like horizontal scaling, collection partitioning, RBAC, and support for hybrid dense+sparse search. The managed cloud version is Zilliz Cloud.

Is Milvus open source?

Yes. Milvus is open source under the Apache 2.0 license. GitHub: github.com/milvus-io/milvus. Zilliz Cloud is the fully managed version from the company that created Milvus, providing managed infrastructure, autoscaling, and enterprise SLA without self-hosting.

How does Milvus compare to Qdrant?

Both are open-source vector databases with self-hosting options. Milvus is designed for billion-scale deployments with Kubernetes-native horizontal scaling, more complex index types, and a longer production track record with enterprise users. Qdrant is written in Rust (faster per-node), simpler to deploy (single binary), and has excellent filtering. Milvus for very large scale; Qdrant for simplicity and performance.

What index types does Milvus support?

Milvus supports multiple vector index algorithms: FLAT (exact brute force), IVF_FLAT (inverted file), IVF_SQ8 (quantized), IVF_PQ (product quantization), HNSW (hierarchical navigable small world graph), ANNOY, DiskANN (disk-based for massive scale). Different indexes provide different tradeoffs between accuracy, memory usage, build time, and query speed.

Alternatives

Integrations

None listed.

Built on

None listed.

Good for these tasks

Related tools

Listed 2026-02-28 · updated 2026-08-15