Milvus
Open source · RAG and vector databases · milvus-io/milvus
What it does
Milvus is a vector database built to scale from a laptop to a large cluster. It stores embeddings and runs similarity search, with several index types to trade speed against accuracy.
Good for: Vector search that may need to grow to very large collections.
Milvus on GitHub (opens in a new tab) Project homepage (opens in a new tab)
Visitor votes, one per browser. Your own vote is kept on this device only. How votes work.
The signals we checked
- Licence
- Apache-2.0 (OSI-approved open-source licence)
- Popularity
- Stars: 46,395 (checked 16 Oct 2026)
- Last commit
- 16 Oct 2026
- Open issues and PRs
- 1,445
- Status
- Active (not archived)
- Self-host
- ModerateDocker Compose for a single machine; Kubernetes for a cluster.
- GitHub topics
- anns
- cloud-native
- diskann
- distributed
- embedding-database
- embedding-similarity
- embedding-store
- faiss
- golang
- hnsw
More in rag and vector databases
- RAGFlow A self-hosted knowledge base over company documents, with answers that cite their source.
- LlamaIndex Developers building document Q&A or data agents in Python or TypeScript.
- Qdrant The search layer behind a "chat with your documents" app.
- Chroma Adding document search to a prototype or small app with very little setup.
- Weaviate Search over your own content that mixes keyword matching with meaning-based matching.
No affiliate links on this page, and we are not paid by this project. The summary is our own plain-English description; check the repo for current features before you rely on it.
Stars, licences and commit dates come from the GitHub API, checked 16 Oct 2026. "Last commit" is the last push to the repo. Star counts are a rough popularity signal, not a quality score. There are no affiliate links in this section: links go straight to each project.