What is MyScaleDB used for?

MyScaleDB is an open-source SQL vector database built on ClickHouse, combining vector search, full-text search and analytics for AI applications. It is a good fit for retrieval-augmented generation backends, image and similarity search, and combining analytics with vector search in SQL.

Is MyScaleDB open source?

Yes. MyScaleDB is open source under the Apache-2.0 licence. Its source code is on GitHub at myscale/MyScaleDB and is written mainly in C++.

Yes. MyScaleDB is open source, so the software itself is free to use. A managed cloud version is also available.

Can I self-host MyScaleDB?

Yes. MyScaleDB can be self-hosted on your own server or infrastructure.

What is MyScaleDB an alternative to?

MyScaleDB is an open-source alternative to Pinecone. Other open-source alternatives to Pinecone include Milvus, Qdrant and Chroma.

Is MyScaleDB actively maintained?

The most recent commit to MyScaleDB was on 5 February 2025. The project has 1k stars on GitHub.

MyScaleDB: open-source alternative to Pinecone

About MyScaleDB

MyScaleDB is a database that adds high-performance vector search and full-text search to ClickHouse, so developers can build retrieval-augmented generation and other AI applications using ordinary SQL. It is a fork of ClickHouse rather than a separate service layered on top, and it keeps the OLAP architecture that makes ClickHouse suited to large datasets.

Because it speaks SQL, queries can combine vector similarity, metadata filters and joins across tables, which the project says improves RAG accuracy compared with filtering after retrieval. It manages structured data, text, vectors, JSON, geospatial and time-series data in one system, and the README stresses scalability as data grows.

The source code is released under Apache-2.0 and can be self-hosted. A managed offering, MyScale Cloud, runs MyScaleDB with extra premium features at billion-scale and is positioned against specialized vector databases that use custom APIs. It suits teams already comfortable with SQL who want one system for vectors and analytics.

Key features

SQL interface with vector-related functions
Vector search with metadata filtering
Full-text search alongside vectors
SQL-vector join queries
Built on the ClickHouse OLAP architecture
Supports JSON, geospatial and time-series data

Good fit for

→Retrieval-augmented generation backends
→Image and similarity search
→Combining analytics with vector search in SQL

Built with: C++
Tags: vector-database; sql; clickhouse; vector-search; full-text-search; rag; ai; similarity-search

MyScaleDB: questions and answers

What is MyScaleDB used for?: MyScaleDB is an open-source SQL vector database built on ClickHouse, combining vector search, full-text search and analytics for AI applications. It is a good fit for retrieval-augmented generation backends, image and similarity search, and combining analytics with vector search in SQL.
Is MyScaleDB open source?: Yes. MyScaleDB is open source under the Apache-2.0 licence. Its source code is on GitHub at myscale/MyScaleDB and is written mainly in C++.
Is MyScaleDB free?: Yes. MyScaleDB is open source, so the software itself is free to use. A managed cloud version is also available.
Can I self-host MyScaleDB?: Yes. MyScaleDB can be self-hosted on your own server or infrastructure.
What is MyScaleDB an alternative to?: MyScaleDB is an open-source alternative to Pinecone. Other open-source alternatives to Pinecone include Milvus, Qdrant and Chroma.
Is MyScaleDB actively maintained?: The most recent commit to MyScaleDB was on 5 February 2025. The project has 1k stars on GitHub.