Epsilla VectorDB

Open source

Open-source vector database written in C++ for scalable embedding search with hybrid dense and sparse queries, metadata filtering and LangChain integrations.

Open-source alternative to

epsilla.com
Epsilla VectorDB homepage screenshot
GitHub stars
874
Last 30 days
+0
Last commit
1 mo ago
Repository age
3 years
Version
v0.3.16
Licence
GPL-3.0
Self-hosted
Yes

About Epsilla VectorDB

Epsilla is an open-source vector database focused on scalability, high performance and cost-effective vector search. It is designed to connect information retrieval with memory for large language models, so developers building retrieval-augmented generation systems can store embeddings and query them quickly. The core is written in C++ and uses parallel graph traversal techniques for indexing, which the project says is faster than HNSW at comparable precision.

It behaves like a complete database management system, with familiar database, table and field concepts where a vector is just another field type. Features include production-scale similarity search, metadata filtering, hybrid search combining dense and sparse vectors, built-in embedding support for natural-language search, and a cloud-native design with compute and storage separation, serverless operation and multi-tenancy. Integrations cover LangChain and LlamaIndex, and clients are available for Python, JavaScript and Ruby along with a REST API.

You can run the backend in Docker and talk to it from the Python client, or use Epsilla as a Python library without Docker by building the bindings. A managed Epsilla Cloud vector database service is offered and marked experimental. The code is licensed under GPL-3.0.

Key features

  • Vector similarity search for embeddings
  • Hybrid dense and sparse search
  • Metadata filtering
  • Database, table and field data model
  • Built-in embedding support
  • LangChain and LlamaIndex integrations
  • Python, JavaScript and Ruby clients

Good fit for

  • Powering retrieval for LLM applications
  • Running semantic search over embedded documents
Built with
C++ tools
Tags
vector-database
embeddings
rag
llm
similarity-search
cpp
hybrid-search
ai-infrastructure

Epsilla VectorDB: questions and answers

What is Epsilla VectorDB used for?
Epsilla VectorDB is an open-source vector database written in C++ for scalable embedding search with hybrid dense and sparse queries, metadata filtering and LangChain integrations. It is a good fit for powering retrieval for LLM applications and running semantic search over embedded documents.
Is Epsilla VectorDB open source?
Yes. Epsilla VectorDB is open source under the GPL-3.0 licence. Its source code is on GitHub at epsilla-cloud/vectordb and is written mainly in C++.
Is Epsilla VectorDB free?
Yes. Epsilla VectorDB is open source, so the software itself is free to use. A managed cloud version is also available, with paid plans from $29 per month.
Can I self-host Epsilla VectorDB?
Yes. Epsilla VectorDB can be self-hosted on your own server or infrastructure.
What is Epsilla VectorDB an alternative to?
Epsilla VectorDB is an open-source alternative to Pinecone. Other open-source alternatives to Pinecone include Infinity, Qdrant and Milvus.
Is Epsilla VectorDB actively maintained?
Yes. The most recent commit to Epsilla VectorDB was on 4 October 2026, and the latest release is v0.3.16, published on 9 March 2025. The project has 874 stars on GitHub.

Open-source alternatives to Epsilla VectorDB

See all

SaaS alternatives to Epsilla VectorDB

See all