epsilla-cloud/vectordb

Epsilla is a high performance Vector Database Management System

45
/ 100
Emerging

Implements hybrid dense-sparse vector search with built-in embedding support and metadata filtering, enabling natural language queries without separate embedding pipelines. The C++ core uses parallel graph traversal algorithms optimized for vector indexing, achieving 10x faster performance than HNSW at 99.9%+ precision. Integrates with LangChain and LlamaIndex, offers Python/JavaScript/Ruby clients plus REST API, and supports cloud-native deployment with compute-storage separation.

871 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

871

Forks

43

Language

C++

License

GPL-3.0

Last pushed

Nov 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/epsilla-cloud/vectordb"

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