nubskr/satoriDB
High performance embedded vector database
SatoriDB helps applications quickly find the most similar items within enormous datasets, even those too large to fit in your computer's memory. It takes in large collections of 'vectors' (numerical representations of items like product images, documents, or user preferences) and lets you query for the nearest matches to a new item. This is ideal for developers building search, recommendation, or data retrieval systems that need to handle billions of items locally within their application.
201 stars.
Use this if you need to build an application with extremely fast similarity search capabilities over datasets containing billions of data points directly within your service, without relying on external database servers.
Not ideal if your application requires a distributed database system for horizontal scaling across multiple machines or if you prefer a managed service.
Stars
201
Forks
13
Language
Rust
License
MIT
Category
Last pushed
Jan 24, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/nubskr/satoriDB"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
databendlabs/databend
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from...
oceanbase/oceanbase
The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.
matrixorigin/matrixone
MySQL-compatible HTAP database with Git for Data, vector search, and fulltext search....
ArcadeData/arcadedb
ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB...
datalevin/datalevin
A simple, fast and versatile Datalog database