nubskr/satoriDB
High performance embedded vector database
Employs a two-tier HNSW routing layer (quantized bucket centroids in RAM) paired with parallel disk-based bucket scanning via CPU-pinned Glommio workers with io_uring, enabling billion-scale ANN search without holding entire datasets in memory. Vectors are automatically clustered via k-means with dynamic rebalancing, and all distance computations use SIMD (AVX2/AVX-512) acceleration. Built as an in-process Rust library targeting Linux (kernel 5.8+) with configurable fsync durability and both sync/async APIs.
201 stars.
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...
lightonai/fast-plaid
High-Performance Engine for Multi-Vector Search