nubskr/satoriDB

High performance embedded vector database

44
/ 100
Emerging

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.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 11 / 25

How are scores calculated?

Stars

201

Forks

13

Language

Rust

License

MIT

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.