KMJ-007/VecPuff
vector database built on top of S3, inspired by turbopuffer
VecPuff helps developers experiment with and learn about building scalable vector search systems. It takes raw vector data, along with optional metadata, and stores it in a way that allows for efficient similarity searches. This project is ideal for engineers and architects looking to understand the underlying mechanics of vector databases built on cloud object storage.
Use this if you are a developer or architect interested in understanding and experimenting with the architecture of a scalable vector database, particularly one built on S3.
Not ideal if you need a production-ready vector database with extensive features, enterprise support, or a fully managed service.
Stars
8
Forks
—
Language
Rust
License
MIT
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/KMJ-007/VecPuff"
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