TusKANNy/kannolo

Official repository of the kANNolo library.

56
/ 100
Established

kANNolo is a specialized library for researchers and practitioners working with large datasets that need to find the most similar items quickly. It takes in collections of dense or sparse numerical representations (embeddings) and efficiently outputs the approximate nearest neighbors. This is ideal for anyone in academic or industrial research who develops or evaluates similarity search algorithms.

Use this if you are a researcher or engineer prototyping new approximate nearest neighbor search algorithms and need a flexible yet performant framework to test your ideas.

Not ideal if you are looking for an off-the-shelf solution for simple nearest neighbor lookup without the need to modify or develop new search algorithms.

information-retrieval similarity-search machine-learning-research data-mining algorithm-development
No Package No Dependents
Maintenance 13 / 25
Adoption 12 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

49

Forks

8

Language

Rust

License

MIT

Last pushed

Mar 26, 2026

Monthly downloads

35

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/TusKANNy/kannolo"

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