mariotoffia/goannoy

go native port of annoy. Approximate Nearest Neighbors in optimized for memory usage and loading/saving to disk.

48
/ 100
Emerging

This is a Go-native library designed for efficiently finding items that are similar to a given item, often called approximate nearest neighbor search. You provide numerical representations (embeddings or vectors) of your data, and it quickly finds the most similar items. It's built for developers working with Go applications who need to implement features like recommendation systems or data clustering.

Use this if you are a Go developer building applications that require fast and memory-efficient approximate nearest neighbor search, such as for recommendation engines or data clustering, and prefer a pure Go solution.

Not ideal if you are not a Go developer or need an exact nearest neighbor search, which might be more computationally intensive but guarantees the absolute closest results.

Go-development recommendation-systems data-clustering search-algorithms embedding-storage
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

19

Forks

6

Language

Go

License

Apache-2.0

Last pushed

Feb 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mariotoffia/goannoy"

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