Fast Search on Millions of Vectors

AnnDB is a distributed approximate nearest neighbors database that scales to millions of high-dimensional vectors.



AnnDB shards the data to horizontally scale to hundreds of servers.


Map-Reduce like search allows us to achieve low-latency and high throughput.


Synchronous replication means we never loose a bit of your data.

Vector search

Have your own vectors? We can help you organise them.

Image search

Provide next-generation search experience in your products.

Document search

Search documents by their semantic meaning not just the text they contain.

Get in touch

Want to hear from us?

We will let you know as soon as we launch.