Lantern is the only database you need for your AI applications.

  • Built on top of Postgres - No need to integrate a new library, you can just write another SQL query. We support Postgres 11 - 16.
  • Fast index creation that scales to millions of vectors - Create an HNSW index for your data in minutes (see our blog post for benchmarks)
  • Create embeddings without worrying about infrastructure - With Lantern Cloud, simply select the model you’d like to use to embed your data, and we’ll handle the rest. No need to worry about finding the right library, switching languages, or handling API call failures
  • Coming Soon: Index hyperparameter optimization - With Lantern Cloud, we’ll automatically tune your index for you, so you don’t have to worry about finding the right set of parameters, and changing them over time

Getting Started

The easiest way to get started with Lantern is with Lantern Cloud. Lantern Cloud is a fully managed database offering with support for embedding generation and management.

Since Lantern is 100% open source, you’re welcome to self host Lantern (p.s don’t forget to ⭐ on Github). We offer multiple guides to get started, including Docker, binaries, and brew. For further customization, you can also build from source.


Check our Development Guide to learn more about how to use Lantern. With a single operator, you can query your vectors and your existing data together. We support multiple distance functions.


We welcome contributions! If you’re interested, check out our Contribution Guide for tips to get started.