Plain-AyI
← All projects
Developer building blocks

turbovec

A compact, fast way for programs to search large collections of AI data by meaning, using far less memory.

Research-backed

What it does

turbovec is a code library for searching vectors, the lists of numbers AI tools use to represent the meaning of text or images. It's the kind of search behind "find similar" features and document chatbots.

It squeezes each vector into a much smaller form using a research method called TurboQuant, and searches that compressed form directly. Its makers say this uses many times less memory and searches faster than the widely used FAISS library, with similar accuracy.

It runs inside your own program, so no data leaves your machine. You can add and remove items at any time without rebuilding, and filter results.

Who it's for

Developers building AI search or memory features who need to handle many items on limited hardware.

Can I use it without coding?

Developers only. A Python and Rust library used by writing code. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it