Embeddings
Libraries that turn text and other data into embedding vectors.
Start here
The Featured projects with the most downloads.
-
fastembed-rs
Library for generating vector embeddings, reranking locally.
1.1M downloads (30 days) Latest release: 7.6.1, 6 Nov 2026
-
model2vec-rs
Official Rust Implementation of Model2Vec
194k downloads (30 days) Latest release: 0.4.0, 30 Oct 2026
All projects
Order: strongest tier first, then most downloads, then name, with unmeasured values last. A library counts downloads over 30 days. An app counts binary downloads per release. An app with none counts its crate downloads over 30 days.
What do the tiers mean?
- Featured
- Shown first. It passes every Featured gate.
- Listed
- Shown in the normal listing. No other tier applies.
- New
- A project whose first release is recent.
- Archived
- No longer maintained, or ended by its author.
Tiers come from published rules over raw signals. Stars alone never qualify a project.
Active dependents: crates from other owners that depend on this project in a current release. One owner counts at most once.
Movement needs more history.
| Project | Downloads | Dependents | Stars | Latest release | Runs on (GPU) | Native code | License |
|---|---|---|---|---|---|---|---|
| Featured 2 projects | |||||||
|
fastembed-rs Featured
Library for generating vector embeddings, reranking locally. |
1,147,765 downloads over 30 days | 331 | 1,051 | 7.6.1 | CUDA, WebGPU, Metal | Binds native code: accelerate-src (feature accelerate), intel-mkl-src (feature mkl), ort-sys (feature directml) | Apache-2.0 |
|
model2vec-rs Featured
Official Rust Implementation of Model2Vec |
194,422 downloads over 30 days | 48 | 234 | 0.4.0 | GPU support unknown | No native code found | MIT |
| Listed 9 projects | |||||||
|
fasttext-rs Listed
fastText pure Rust implementation |
102,405 downloads over 30 days | 4 | 71 | 0.8.1 | GPU support unknown | Binds native code: cfasttext-sys, cfasttext_static. Build uses a native toolchain: cc | MIT |
|
Optimized vector quantization for dense vectors |
5,567 downloads over 30 days | 4 | 7 | 0.9.0 | GPU support unknown | Binds native code: accelerate-src (feature accelerate-test), lapack-sys (feature opq-train) | Apache-2.0 |
|
Reader and writer for common word embedding formats |
5,203 downloads over 30 days | 6 | 105 | 0.18.0 | GPU support unknown | Binds native code: accelerate-src (feature accelerate), intel-mkl-src (feature intel-mkl), netlib-src (feature netlib), openblas-src (feature openblas) | Apache-2.0 OR MIT |
|
Rust interface to word2vec. |
59 downloads over 30 days | 1 | 32 | 0.3.3 | GPU support unknown | No native code found | MIT |
|
Train/use word embeddings with subword units |
24 downloads over 30 days | 0 | 90 | 0.9.4 | GPU support unknown | No native code found | Apache-2.0 OR BlueOak-1.0.0 |
|
rust-sbert Listed
Rust implementation of Sentence Bert (SBert) |
10 downloads over 30 days | 0 | 127 | 0.4.1 | CUDA | Binds native code: torch-sys | Apache-2.0 |
|
Cleora AI is a general-purpose open-source model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data. Created by Synerise.com team. |
0 binary downloads per release | Not applicable | 545 | Not measured | Not measured | Not measured | |
|
A library that provides the ability to convert tokens into embeddings, as well as to encode their positions |
0 downloads over 30 days | 0 | 9 | 1.0.1 | GPU support unknown | No native code found | MIT |
|
pure rust implemention of word2vec |
Not measured | Not applicable | 87 | Not measured | Not measured | Not measured | None stated |