fastembed-rs and hypembed
These are **competitors**: both provide local-first text embedding inference in Rust, with fastembed-rs offering a more mature implementation supporting multiple embedding models via ONNX, while hypembed focuses specifically on BERT-compatible models.
About fastembed-rs
Anush008/fastembed-rs
Rust library for vector embeddings and reranking.
This is a Rust library that helps developers add advanced search and information retrieval capabilities to their applications. It takes text or images as input and converts them into numerical 'embeddings,' which are mathematical representations that capture meaning. These embeddings can then be used to find similar text or images, or to re-rank search results for better relevance. It's intended for Rust developers building intelligent applications.
About hypembed
neuralforgeone/hypembed
Pure-Rust BERT-compatible text embedding inference for local-first applications.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work