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.
Performs inference using ONNX Runtime via the `ort` crate and HuggingFace tokenizers for fast token encoding, enabling synchronous (non-async) embedding generation without external dependencies. Supports 25+ pre-trained text embedding models from BAAI, Sentence Transformers, and others, plus sparse embeddings, image embeddings, and reranking—with quantized variants and optional Candle backend support for advanced models like Qwen3.
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