rembed is an open-source Go tool and library for running text-embedding models locally. It supports BERT-style encoders and decoder-derived embedders without cgo or ONNX Runtime, enabling developers to ship static binaries with embedded inference.
In the Inference & model serving space, rembed takes a focused approach. It focuses on running text-embedding models without cgo, ONNX Runtime, or complex native dependencies. rembed is an open-source project aimed at developers building local or embedded AI applications. rembed is open source under the Open Source license. rembed is available on the command line, and it can be self-hosted.
It is developed by Rostam Labs. Key capabilities include text embeddings, BERT inference, and decoder embedders.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match