is a fast, dataset-agnostic, deep visual search engine for digital art history based on neural network embeddings. Its main feature is the concept of "re-search": results from a search can immediately form the basis of another search. This allows the intuitive exploration of an image corpus, while results are continuously refined. utilizes modern approximate k-NN algorithms via Spotify's Annoy library to deliver fast search results even for very large datasets in low-resource environments. It is currently in beta and will be made available under an open source license. Sign up for a beta test account here (requires approval).

Watch Peter Bell's art historical introduction: German / English is developed by Fabian Offert, with contributions by Peter Bell and Oleg Harlamov. Get in touch at