Each claim in a research paper requires all relevant prior knowledge to be\ndiscovered, assimilated, and appropriately cited. However, despite the\navailability of powerful search engines and sophisticated text editing\nsoftware, discovering relevant papers and integrating the knowledge into a\nmanuscript remain complex tasks associated with high cognitive load. To define\ncomprehensive search queries requires strong motivation from authors,\nirrespective of their familiarity with the research field. Moreover, switching\nbetween independent applications for literature discovery, bibliography\nmanagement, reading papers, and writing text burdens authors further and\ninterrupts their creative process. Here, we present a web application that\ncombines text editing and literature discovery in an interactive user\ninterface. The application is equipped with a search engine that couples\nBoolean keyword filtering with nearest neighbor search over text embeddings,\nproviding a discovery experience tuned to an author's manuscript and his\ninterests. Our application aims to take a step towards more enjoyable and\neffortless academic writing.\n The demo of the application (https://SciEditorDemo2020.herokuapp.com/) and a\nshort video tutorial (https://youtu.be/pkdVU60IcRc) are available online.\n