An open-source UI-focused agent framework that translates natural language user requests into actionable operations on Windows OS.
UFO is an innovative open-source framework developed by Microsoft that enables seamless interaction with Windows applications through natural language commands. By leveraging advanced visual language models, UFO employs a dual-agent system to observe and analyze graphical user interfaces (GUIs), allowing it to navigate and operate within individual or multiple applications to fulfill user requests. Enhanced by Retrieval Augmented Generation (RAG) from diverse sources, including offline help documents and online search engines, UFO acts as an application 'expert,' automating complex tasks and improving user productivity.
We use cookies to enhance your experience. By continuing to use this site, you agree to our use of cookies. Learn more