OpenDesk AI: An Intelligent Desktop Assistant for Natural Language-Based File Search, System Monitoring, and Task Automation
Year: 2026
Type: article
Abstract: Modern computer operating systems require users to navigate multiple menus, folders, and applications to complete everyday tasks. This process can be time-consuming and challenging, especially for users with limited technical knowledge. This research paper presents OpenDesk AI, an intelligent desktop assistant designed to simplify computer interactions using Natural Language Processing (NLP). The system allows users to perform tasks such as searching for files, monitoring CPU and memory usage, managing applications, and automating routine desktop activities through natural language commands. OpenDesk AI follows a local-first architecture, where user data and system operations are processed locally to improve privacy, security, and response speed. The proposed system uses intent recognition and entity extraction to understand user commands and execute the corresponding operations through operating system interfaces. It combines natural language understanding with system monitoring and task automation to provide a more accessible and efficient computing experience. The experimental results reported in this study show an intent classification accuracy of 94.6% and task execution time reductions ranging from 84% to 89.12% compared with traditional manual operations. These findings suggest that OpenDesk AI can improve user productivity, reduce repetitive manual work, and provide a practical approach to privacy-focused desktop automation. Keywords: Desktop Automation, Artificial Intelligence, Natural Language Processing, Intent Recognition, Semantic File Search, System Monitoring, Local-First Architecture, Human-Computer Interaction.
Institution: MIT Art, Design and Technology University
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7236724371
