DAEMLABS
AI-powered desktop scheduler merging OS algorithms, Agentic AI & XGBoost. Natural language task entry with real-time conversational adjustments.
Modern task scheduling tools fail to adapt to human complexity—they lack intelligent negotiation for missing task parameters, cannot recommend optimal scheduling strategies dynamically, and offer no conversational interface for real-time schedule adjustments, leaving users overwhelmed by rigid, one-size-fits-all planners.
We bridge operating system CPU scheduling algorithms (FCFS, SJF, SRTF, RR, Priority, EDF) with human productivity through an Agentic AI pipeline. A multi-agent system (Negotiator, Planner, Chatbot) powered by Groq's Qwen-3-32b validates natural language tasks, suggests breakdowns, and enables conversational timeline edits. An XGBoost classifier trained on 20,000+ synthetic scheduling simulations predicts the optimal algorithm and Round Robin quantum based on workload features, while a React + Electron desktop GUI delivers real-time Gantt visualization.
91% accuracy in optimal algorithm prediction via XGBoost + SMOTE
65% faster task entry through NLP & automated validation
Sub-second chat responses for real-time schedule edits
Side-by-side Gantt comparing manual vs. AI-suggested schedules
Cross-day task splitting for workflows spanning midnight
Feedback logging enabling future RL personalization