Modern supply chain management relies critically on accurate inventory forecasting to minimizeholding costs and prevent stockouts. However, traditional predictive models often struggle withcomplex, multivariate demand patterns, and state-of-the-art deep learning approaches frequentlysuffer from a "black-box" nature, limiting their adoption in operational decision-making. Toaddress this gap, this project introduces "Smart Inventory, " a hybrid Decision Intelligence framework that integrates deep learning-based multivariate time-series forecasting with Large Language Model (LLM)driven explainability. The core predictive engine utilizes Poarch-based Long Short-TermMemory (LSTM) neural networks to forecast future demand across multiple variables.To bridge the gap between complex mathematical outputs and human operations, thesystem employs an LLM integration to translate numerical forecasting thresholds into actionable,human-readable purchasing insights. The framework is deployed as a full-stack architecture,featuring a highly responsive Next.js frontend dashboard and a scalable Python Fast API backend.Furthermore, the system incorporates a resilient, automated SMTP alert mechanism for proactivelow-stock management, engineered with robust fallback protocols for cloud deploymentconstraints. Ultimately, this framework provides a comprehensive decision support system that notonly delivers high-fidelity demand predictions but also fosters user trust through Explainable AI.