Small-scale vendors in local markets face significant challenges in maintaining competitiveness and profitability due to limited access to advanced pricing tools and market insights. This research presents StreetSmart, an AI-powered dynamic pricing system tailored to the unique needs of small-scale vendors in the fruits and vegetables market. The system integrates real-time data on demand, seasonal trends, location-specific factors, and competitor pricing to generate optimal pricing strategies. By leveraging machine learning models, StreetSmart offers actionable insights, enabling vendors to dynamically adjust their prices, minimize losses, and maximize profitability. Our methodology involves collecting and preprocessing diverse datasets, training advanced machine learning algorithms, and integrating real-time data sources. The system’s core includes a pricing optimization engine that considers inventory levels, demand elasticity, and competitor price comparisons to provide data-driven recommendations. A user-friendly dashboard displays pricing insights and trends, empowering vendors with minimal technical expertise to make informed decisions. Experimental evaluation, including real-world pilot testing with vendors, demonstrates that the system reduces inventory wastage by 25%, increases vendor profitability by 22%, and enhances responsiveness to market dynamics. This research bridges gaps in existing literature by addressing the accessibility and usability challenges faced by small-scale vendors in adopting AI-driven pricing systems. The findings contribute to fostering equitable competition in local markets while promoting sustainable economic growth.