The farming sector plays a significant role in contributing to India’s economy, with a major portion of the population relying on agriculture as their primary source of livelihood. However, the agriculture sector faces numerous challenges in maintaining crop health due to several issues like weeds, diseases, and pests’ attacks that threaten overall productivity. Current solutions for addressing these issues are frequently limited in their effectiveness and practicality, particularly in complex field environments, which results in causing delays in identifying problems that influence timely crop management decisions, ultimately impacting productivity. This paper aims to propose a YOLOv9c-integrated lightweight mobile app for weed detection in a real field natural environment. As weeds are undesirable plants they have competition with the crops for vital nutrients, early detection will help to make timely decisions for precise spraying of herbicides. By using the advanced capabilities of YOLOv9c for fast, accurate object detection, the proposed application offers a user-friendly, lightweight solution that works efficiently on mobile devices, even in low-resource settings. The methodology utilizes a dataset acquired from real agricultural fields, to enhance sustainable practices in Indian agriculture landscape.