<p>The integration of network pharmacology with computational tools in <i>in-silico</i> research on antidiabetic herbs provides a comprehensive understanding of the therapeutic potential of these herbs. As the global burden of diabetes continues to rise, there is increasing interest in identifying novel therapeutic agents from herbal sources to treat diabetes. By combining the principles of network pharmacology with computational methods such as molecular docking, molecular dynamics, and omics technologies, along with advancements in generative artificial intelligence and machine learning, researchers can effectively identify molecular targets, explore herb‒compound‒target networks, and investigate the synergistic effects and polypharmacology of the herbs. Unlike existing literature, this review uniquely consolidates a wide range of computational approaches and tools, offering a unified framework that bridges traditional herbal medicine with modern computational innovations. This review highlights the key steps in <i>in-silico</i> drug discovery and compiles computational tools and their features focusing on their application in predicting drug-target interactions, optimizing drug-likeness, and assuming ADMET properties. The <i>in-silico</i> approaches comprehensively contribute to a deeper understanding of the mechanism of actions of antidiabetic herbs and offer promising avenues for future drug development.</p> Graphical Abstract <p></p>