Chemical and material technologies underpin countless industrial and consumer applications—from healthcare and agriculture to electronics and manufacturing. Yet the sheer number of chemicals in use—and the gaps in safety data for many of them—raises significant health and environmental concerns. To manage and mitigate such risks, regulators and scientists need clear, comprehensive information on how and where specific chemicals are applied and when exposure might occur. Unfortunately, that information is often scattered across diverse scientific and regulatory sources, making it difficult to assemble a complete picture. Therefore, our project aims to build an open‐access, automated and scalable “toolbox” that deploys cheminformatics and machine‐learning workflows to automatically extract chemical and material use information from diverse unstructured text sources (such as books, patents), which can then be harmonized. This information can support safety assessment and inform regulatory decisions, including identifying alternatives to problematic chemicals and materials. To do so, we have developed a two-stage natural language processing (NLP) framework based on large language models. In a first step, we have fine-tuned an open-source large language model to recognize the chemical names from any text. Then, we have further fine-tuned the model to recognize “chemical-use” information pair. As such, we have built a fully automated pipeline that can mine “chemical-use” information from any text. Using this foundation, our toolbox can help extract and establish a rich dataset linking each chemical to its applications. Looking ahead, we are currently working on improving the model performance, construct the chemical-use database and clean the database through expert and machine-based methods, for sharing both with the broad regulatory and scientific communities.