Nowadays, manufacturing enterprises face enormous environmental challenges, due to complex and diverse economic trends, including shorter product life cycles, rapid advances in science and technology, increased diversity in customer demands and globalization of production activities. Consequently, the cost is highly affected by environmentally related factors. Energy efficiency is one of the main factors, which together with waste management, affect manufacturing decisions. The complexity and diversity of the factors that determine energy efficiency require intelligent systems for their optimization at each “manufacturing level”. Manufacturing decisions should be taken as fast as possible and with the highest possible accuracy. Artificial intelligence/machine learning tools have made significant progress during the last decade and are suitable for such applications. The main objective of the current study is that an architecture for the development of a networked, online, decision support tool, be provided towards achieving sustainable value chain management. The main idea behind the proposed design is that stakeholders be assisted in taking decisions towards improving the energy and eco-efficiency of the entire value chain or parts of it. This is suggested within the context of a multi-objective optimization procedure, taking into account other important decision making attributes, such as flexibility, quality and time for the final reduction in the overall cost. This architecture incorporates real time information modules that interact with online monitoring systems, using any available information within the value chain and the existing IT tools. A partial realization of the proposed idea is implemented in the form of a user friendly software tool (the MetaCAM tool). This based, decision support tool aiming to optimize a current production line or to propose alternatives for the manufacturing of a product. The tool performs optimization based on a set of predefined criteria, namely energy, waste, cost and time. For each of these criteria, the end-user selects the desired weight factor in order to drive the optimization procedure accordingly. The tool presents the characteristics of the setup of the proposed optimized line and maintains all used data and calculations in order to be reused when necessary.. For the tool’s validation, three real case studies from different industrial sectors have been used. The first case study comes from the domestic appliances sector (refrigerator door panel), the second one from the automotive sector (a two seat bench for light commercial vehicles) and finally, the third case study derives from the aeronautics sector and deals with the production of the loading ramp hinge of a military aircraft.