In reinforced concrete structures, the utilization of composite rebar has been increased by considering their high corrosion resistance, anti-magnetic properties, and significant tensile strength. According to the lower elasticity modulus of composite rebar in comparison with steel rebar, concrete beams reinforced including composite rebar possess a relatively lower shear strength by comparing with steel rebar. In addition, in concrete beam, reinforced shear failure by composite rebar is commonly brittle and requires precise performance prediction of the members. Thus, the reinforced concrete beams' shear strength by composite rebar is predicted utilizing an Extreme Learning Machine network based on Chaos Red Fox Optimization Algorithm (ELM-CRFOA) according to a wide range of data. The most important parameters, which are considered in this investigation, are the web width, beam effective depth, the strength of concrete compressive, the ratio of the shear span to depth, FRP longitudinal bars elasticity modulus, and ratio of the longitudinal reinforcement. This method's precision has been proved by having a comparison among the model predictions and the accumulated data and available shear design equations. According to the study outcomes, the presented model has precise outcomes in computing the concrete beams' shear strength in comparison with other existing relations. For assessing input parameters' impact on the FRP-reinforced concrete beams' shear strength, a sensitivity analysis is executed.