In many real-world applications (e.g., human-robot collaboration), the environment changes rapidly, and the intended path may become invalid due to moving obstacles. In these situations, the robot should quickly find a new path to reach the goal, possibly without stopping. Planning from scratch or repairing the current graph can be too expensive and time-consuming. This paper proposes a path replanner, MARS, that enables a robot to move in dynamic environments with unpredictable obstacles. The method exploits a set of pre-computed paths to compute a new solution in a few hundred milliseconds when an obstacle obstructs the robot's way. It enhances the search speed using informed sampling and improves the current solution in an anytime fashion to make the robot reactive to environmental changes. In addition, the paper presents a multithread architecture, applicable to several replanning algorithms, to handle the execution of the robot's trajectory with continuous replanning and the collision checking of the traversed path. The paper compares state-of-the-art sampling-based path-replanning algorithms in complex and high-dimensional scenarios, showing that MARS is superior in terms of success rate and quality of solutions found. An open-source ROS-compatible implementation of the algorithm is also provided.