This study leverages a graph-based genetic algorithm (GB-GA) for the design ofefficient nitrogen-fixing catalysts as alternatives to the Schrock catalyst, with the aim toimprove the energetics of key reaction steps. Despite the abundance of nitrogen in theatmosphere, it remains largely inaccessible due to its inert nature. The Schrock catalyst,a molybdenum-based complex, offered a breakthrough but its practical application islimited due to low turnover numbers and energetic bottlenecks. The genetic algorithmin our study explores the chemical space for viable modifications of the Schrockcatalyst, evaluating each modified catalyst’s fitness based on reaction energies of keycatalytic steps and synthetic accessibility. Through a series of selection and optimizationprocesses, we obtained fully converged catalytic cycles for 20 molecules at the B3LYPlevel of theory. From these results, we identified three promising molecules, eachdemonstrating unique advantages in different aspects of the catalytic cycle. This studyoffers valuable insights into the potential of generative models for catalyst design. Ourresults can help guide future work on catalyst discovery for the challenging nitrogenfixation process.