According to a post summarizing an NVIDIA paper, Agora uses Git records and an index of open branches and verified claims to coordinate research agents. In the reported test, 13 LLM workers ran for nearly 12 days without assigned tasks or a central planner, posting 1,703 contributions. Their task was to initialize a 119.6-million-parameter hybrid model from 141 donor models without training data or gradient updates. The summary reports that they lowered the evaluator score from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M, and that all 165 independent reproductions succeeded.