Karpathy Autoresearch Hits 66K GitHub Stars — Red Hat Runs 198 Experiments Zero Intervention on OpenShift AI in 24 Hours

Red Hat Developer·medium signal

Red Hat published an April 7 case study running Karpathy's autoresearch framework on OpenShift AI: 198 experiments, 29 kept, 2.3% validation loss improvement, zero human intervention in 24 hours. The project has grown from 21K stars at March launch to 66K+ stars and 9,600 forks. The Red Hat deployment demonstrates the pattern works at enterprise scale — an AI agent autonomously designing, running, and evaluating ML experiments on standard cloud infrastructure.