NightmareNet

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without catastrophic forgetting. Dockerized, EU AI Act compliance reporting. Maintained by Adit-Jain-srm on GitHub, where it has earned 46 stars from the community.

It's actively developed around adversarial-robustness, adversarial-training, deep-learning, and is a solid reference for anyone building with these tools.