Coherence-Aware Reinforcement Learning (CARL) - breakthrough LLM post-training and test-time training paradigm. carl builds the world's most advanced and intelligent agent systems that are a step change over current gen agents
AmiPilot: object-level GUI automation for classic AmigaOS — point at, locate, click, type, drag, launch, screenshot, and wait on real windows/gadgets by role, label, or manifest ID over a wire protocol or MUI's own ARexx port, driven from Python or pytest, not by pixels
