Progressive growth: brain grows a layer every 2nd dream (identity-init, params 348k→~908k), shown live

Fix mode-collapse: repetition penalty, typed praise=feedback (not vocab), seed-anchored stable training, gentler lr; newborn babbles before first dream

Wire the missing Dream button into the UI

Add MoodNet (2nd tiny model): 40 affect-anchored moods drive speech + behavior; energy/dream loop

DREAM beat: deferred learning — babble while awake, fine-tune on dream

Drop unused numpy; requirements now just torch

Full pivot: from-scratch char-level baby that learns to talk + personality/evolution (CPU, off-grid)

Single-chat UI (teach by talking), graceful GPU fallbacks, synth at sleep

Route all GPU ops through one @spaces.GPU dispatcher (ZeroGPU multi-fn CUDA fix)

ZeroGPU-safe brain: single-purpose GPU workers, disk adapter handoff, teach-time Q synthesis

Fix Gradio 6 API: drop Chatbot type arg, move theme to launch()

Dreamling MVP: teach (RAG) + sleep (LoRA) → recall from weights

initial commit