docs: add metadata tags to README and ignore Python cache files

docs: update README with MemRL details and social links

fix: add dummy @spaces.GPU function and torch dependency for ZeroGPU startup

feat: migrate Whisper ASR and Gemma NLU to serverless Modal backend

fix: Add canonical-based MemRL lookup for true cross-language recall

fix(multilingual): Improve color extraction for Spanish/French in both server rule-based and client-side fallback

fix(demo): jsonBox now always contains pure actions array (for correction/preview editing)

fix: Gemma CPU fallback now reliably produces actions from canonical when model returns empty actions array

feat(hackathon-demo): Language-agnostic canonical templates + RAG for multilingual MemRL

feat: text shape support + preview-before-reinforce MemRL correction flow

fix: implement direct CPU fallback for Gemma generation when GPU nodes/CUDA are offline

feat: upgrade canvas to support multi-command lists, relative freehand paths, shape dragging, trace animations, and blueprint grids

feat: implement MemRL Audio Canvas with Whisper and Gemma 4

initial commit