Fix: Lower default similarity_threshold to 0.10 for hash embeddings

v4: SLM-inspired architecture with three-tier memory, neural links, self-tuning

v3 TUNED: All bottleneck fixes + optimized threshold (0.45)

Update mcp_server.py with smart injection and real embeddings

Update app.py with smart injection and real embeddings

Update requirements.txt with smart injection and real embeddings

Update README.md with smart injection and real embeddings

Update mnemo.py with smart injection and real embeddings

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload requirements.txt with huggingface_hub

Upload README.md with huggingface_hub

Upload mnemo.py with huggingface_hub

initial commit