You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.
Lightweight 3-tier memory and context management for AI agents. Token-budget-aware, SQLite-backed, zero-config. Works with Claude, OpenAI, or any LLM agent system.