OpenAI-compatible proxy that keeps LLM agent context small: it injects relevant memories instead of the full chat history (−51% tokens on real traffic). Local, beta.
reactive-programming home-assistant hippocampus neocortex rag local-first self-correcting hacs-integration llm vector-symbolic-architecture agent-memory programmable-memory vector-symbolic-ai retrieval-cache agent-nursery memory-proxy gpu-agent-memory graph-vm
-
Updated
Nov 15, 2026 - Python