Anti-RAG dual-whitebox memory for LLM agents. 2.72 MB SQLite + Markdown kernel, no vector DB, no embeddings. Lifts qwen2.5:7b from 1.79% to 60.71% on NoLiMa-32k (+58.9pp), 88.71% on LV-Eval EN 256k, 84.8% on LongMemEval-S. Restart-safe, concurrency-bullet-proof, 100% transparent.
agent memory sqlite mcp memory-management obsidian hallucination rag ai-agent llm long-context langchain local-llm ollama context-window qwen longmemeval vector-database-alternative nolima lv-eval
-
Updated
May 10, 2026 - Python