Show HN: Adaptive Recall, persistent memory for AI assistants over MCP

Adaptive Recall is a memory API for AI assistants that goes beyond standard vector search by using cognitive science and machine learning to improve retrieval quality over time. It features four parallel retrieval strategies, automatic knowledge graph construction, memory lifecycle management, and self-improving ML models that learn from usage patterns. The system is available as a free tier with 500 memories and works via MCP integration or HTTP REST API.