Adaptive Recall - Self-learning persistent memory for AI assistants over MCP

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

Adaptive Recall transforms static data storage into a dynamic, self-improving memory system for AI applications. Powered by cognitive science and machine learning, it goes beyond standard vector search by running four parallel retrieval strategies and automatically constructing knowledge graphs. Unlike traditional databases, memories evolve, gain confidence through evidence, and fade naturally when unused. With a simple API supporting MCP for tools like Claude Code, developers can build assistants that learn from every interaction, ensuring retrieval quality improves automatically over time without manual tuning.

"Memories are not static rows in a database; they progress through stages, gain or lose confidence based on corroborating evidence, and fade naturally when no longer accessed."