AMP (Agent Memory Protocol)

Provides local-first persistent memory with episodic and semantic storage, enabling context retention across sessions and knowledge graph building from conversations.

AMP (Agent Memory Protocol) provides AI agents with persistent memory capabilities through a three-layer architecture mimicking human cognition: short-term memory for immediate context, long-term memory for consolidated insights, and a graph layer for entity relationships. Built with SQLite for storage and FastEmbed for local embeddings, it features hybrid vector and full-text search without requiring cloud APIs. Includes an interactive web dashboard with real-time semantic cluster visualization using D3.js physics simulation, showing how memory nodes cluster by meaning and topological connections between related concepts. Supports natural language querying with relevance scoring and memory consolidation processes that move thoughts from working memory to long-term storage.