MCP server that enables persistent, hybrid, local memory for LLM agents, with vector + BM25 search, knowledge graph, and policy-driven retention, providing token-budgeted context injection for AI assistants.
A local-first MCP server that gives AI clients a shared, user-owned memory and skills plane, enabling persistent memory across apps via the Model Context Protocol.
A deterministic, local-first memory engine for AI assistants that provides versioned context management via MCP, enabling token-budgeted context patches with provenance and explainability.