AgentKits Memory

Provides persistent memory capabilities for coding assistants by automatically capturing tool usage, decisions, and patterns across sessions in a local SQLite database with hybrid search combining keyword and semantic similarity.

AgentKits Memory provides persistent memory capabilities for AI coding assistants through a comprehensive MCP server implementation that captures, stores, and retrieves project context across coding sessions. Built by AityTech, it automatically hooks into Claude Code sessions to capture tool usage observations, decisions, and patterns, storing them in a local SQLite database with optional vector search capabilities using offline embeddings via Transformers.js. The system includes hybrid search combining keyword and semantic similarity, token economics tracking to measure memory ROI, and multiple interfaces including CLI tools, web viewer, and direct MCP integration.