ThinkMem: Instructions file for Claude Code

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

THINK-MEM is an AI memory management system for LLMs, providing multiple memory types and communication protocols. It's built as an MCP (Model Context Protocol) server with both stdio and HTTP modes.

Core Architecture

The system provides three types of memory storage for LLMs:

Memory Types

• RawMemory: Unstructured text with summary management and line-level operations
• ListMemory: Ordered collections that can function as arrays, deques, or stacks
• GraphMemory: Graph/knowledge graph structures (planned but not yet implemented)

Key Components

• MCP Server (src/server/ThinkMemServer.ts): Handles stdio protocol communication
• StreamableHTTP Server (src/server/HttpServer.ts): Web API with real-time events
• Memory Management (src/memory/): Core memory implementations
• Storage Layer (src/storage/): JSON file persistence with proper locking
• Utilities (src/utils/): Text processing and error handling

Development Commands

Build and Development

# Install dependencies
npm install

# Build TypeScript to JavaScript
npm run build

# Development mode (stdio)
npm run dev

# Production start (stdio mode by default)
npm start

# HTTP mode with custom port
npm start -- --mode http --port 8080

# Code linting
npm run lint

# Version synchronization (auto-runs after npm version)
npm run postversion

Testing

# Run all tests
npm test

# Run specific test pattern
npm test -- --testNamePattern="RawMemory"

# Run tests in watch mode
npm test -- --watch

# Generate coverage report
npm test -- --coverage

# Run tests with CI-like clean install
npm ci && npm test

Key Design Patterns

Dual Operation Modes

• Stdio Mode: MCP protocol over stdin/stdout for AI assistant integration
• HTTP Mode: StreamableHTTP for web applications and multi-client support