基于 KuzuDB 的内存库，用于使用 TypeScript 构建的代码代理，并遵循 MCP 协议
概览
一种基于 TypeScript 实现的分布式内存银行，作为 MCP（模型上下文协议）工具，存储内存在具备存储库和分支过滤功能。分支隔离通过使用图唯一标识符实现，实现集中存储库，同时支持仓库特定和分支视图。完全符合 MCP 规范，实现与集成环境（IDE）和 AI 代理的无缝集成。 - - 高级推理模型（OpenAI o3/o4-mini，Claude 4）支持MCP采样，用于智能内存管理 - - 自动快照系统，保证回滚功能 - - MCP采样分析实际内存状态以制定自适应优化策略 - - 12个整合工具涵盖所有内存库操作 - - 确保每个资源仅实例化一次，且线程安全良好 - - 遵循高级内存库规范，使用KùzuDB图 - - 所有操作均按仓库名称和分支进行上下文化 - - 用途......
概述（AI 翻译）
一种基于 TypeScript 实现的分布式内存银行，作为 MCP（模型上下文协议）工具，将内存存储在具备仓库和分支过滤功能的 **KùzuDB 图数据库中。分支隔离通过使用图唯一标识符实现，实现集中存储库，同时支持仓库特定和分支特定视图。完全符合 MCP 规范，实现与 IDE 和 AI 代理的无缝集成。
主要特色
- ** 🧠 AI驱动内存优化** - 高级推理模型（OpenAI o3/o4-mini，Claude 4），采用MCP采样实现智能内存管理
- ** 🛡️ 生产准备安全** - 自动快照系统，保证回滚功能
- ** 🎯 上下文感知智能** - MCP采样分析实际内存状态以实现自适应优化策略
- ** 🔧 统一工具架构** - 12个涵盖所有内存库操作的整合工具
- ** 🧵 线程安全的单例模式** - 确保每个资源仅实例化一次，且有适当的线程安全
- ** 📊 分布式图结构** - 遵循使用 KùzuDB 图的高级内存库规范
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
KuzuMem-MCP
A TypeScript implementation of a distributed memory bank as an MCP (Model Context Protocol) tool, storing memories in a KùzuDB graph database with repository and branch filtering capabilities. Branch isolation is achieved by using a graph-unique identifier for entities, enabling a centralized memory bank while allowing repository-specific and branch-specific views. Fully compliant with MCP specification for seamless integration with IDEs and AI agents.
Key Features
- 🧠 AI-Powered Memory Optimization - Advanced reasoning models (OpenAI o3/o4-mini, Claude 4) with MCP sampling for intelligent memory management
- 🛡️ Production-Ready Safety - Automatic snapshot system with guaranteed rollback capabilities
- 🎯 Context-Aware Intelligence - MCP sampling analyzes actual memory state for adaptive optimization strategies
- 🔧 Unified Tool Architecture - 12 consolidated tools covering all memory bank operations
- 🧵 Thread-Safe Singleton Pattern - Ensures each resource is instantiated only once, with proper thread safety
- 📊 Distributed Graph Structure - Follows the advanced memory bank specification using a KùzuDB graph
- 🌿 Repository & Branch Awareness - All operations are contextualized by repository name and branch
- ⚡ Asynchronous Operations - Uses async/await for better performance
- 🔌 Multiple Access Interfaces - Access via CLI and multiple MCP server implementations
- 💾 KùzuDB Backend - Utilizes KùzuDB for graph-based memory storage and querying
- ✅ Fully MCP Compliant - All tools follow the Model Context Protocol for client integration
- 📡 Progressive Results Streaming - Supports streaming for long-running graph operations
- 🏠 Client Project Root Isolation - Each client project gets its own isolated database instance
- 🧠 High-Reasoning Analysis - Leverages OpenAI HIGH reasoning and Anthropic extended thinking for memory optimization
- 🗑️ Safe Bulk Operations - Advanced bulk deletion with dependency validation and dry-run capabilities
Unified Tools
The system currently broadcasts 12 unified tools that consolidate all memory bank operations:
- memory-bank - Initialize and manage memory bank metadata
- entity - Create, update, delete, and retrieve all entity types (components, decisions, rules, files, tags)
- introspect - Explore graph schema and metadata
- context - Manage work session context
- query - Unified search across contexts, entities, relationships, dependencies, governance, history, and tags
- associate - Create relationships between entities
- analyze - Run graph algorithms (PageRank, K-Core, Louvain, Shortest Path)
- detect - Detect patterns (strongly/weakly connected components)
- bulk-import - Efficient bulk entity import
- search - Full-text search across all entity types with KuzuDB FTS integration
安装
npx -y ts-node /absolute/path/to/kuzumem-mcp/src/mcp-stdio-server.ts配置
{
"mcpServers": {
"KuzuMem-MCP": {
"command": "npx",
"args": ["-y", "ts-node", "/absolute/path/to/kuzumem-mcp/src/mcp-stdio-server.ts"],
"env": {
"PORT": "3000",
"HOST": "localhost",
"DB_FILENAME": "memory-bank.kuzu",
"HTTP_STREAM_PORT": "3001"
}
}
}
}