内存 MCP
基于知识图谱的人工智能代理记忆系统,可在对话之间实现持久信息存储。
特征
使用知识图谱结构的持久内存存储
用于组织信息的实体关系模型
添加、搜索和检索记忆的工具
工具
系统提供以下MCP工具:
load_knowledge_graph():检索整个知识图谱get_knowledge_graph_size():返回图的当前大小类别(“小”、“中”或“大”)add_entities(entities):将新实体添加到内存中add_relations(relations):创建实体之间的关系add_observations(entity_name, observations):向现有实体添加观察结果delete_entities(entity_names):从内存中删除实体delete_relations(relations):删除关系search_nodes(query, search_mode):搜索与查询匹配的实体和关系。支持三种搜索模式:“exact_phrase”:将整个查询作为子字符串匹配
“any_token”:如果查询中的任何单词匹配则匹配(默认)
“all_tokens”:如果查询中的所有单词都匹配,则匹配
open_nodes(names):检索特定实体及其之间的关系
用法
使用以下命令运行代理:
代理将自动:
在对话开始时加载其内存
互动时参考相关信息
对话结束时用新信息更新其记忆
输入q退出对话。
配置
使用MEMORY_FILE_PATH环境变量设置内存存储位置(默认为memory.json )。
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
基于知识图谱的人工智能代理记忆系统,可在对话之间实现持久信息存储。
Related MCP Servers
- AsecurityAlicenseAqualityEnhances user interaction through a persistent memory system that remembers information across chats and learns from past errors by utilizing a local knowledge graph and lesson management.Last updated -1394,39153MIT License
- -securityAlicense-qualityA persistent memory implementation using a local knowledge graph that lets Claude remember information about users across conversations.Last updated -7MIT License
- AsecurityAlicenseAqualityAn implementation of persistent memory for Claude using a local knowledge graph, allowing the AI to remember information about users across conversations with customizable storage location.Last updated -1121654JavaScriptMIT License
- -securityAlicense-qualityEnables AI assistants to store and retrieve memories with semantic search capabilities using vector embeddings. Provides persistent memory storage with SQLite backend for context retention across conversations.Last updated -17MIT License