daryl-memories
Mnemosyne
为 3 个 Hermes 代理提供的共享 GraphRAG 记忆 MCP 服务器。完全本地化——数据不会离开网络。
架构
Machine 1 (HOST: this PC) Machine 2 Machine 3
+--------------------------+ +-------------+ +-------------+
| Neo4j (Docker) | | Hermes | | Hermes |
| Ollama (native) |<---| Agent | | Agent |
| MCP server (Python) | MCP| (client) | | (client) |
| Port 8080 | +-------------+ +-------------+
+--------------------------+机器 1 运行所有内容。机器 2 和 3 是纯 MCP 客户端。
Neo4j 在一个容器中处理图、向量和全文检索。
Ollama 以原生方式运行(非 Docker)以简化操作。
MCP 是 Hermes 的原生协议——代理将记忆工具作为一等功能。
Related MCP server: Knowledge Graph Memory Server
快速开始
# 1. Clone and configure
git clone https://github.com/DarylAndrian/Mnemosyne.git
cd Mnemosyne
cp .env.example .env
# Edit .env with your passwords
# 2. Start Neo4j
docker compose up -d
# 3. Install Python deps
uv venv .venv
uv pip install -r requirements.txt
# 4. Start the server
python -m server.main服务器在 http://0.0.0.0:8080/mcp 上启动。健康检查位于 /health。
环境变量
变量 | 默认值 | 说明 |
|
| Neo4j Bolt URI |
|
| Neo4j 用户名 |
| (必需) | Neo4j 密码 |
|
| Ollama API URL |
|
| 用于实体抽取的 LLM |
|
| 嵌入模型(768 维) |
|
| 绑定地址 |
|
| 监听端口 |
| (必需) | 用于认证的共享 API 密钥 |
MCP 工具
remember(content, agent_id, session_id?, tags?)
存储一条记忆。服务器将实体、关系和事实抽取到知识图谱中。检测与现有事实的冲突。
recall(query, top_k?, agent_id?)
混合 RAG 搜索:向量相似度 + 关键词 + 图邻域扩展。结合新近度和访问次数加权。
context(entity_name, depth_limit?)
图邻域遍历。返回与实体相连的所有边(1-3 跳内)。
resolve(entity_a, entity_b)
合并重复实体。重新指向所有边,保留两个名称作为别名。
forget(memory_id)
软删除一个情节。保留溯源信息。
代理配置
添加到你的 Hermes 配置中:
{
"mcpServers": {
"mnemosyne": {
"url": "http://<HOST_IP>:8080/mcp",
"headers": {
"Authorization": "Bearer <MCP_API_KEY>"
}
}
}
}基础设施
Neo4j 5.26(社区版)——图、向量和全文检索于一个容器
Ollama 0.32+ —— qwen2.5:3b(抽取)+ nomic-embed-text(嵌入)
Python 3.11+ —— 使用 Streamable HTTP 传输的 FastMCP 服务器
Docker Compose —— 仅 Neo4j(Ollama 保持原生)
开发
# Run integration tests (requires live stack)
.venv/Scripts/python.exe -c "from tests.test_integration import *; ..."许可证
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
FlicenseNot gradedqualityNot gradedmaintenanceProvides local-first memory storage and retrieval with automatic embedding, vector search, and knowledge graph capabilities. Enables agents to store memories locally and retrieve relevant context through hybrid search with optional Neo4j graph traversal.- AlicenseNot gradedqualityDmaintenanceA persistent memory server that implements a local knowledge graph using the Kuzu embedded database to store entities, relationships, and observations. It enables AI models to maintain structured long-term context through searchable nodes and comprehensive tag-based organization.8MIT
- AlicenseNot gradedqualityCmaintenanceA lightweight, powerful local memory server for AI agents supporting text, entities, and relations. Enables persistent codebase understanding and user preference management.5749MIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent knowledge graph memory for AI agents, enabling them to store, recall, and query facts about people, projects, and relationships across sessions.MIT
Related MCP Connectors
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DarylAndrian/Mnemosyne'
If you have feedback or need assistance with the MCP directory API, please join our Discord server