Skip to main content
Glama
DarylAndrian

daryl-memories

by DarylAndrian

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_URI

bolt://localhost:7687

Neo4j Bolt URI

NEO4J_USER

neo4j

Neo4j 用户名

NEO4J_PASSWORD

(必需)

Neo4j 密码

OLLAMA_URL

http://localhost:11434

Ollama API URL

EXTRACT_MODEL

qwen2.5:3b

用于实体抽取的 LLM

EMBED_MODEL

nomic-embed-text

嵌入模型(768 维)

MCP_HOST

0.0.0.0

绑定地址

MCP_PORT

8080

监听端口

MCP_API_KEY

(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

F
license - not found
Not graded
quality - not tested
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

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

  • F
    license
    Not graded
    quality
    Not graded
    maintenance
    Provides 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.
  • A
    license
    Not graded
    quality
    D
    maintenance
    A 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.
    8
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides persistent knowledge graph memory for AI agents, enabling them to store, recall, and query facts about people, projects, and relationships across sessions.
    MIT

View all related MCP servers

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.

View all MCP Connectors

Latest Blog Posts

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