@agentage/mcp-memoryofficial
A
licenseA
qualityB
maintenanceExposes local memory vaults as 6 MCP tools over stdio, enabling clients like Windsurf, Zed, and Claude Desktop to read and write memory.
6
137 npm
2
MIT
ebbingflow-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ebbingflow-mcpremember that I'm looking for AI application jobs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ebbingflow-mcp
EbbingFlow 长期记忆的 MCP 集成桥 —— 一个轻量 stdio MCP Server，把 EbbingFlow 的记忆能力以 MCP 工具形式接入 OpenCode / Claude / 任意 MCP 客户端。
这是什么
针对"对话一长 AI 就丢失前文"的上下文记忆痛点：EbbingFlow 是本地部署的开源 AI 记忆引擎（Neo4j 知识图谱 + 向量 + SQL 证据链 + Ebbinghaus 遗忘曲线）。本仓库提供一个薄桥接层，将记忆能力封装为 4 个 MCP 工具，让 Agent 能跨会话写入、检索、溯源记忆。
┌────────────┐ stdio(MCP) ┌────────────────┐ HTTP ┌──────────────┐
│ OpenCode / │ ◄────────────► │ ebbingflow-mcp │ ◄───────► │ EbbingFlow │
│ 任意 MCP │ 4 个工具 │ (本仓库) │ │ 核心服务 │
│ 客户端 │ │ 薄转发，无状态 │ │ localhost:8000│
└────────────┘ └────────────────┘ └──────────────┘设计要点：本桥不直接触碰 Chroma/Neo4j/SQLite，只把请求转发给已运行的 EbbingFlow HTTP 服务（默认 localhost:8000），避免多进程对本地持久化存储的锁冲突。
Related MCP server: sill-ensoul
提供的工具
工具 | 说明 |
| 写入一条长期记忆（经 EbbingFlow 抽取事实 → 图谱 + 向量 + 证据链） |
| 多轨检索（图谱/向量/BM25/SQL/剧情），按 Ebbinghaus 衰减排序 |
| 带完整记忆上下文的对话（回复也会回写记忆） |
| 检查 EbbingFlow 核心服务是否在线 |
前置要求
EbbingFlow 核心服务已启动并监听
localhost:8000（上游仓库：https://github.com/MMX920/ebbingflow）Python 3.10+
pip install -r requirements.txt运行与配置
环境变量（均可选，有默认值）：
变量 | 默认 | 说明 |
|
| EbbingFlow 核心服务地址 |
|
| 记忆归属的用户 ID |
|
| MCP Server 名称 |
|
| 请求上游的超时秒数 |
直接运行：
python mcp_server.py接入 OpenCode（opencode.jsonc）：
{
"mcp": {
"ebbingflow": {
"type": "local",
"command": ["python", "/path/to/ebbingflow-mcp/mcp_server.py"],
"enabled": true
}
}
}示例
# 写入
remember: "用户正在求职 AI 应用方向岗位"
→ remembered. engine confirmation: 已记住...
# 检索
recall: "用户求职什么方向"
→ 1. [GRAPH] ... [score=0.9, source=关系网]许可
本仓库（MCP 集成桥）：MIT
上游 EbbingFlow 引擎：Apache-2.0（见 MMX920/ebbingflow）
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
- LogRackOAuthai.lograck
Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.
- mcpOAuthai.butlerbrain
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Cross-tool persistent memory and context for AI assistants over MCP.
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Related MCP Servers
sill-ensoulofficial
AlicenseAqualityBmaintenanceProvides persistent, cross-session memory for CLI agents via MCP tools, enabling them to recall, distill, and share experiences across projects and tools.86MIT- AlicenseNot gradedqualityAmaintenanceExposes repo-native, self-verifying memory to coding agents over stdio MCP, letting them recall ranked past decisions, record new claims with verifiable receipts, and check the health and stats of stored memory. Keeps agent context honest by surfacing memories whose evidence no longer holds.2 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients such as Claude Code to give LLM agents long-term memory by exposing remember, recall and forget tools over stdio, backed by a hybrid BM25 and vector store that reinforces frequently used memories.MIT