local-memo
Local-only MCP server for saving and restoring conversation context across AI agent sessions using JSON files on disk.
README
local-memo
Local-only MCP server for saving and restoring conversation context across AI agent sessions. No cloud, no accounts — just JSON files on disk.
Inspired by Upstash Memo, but fully local.
Why?
Memo is a great idea — save your conversation context, get a short ID, restore it later in a different session or agent. But there's no reason that data needs to leave your machine. This version replaces the cloud API + Redis with plain files in ~/.local-memo/.
Install
Claude Code
claude mcp add local-memo -- npx local-memo
Or from a local clone:
claude mcp add local-memo -- node /path/to/local-memo/dist/index.js
Claude Desktop / Cursor
Add to your MCP config:
{
"mcpServers": {
"local-memo": {
"command": "npx",
"args": ["local-memo"]
}
}
}
Usage
Save context
Ask your AI agent to save the current conversation context. It will call memo_set and return a short ID:
> Please save our conversation context
Context saved locally.
ID: 4tJ630XqhCV5gQelx98pu
Expires: 2025-01-30T14:38:51.278Z (1440 minutes)
Restore context
In a new session, give the agent the ID:
> Restore memo 4tJ630XqhCV5gQelx98pu
List saved memos
> List my saved memos
Delete a memo
> Delete memo 4tJ630XqhCV5gQelx98pu
Tools
| Tool | Description |
|---|---|
memo_set |
Save structured context (goal, completed tasks, pending tasks, decisions, files, extra context). Returns an ID. |
memo_get |
Restore context by ID. Returns formatted markdown. |
memo_list |
List all unexpired memos with their IDs and goals. |
memo_delete |
Delete a memo by ID. |
Options
| Flag | Default | Description |
|---|---|---|
--ttl-mins |
1440 (24h) |
How long memos live before expiring |
--dir |
~/.local-memo |
Storage directory |
Example with 7-day TTL:
claude mcp add local-memo -- npx local-memo --ttl-mins 10080
Storage
Memos are plain JSON files in ~/.local-memo/memos/:
{
"id": "4tJ630XqhCV5gQelx98pu",
"createdAt": "2025-01-29T14:38:51.278Z",
"expiresAt": "2025-01-30T14:38:51.278Z",
"ttlMins": 1440,
"context": {
"goal": "Build a local memo system",
"completed": ["Designed schema", "Wrote MCP server"],
"pending": ["Test it"],
"decisions": ["Use filesystem instead of Redis"],
"files": ["index.ts", "package.json"],
"context": "Extra notes here"
}
}
Back them up, sync them, grep them — they're just files.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。