Remember Me
@phlax
关于 Remember Me
MCP server to persist chat artefacts and rules
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"remember-me": {
"command": "python",
"args": [
"-m",
"mcp.server.run",
"remember_me_mcp_server.server"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Remember Me?
Remember Me is a persistence framework for maintaining conversational context and rules in MCP-based language model applications. It stores, retrieves, and manages persistent resources like rules, snippets, and summaries using SQLite, and is designed for developers building LLM applications that need durable context across conversations.
How to use Remember Me?
Install the package with pip install -e ., then run the MCP server with python -m mcp.server.run remember_me_mcp_server.server. Configure your LLM platform to connect to the MCP server and expose the tools. In conversations, the LLM should first load the context and then follow any rules returned.
Key features of Remember Me
- Centralized context manager (MyContext) for all persistence operations
- Rule system with MUST, MUST NOT, SHOULD, SHOULD NOT, and MAY policies
- Snippet management for reusable code or text fragments
- Summary management for preserving conversational context
- Backup and restore of entire context states
- Namespaced resources via “context” parameter (e.g., “me” for global)
Use cases of Remember Me
- Defining behavior guidelines that an LLM must follow across all conversations
- Storing reusable code snippets or text fragments for quick retrieval
- Preserving important contextual summaries between chat sessions
- Organizing different rule sets for different tasks (e.g., coding, creative writing)
- Creating backups before making major changes to conversational state
FAQ from Remember Me
What is the “me” context?
The “me” context is a special default context always available. It contains global rules, snippets, and summaries that apply to every conversation. When loading context, the “me” context is always included automatically.
How do I load extra contexts beyond the “me” context?
You can load additional contexts by specifying them in the extra_context parameter. This allows organizing different sets of resources for different conversation types, such as a “coding” context with programming snippets.
What types of resources does Remember Me support?
Remember Me supports three resource types: Rules (behavior constraints), Snippets (reusable code or text fragments), and Summaries (important contextual information).
How do backup and restore work?
You can create a backup of the current state with my_context_backup_create(), list available backups with my_context_backup_list(), restore from a backup with my_context_backup_restore(), and remove backups individually or clear all with my_context_backup_remove() and my_context_backup_clear().
What are the dependencies for running Remember Me?
The server runs on Python and uses SQLite for persistence. It communicates via the MCP protocol and requires an MCP‑compatible LLM platform to expose its tools.
其他 分类下的更多 MCP 服务器
MaxKB
1Panel-dev🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Servers
modelcontextprotocolModel Context Protocol Servers
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
评论