Where is the memory data stored?
By default in `memory.json` in the server directory. You can change this by setting the `MEMORY_FILE_PATH` environment variable.
@s2005
基本信息
Standalone MCP server for enabling memory for Claude through a knowledge graph
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-memory-server": {
"command": "docker",
"args": [
"build",
"-t",
"mcp/memory",
"-f",
"src/Dockerfile",
"."
]
}
}
}Create multiple new entities in the knowledge graph
Create multiple new relations between entities
Add new observations to existing entities
Remove entities and their relations
Remove specific observations from entities
Remove specific relations from the graph
Read the entire knowledge graph
Search for nodes based on query
Retrieve specific nodes by name
A basic implementation of persistent memory using a local knowledge graph. It lets Claude remember information about the user across chats by storing entities, relations, and observations.
Add the server configuration to claude_desktop_config.json using Docker (recommended) or NPX. Optionally set the MEMORY_FILE_PATH environment variable to customize the storage location. Use the provided system prompt example in a Claude.ai Project to enable memory operations.
By default in `memory.json` in the server directory. You can change this by setting the `MEMORY_FILE_PATH` environment variable.
Add the Docker configuration from the README to `claude_desktop_config.json`. The Docker command mounts a volume `claude-memory` for persistence and runs the `mcp/memory` image.
Yes. Install the npm package `mcp-memory-server` or run directly with `npx mcp-memory-server`.
The server ignores duplicate entity names when using `create_entities`. Similarly, duplicate relations are skipped.
It is licensed under the MIT License.

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
评论