How does Jean Memory work across different apps?
Jean Memory creates a connected memory graph where related memories are automatically linked and surfaced when relevant, and updates sync in real time across all connected applications.
@jonathan-politzki
基本情報
Premium, consistent memory and long-term storage across AI applications. Remote MCP server.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"jean-memory": {
"command": "npx",
"args": [
"-y",
"supergateway",
"--sse",
"https://api.jeanmemory.com/mcp/claude/sse/773e2c10-1fd1-48cb-bc15-7674aaa9b09c"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Jean Memory is a secure, unified memory layer that works across all AI applications, giving AI assistants the ability to remember user preferences, context, and history while keeping everything private and under user control. It is built on the Model Context Protocol (MCP) and can be used with any MCP-compatible application.
Users can sign up at jeanmemory.com and run npx install-mcp i https://api.jeanmemory.com/mcp/claude/sse/your-user-id --client claude to connect Claude Desktop. Alternatively, developers can run the server locally by cloning the repository and using make build; make up from the openmemory directory.
Jean Memory creates a connected memory graph where related memories are automatically linked and surfaced when relevant, and updates sync in real time across all connected applications.
Yes, the local deployment option uses docker-compose and gives users complete control over their data with a fully self-hosted setup.
Jean Memory works with any MCP-compatible application including Claude Desktop, Cursor, Windsurf, Cline, and any MCP client.
It offers end-to-end encryption for sensitive data, a local deployment option for complete control, and no vendor lock-in so users can export their data at any time.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

One permissioned folder your team and your AI agents both log into.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.
コメント