@meetdhanani17
基本情報
Global MCP server that manage all the project data,
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": {
"zmem": {
"command": "npx",
"args": [
"ts-node",
"index.ts"
]
}
}
}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。
zmem MCP Memory Server is a TypeScript-based Model Context Protocol (MCP) server that enables project-specific and knowledge graph-based memory for Claude, LLM agents, and other tools. It supports storing, retrieving, and managing entities, relations, and observations per project, with a focus on flexibility and cross-project knowledge sharing.
To use zmem, add it to your MCP configuration (e.g., for Windsurf) with the command and path to the built index. Install dependencies, build, and run via npm or Docker. Use the MCP client to call tools such as save_project_observations with a project ID and observations. Persisted memory files are stored in a configurable directory (default /app/memories).
It exposes tools for saving and getting project observations, adding graph observations, creating entities and relations, deleting entities/observations/relations, reading the graph, searching nodes, searching all projects, opening nodes, and copying memory.
Memories are persisted to disk in a `memories` directory (configurable via the `MEMORY_DIR_PATH` environment variable, default `/app/memories`).
Yes. Build the Docker image with `docker build -t zmem-mcp-server` and run it with a volume mount to persist memories.
Call the `save_project_observations` tool via the MCP API with a `projectId` and an array of observations, each containing an `entityName` and `contents` array.
zmem is TypeScript-based and requires Node.js. Install dependencies with `npm install`, build with `npm run build`, and run with `npm start` for production.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths
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
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.
コメント