Memory Plus
@Yuchen20
Memory Plus について
🧠 𝑴𝒆𝒎𝒐𝒓𝒚-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who
基本情報
設定
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": {
"memory-plus": {
"command": "uvx",
"args": [
"memory-plus"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Memory Plus?
Memory Plus is an MCP server that provides a persistent memory system for AI assistants, allowing them to store, update, and recall information across sessions. It integrates with MCP-compatible clients like VS Code and Cursor and can be used with any LLM that supports the Google API key. It targets developers who want to give their AI agents long-term memory with features like memory graph visualization and file import.
How to use Memory Plus?
Install Memory Plus by obtaining a Google API key, setting it as GOOGLE_API_KEY, and installing the UV runtime. Then run uvx memory-plus in your terminal, or add the command and args to your IDE's MCP configuration (e.g., VS Code settings.json). For local testing, use the MCP Inspector command npx @modelcontextprotocol/inspector fastmcp run run .\\memory_plus\\mcp.py, or run the provided agent.py chatbot template.
Key features of Memory Plus
- Memory recording and updating across sessions.
- Improved prompt engineering for smarter memory retention.
- Visualizes the memory graph for better understanding.
- Supports importing files into the memory system.
Use cases of Memory Plus
- Give an AI coding assistant memory of past code changes and preferences.
- Build a personal knowledge assistant that remembers user facts and context.
- Enable an agent to recall previous conversations without needing to repeat information.
- Import project documentation or notes into the memory graph for the AI to reference.
FAQ from Memory Plus
What prerequisites are needed to run Memory Plus?
You need a Google API key (set as GOOGLE_API_KEY in your environment) and the UV runtime installed (pip install uv or via shell scripts).
How do I install Memory Plus in VS Code?
Click the "One Click Install" badge in the README, or manually add { "command": "uvx", "args": ["memory-plus"] } to your MCP servers in settings.json.
Can I use Memory Plus with Cursor?
Yes. In Cursor, go to file -> Preferences -> Cursor Settings -> MCP and add the same JSON configuration as for VS Code.
Is there a way to test Memory Plus locally without an IDE?
Yes. Clone the repository and use npx @modelcontextprotocol/inspector fastmcp run run .\\memory_plus\\mcp.py with MCP Inspector, or run uv run agent_memory.py after setting up the fastagent configuration.
What license is Memory Plus under?
It is licensed under the MIT License.
「メモリとナレッジ」の他のコンテンツ
Anytype MCP Server
anyprotoAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.
MCP Apple Notes
RafalWilinskiTalk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol.
Rust Docs MCP Server
Govcraft🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.
MCP server for Obsidian
MarkusPfundsteinMCP server that interacts with Obsidian via the Obsidian rest API community plugin
Solomd
zhitongblogA markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.
コメント