Memory Plus
Lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" a
Memory Plus is an MCP server implementation that provides memory management capabilities for AI agents. Developed by Yuchen Mao, it uses Qdrant for vector storage and Google's Gemini for embeddings, allowing agents to record, retrieve, and manage memories efficiently. The server includes features like memory categorization, visualization of memory embeddings, and file import capabilities, making it particularly useful for building AI assistants that need to maintain context and recall information across conversations.
Source
Repository: https://github.com/yuchen20/memory-plus
Maintain Memory Plus?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/yuchen20-memory-plus?ref=badge) Related mcp
Infisical (Secrets Management) Provides a secure bridge to the Infisical secrets management platform, enabling operations like creating, updating, and retrieving
Home Assistant (Vibecode) IDE-integrated development environment for creating and managing Home Assistant automations, dashboards, themes, and configuration
Serial Bridges with physical hardware devices (e.g. Raspberry Pi) via serial communication, enabling real-world control and interaction f
Datawrapper Create and manage Datawrapper charts and visualizations
Coda Provides a bridge between AI and Coda documents, enabling listing, creating, reading, updating, and duplicating pages for collabor
Fast Filesystem Provides streaming-based file operations with auto-chunking for memory-efficient handling of large files, including sequential rea