Memory Management MCP Repositories

Manages project-specific contexts and maintains conversation continuity with hierarchical structures and metadata tagging. Facilitates quick retrieval for efficient workflows within specified project contexts.

Caches data between interactions with AI language models to reduce token consumption and enhance performance by automatically storing and retrieving frequently accessed data.

Utilizes a local knowledge graph to enable persistent memory for AI agents, allowing them to create, update, and retrieve personalized user information across chat sessions. Facilitates tailored interactions by managing entities, relations, and observations.

Provides web search capabilities using Puppeteer, returning structured JSON results from Google searches in a lightweight and stateless design.

A basic implementation of persistent memory using a local knowledge graph that enables storage and retrieval of user-specific information across chats by defining entities and their relationships.

Utilizes a scalable knowledge graph built on Elasticsearch to manage and query large datasets, providing persistent memory for AI systems. Supports complete CRUD operations and offers advanced search capabilities for improved data handling in Model Context Protocol applications.

Manage and enhance interactions with contextual information using a robust knowledge graph. It captures, stores, and retrieves data seamlessly with PouchDB for improved consistency and organization by project-specific paths.

Provides access to Omi conversations and memories through a standardized MCP interface, enabling reading, creating, and managing these elements efficiently within LLM workflows.

Creates chatbots that maintain self-editing memory with different memory tiers to manage limited LLM context windows. Connects to SQL databases, local files, and documents for seamless conversational AI interactions.

High-performance vector search and persistent memory system using libSQL, offering efficient knowledge storage and semantic search capabilities. Supports knowledge graph management and secure token-based authentication for accessing local and remote databases.

Manage agents and memory blocks within the Letta system, enabling the creation, listing, and attachment of memory blocks to agents while facilitating seamless communication through message sending and response receiving.

Stores, updates, and recalls structured information using a dynamic schema, enabling relationship management for entities such as characters, locations, and items in a knowledge graph format. Designed specifically for text-based RPGs and interactive storytelling, it helps maintain consistent memory across conversations.

A knowledge graph implementation that supports semantic search with a Qdrant vector database, enabling effective graph-based representation of entities and their relations. It includes features for file-based persistence and utilizes OpenAI embeddings for enhanced semantic similarity.

Store and retrieve memories using a command-line interface with a backend powered by SQLite. Manage important information efficiently in applications with memory functionalities.

Manage and access project memory banks remotely with centralized control, supporting multi-project operations with secure isolation and consistent file structure enforcement. Perform memory bank operations including reading, writing, and listing files across projects through a type-safe MCP interface.

Provides semantic memory and search capabilities for AI assistants, enabling the storage, retrieval, and management of text-based memories. Enhances context awareness during conversations through advanced features like tagging and health monitoring.

Manage and interact with structured repositories of information for AI assistants, enabling the storage, retrieval, and tracking of context across sessions to enhance AI capabilities. Supports operational modes for tasks like coding, debugging, and system design.

This utility manages interconnected data entities within an application's operational memory space. It enforces rigorous structural checks to guarantee data integrity across the knowledge graph. Drawing parallels to operating system resource control, this tool dynamically allocates and tracks relationships, akin to how virtual memory separates logical from physical addresses to enhance system capacity.

Utilizes a local knowledge graph for the creation, management, and retrieval of entities and their relationships, enabling users to maintain context and continuity in conversations across chats.

Implements a memory system for large language models (LLMs) with capabilities for chatting, retrieving conversation history, and switching between multiple LLM providers.

Facilitates structured sequential thinking by breaking down complex problems into logical steps, validating reasoning chains, and visualizing thinking pathways. Integrates with a Memory Bank for managing and storing reasoning patterns to enhance problem-solving workflows.

Integrates with the Neo4j graph database to maintain complex relationships between memory nodes, enabling long-term retention and querying of knowledge across multiple conversations. Facilitates the construction of an interconnected knowledge base that acts as an external memory system.

Manage session summaries and memos for large language models with persistent local storage and version tracking. Store, retrieve, and list detailed session histories to enhance context retention for improved memory capabilities.

Integrate and automate various tools such as GitHub, GitLab, Google Maps, and Puppeteer through a unified gateway for efficient data retrieval and workflow enhancement. The modular architecture allows for easy addition or removal of individual tool modules.

Provides macOS-specific system information and operations, including retrieval of CPU, memory, disk, and network details, as well as enabling native macOS notifications.

Synchronizes preferences, personal details, and code standards across all Claude interfaces, ensuring consistent updates without manual input. Utilizes a caching system for faster memory-related queries.

Manage long-term memory for AI agents by storing and retrieving memories efficiently with a lightweight Python-based solution. Customize and extend memory capabilities easily through a robust template designed for integration.

Manage and enhance chat experiences by allowing AI models to remember and recall information during conversations. Effortlessly add, search, delete, and list memories using a simple text file system to improve context retention and response relevance.

Facilitates the setup and management of a structured Memory Bank for context preservation in AI assistant environments, offering detailed guidance on file structures, template generation, and project summary analysis. Enhances AI context management through organized documentation and relevant content suggestions.

A memory system that maintains and retrieves comprehensive project and conversation memory, enabling contextually aware AI assistance. It supports multiple memory types including short-term, long-term, episodic, and semantic memory for enhanced development workflows.