Save, search, and manage long-term memories across conversations. Set preferences, facts, and skills; recall them later by topic.
MIT
297,705 tools. Last updated 2026-07-14 08:25
"memory" matching MCP tools:
- Store and retrieve persistent memories with actions like add, search, update, delete. Search before adding to avoid duplication.MIT
- Retrieve, promote, demote, or edit memory nodes. Purge permanently removes content and embeddings after confirmation. Check state for accessibility.AGPL 3.0
- Store and manage persistent facts across sessions. Add, view, update, or remove structured memories organized by sections like work, personal, and preferences.MIT
- Record, query, and validate domain knowledge using structured key prefixes like selector, tip, and avoid to maintain accurate automation contexts.MIT
- Store and retrieve temporary key-value data during development workflows, supporting set, get, list, delete, search, and clear operations with tag-based organization.MIT
Matching MCP Servers
- AlicenseAqualityCmaintenanceA zero-dependency, file-based persistent memory system for AI agents with tiered memory, Ebbinghaus decay, and keyword retrieval.Last updated51MIT
SAE4U Memoryofficial
AlicenseAqualityCmaintenanceProvides persistent memory for Claude with hierarchical categorization, cross-corpus recall, session journals, and customizable persona, enabling memory continuity across sessions.Last updated7MIT
Matching MCP Connectors
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
Persistent agent memory paid per call via x402 USDC. Your wallet is your private memory namespace.
- Manages conversation memory through hierarchical storage, adaptive retrieval, compression, knowledge graphing, inspection, and curation to maintain context integrity in long AI dialogues.MIT
- Store project notes, recall context, search memories with hybrid semantic and keyword retrieval, cluster related items, deduplicate, archive old memories, and set permanent rules for persistent session intelligence.MIT
- Retrieve, search, update, archive, and restore individual memories. Access the latest entry in a chain-shaped namespace or view revision history of any memory.MIT
- Persist AI discoveries with save, recall, and search actions. Organize insights by category and retrieve by task or query.MIT
- Store and retrieve documentation, decisions, tasks, and events to maintain persistent context across conversations. Use semantic search to find relevant information without filesystem tools.MIT
- Store plain text documents or memories in Hyperspell to connect AI applications with unstructured data.
- Store content in a vector database for semantic search and retrieval. Save text with unique identifiers to enable AI-powered similarity-based queries.
- Search stored information using natural language queries to find semantically similar content in vector databases.
- Retrieve and format all markdown files from a specified project directory to provide AI assistants with structured project context for enhanced task understanding and execution.MIT
- Set up a memory-bank directory and generate core files for structured project context tracking. Integrates existing project briefs and provides guidance for next steps. Uses a root directory path to initialize or overwrite files as needed.MIT
- Retrieve real-time Windows memory usage data including total, used, and available memory. Monitor system performance.GPL 3.0
- Generate and execute detailed instructions for updating Memory Bank files, including file roles, update strategies, operation commands, content templates, and priority logic, ensuring immediate implementation of changes.MIT
- Retrieves the top processes consuming memory on a Windows system. Specify the number of processes to return.GPL 3.0
- Retrieve the memory usage breakdown for a specific RabbitMQ cluster node to monitor resource allocation and identify memory bottlenecks.MIT