"Searching for an MCP server with persistent memory for tool usage" matching MCP servers:

A self-hostable MCP server that provides permanent memory for AI agents using Postgres + pgvector for semantic search and Markdown file sync.

A Machine Control Protocol (MCP) server that enables storing and retrieving information from a Qdrant vector database with semantic search capabilities.

An MCP server that gives AI assistants persistent memory across conversations, storing and retrieving user preferences and behaviors using vector search.

Facilitates knowledge graph representation with semantic search using Qdrant, supporting OpenAI embeddings for semantic similarity and robust HTTPS integration with file-based graph persistence.

An integration server implementing the Model Context Protocol that enables LLM applications to interact with Milvus vector database functionality, allowing vector search, collection management, and data operations through natural language.

A knowledge-graph-based persistent memory server for the Model Context Protocol, storing entities, observations, and relations in SQLite with semantic vector search and temporal versioning.

Munin is a high-performance, pragmatic memory layer for AI agents (Cursor, Claude Code, OpenClaw, Gemini CLI,...). Unlike other solutions, Munin focuses on developer productivity with: * Multi-Project Support: Isolate memories into separate "brains" (Context Cores). * GraphRAG: Automatically builds a knowledge graph from your context. * Sub-200ms Search: Blazing fast Hybrid & Semantic

An MCP server for managing persistent AI memory using hybrid search (keyword + semantic vector) with SQLite storage and offline-first local embeddings.

Provides persistent memory for AI agents using hybrid search (vector embeddings + BM25) with neural reranking, enabling storage and retrieval of insights, debugging solutions, and patterns across coding sessions.

Provides AI agents with persistent, searchable memory using semantic search, auto-linking, and categorization, with zero-config local setup or production-ready external providers.

An MCP server that provides AI assistants with persistent, semantic memory using Turso for storage and OpenAI for vector search. It enables natural language operations to store, retrieve, and refine information with automatic duplicate detection and quality validation.

A memory server for Claude that stores and retrieves knowledge graph data in DuckDB, enhancing performance and query capabilities for conversations with persistent user information.

A high-performance MCP server utilizing libSQL for persistent memory and vector search capabilities, enabling efficient entity management and semantic knowledge storage.

Provides persistent memory and knowledge graph capabilities for AI assistants using local SQLite storage. Enables creating, searching, and managing entities, relationships, and observations with vector search support across conversations.

An MCP server that gives AI assistants persistent memory using an OpenAI vector store, enabling saving and semantic searching of text memories across sessions.

Provides persistent, semantic memory storage for LLMs across sessions using vector embeddings and FAISS search. Features bio-inspired memory consolidation, intelligent forgetting, and semantic retrieval without API costs.

Enables MCP clients to remember user information, preferences, and behaviors across conversations using vector search technology. Built on Cloudflare infrastructure with persistent storage and semantic similarity matching.

Local-first MCP server for long-term memory of dev sessions. It indexes session metadata with embeddings in Postgres/pgvector, enables semantic search over past sessions, and resolves only relevant session files for context.

MCP Memory is a MCP Server that gives clients like Cursor and Claude the ability to remember user preferences and behaviors across conversations using vector search.

MCP Memory is an MCP Server that gives MCP Clients the ability to remember information about users across conversations. It uses vector search technology to find relevant memories based on meaning, not just keywords.