Memory & Vector Stores MCP servers
MCP servers for long-term memory and vector search: store notes, embeddings and facts so an AI assistant remembers across sessions. 799 servers in this category.
MCP servers for long-term memory and vector search: store notes, embeddings and facts so an AI assistant remembers across sessions. 799 servers in this category.
Gives AI coding agents a local persistent memory for storing and retrieving decisions, fixes, and project context across sessions.
Gives AI coding agents a shared, self-hosted knowledge graph for storing and retrieving context across sessions and tools.
Lets an AI client semantically search and read Obsidian vault notes and blocks using locally stored Smart Connections embeddings.
$claude mcp add smart-connections-mcp -- npx -y smart-connections-mcpLets an AI client run semantic and hierarchy-aware searches over a Qdrant vector database built from Git, Confluence, JIRA, and local files.
Persistent memory server for Claude Code and OpenCode that stores advice and promotes or demotes it based on scored outcomes.
Gives Google ADK agents durable Redis sessions, semantic long-term memory, vector search tools, and semantic caching.
Provides a persistent, versioned file-system workspace for AI agents to store, search, and recall knowledge across sessions.
$claude mcp add sayou -- uvx sayouGives any MCP-capable AI assistant a local SQLite memory store to save, search, and recall facts, preferences, and decisions across sessions.
$claude mcp add memento -- npx -y @psraghuveer/mementoAllows AI agents to share typed, named memories through a local SQLite vector index with semantic and graph-based recall.
Provides AI coding agents with a persistent, structured, and queryable project memory shared across sessions and MCP clients.
Provides long-term memory for AI agents using knowledge graphs, provenance tracking, and cascading stale-fact detection.
Provides a persistent memory layer for AI coding agents that distinguishes current project truth from superseded historical information.
Provides a self-hosted long-term memory vault for AI agents to read and write markdown notes via the Model Context Protocol.
Provides a portable, local-first memory system that stores user preferences and decisions for MCP-compatible AI clients.
Provides a deterministic, self-hosted long-term memory layer for AI agents to store and recall facts without using an LLM on the read or write path.
Provides durable hybrid memory for AI agents using vector, lexical, temporal, and graph retrieval to maintain context across sessions.
Provides local persistent memory for AI agents to remember decisions, goals, and context across sessions using a semantic graph.
Provides local semantic search and agent memory by indexing over 20 document formats using a local ONNX model and LanceDB.
Provides a persistent associative memory graph and a suite of 60+ tools to give AI agents long-term memory and stealthy web browsing capabilities.
Provides a self-hosted persistent memory layer for AI agents using semantic search and a local file vault.
$claude mcp add strata -- npx -y strata-mcp-server