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.
Provides a shared Graph-RAG memory system for AI agents using a markdown vault with wikilink recall, task management, and messaging.
$claude mcp add mind-mri-agent-second-brain -- npx -y mind-mri-second-brainProvides AI assistants with a permanent, private memory using a local SQLite database with hybrid keyword and semantic vector search.
$claude mcp add sqlite-local-ai-memory -- npx -y sqlite-local-ai-memoryProvides persistent, layered shared memory for AI agents and bot teams using a verified, non-deletable document control system.
$claude mcp add emet -- npx -y @dreamforgestudiollc/emetProvides local long-term memory for Claude Code and other agents by storing and retrieving exact conversation history and command outputs.
$claude mcp add cogito-mem -- uvx cogito-memProvides a self-hosted memory layer for AI agents using a knowledge graph, vectors, and graph RAG to store and recall facts and documents.
$claude mcp add semurg-mcp -- uvx semurgProvides shared long-term memory for AI agent fleets, allowing agents to record and retrieve insights across an organization.
$claude mcp add hivemind -- docker run -i --rm ghcr.io/monochrome-muncher/hivemind:v2.27.2Lets AI clients query Memgraph graphs and store agent memory, knowledge graphs, and document extractions.
Provides a self-hosted semantic memory engine for AI agents to persist project context, skills, and experiences across sessions via MCP.
Provides AI agents with persistent long-term memory using local SQLite storage and hybrid search.
Provides a self-hosted, governed memory service for AI agents using MCP to manage durable evidence, semantic relationships, and provenance.
Lets an AI client store, search, and recall persistent local memory with full-text and vector search plus source provenance.
$claude mcp add warm -- npx -y writerslogic-warm-mcpLets AI agents save draft memories, route them through a review gate, and recall approved, versioned records stored in a Git repository.
Lets an AI client store, search, and link memories and knowledge across sessions using semantic search and a knowledge graph.
$claude mcp add octobrain -- npx -y @muvon/octobrainProvides persistent, adaptive memory for AI agents using hybrid search and a neural memory graph to connect knowledge across conversations.
$claude mcp add --transport http memory-cloud https://memory.kagura-ai.com/mcpProvides AI agents with a local-first, source-cited memory layer featuring proposal review and knowledge graph visualization.
$claude mcp add neurakeep -- npx -y neurakeepExpose protected RAG storage to AI agents through a tiered access system for searching metadata and retrieving private content.
$claude mcp add koma-core-mcp -- npx -y koma-core-mcpProvides AI agents with persistent graph-based memory using SurrealDB to enable multi-hop reasoning and spreading activation recall.
Provides AI agents with a local-first cognitive memory kernel featuring hybrid search, knowledge graphs, and automatic memory consolidation.
Turn documents into agent memory with hybrid semantic and keyword search over emails, PDFs, notes, and past conversations.
Provides persistent agent memory using a hex lattice database for semantic, lexical, and hybrid search.