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 autonomous AI agents with a dual-memory persistence architecture using hybrid search and hierarchical storage for long-term context.
Provides AI agents with a local, sovereign semantic memory layer using hybrid search, knowledge graphs, and a Markdown-based wiki.
$claude mcp add neuromcp -- npx -y neuromcpProvides a local, encrypted memory layer for AI clients to store and retrieve knowledge using hybrid search and a knowledge graph.
$claude mcp add kepta -- npx -y kepta-mcpProvides local-first, source-grounded memory that allows AI agents to retain decisions, evidence, and corrections across different sessions.
$claude mcp add talamus -- uvx talamusProvides secure durable memory and bounded context for AI agents through local or hosted knowledge management and hybrid search.
$claude mcp add --transport http graymatter https://api-0.valkyrlabs.com/graymatter/mcpProvides shared memory for AI agent fleets by consolidating session data into a knowledge graph and injecting relevant context into every prompt.
$claude mcp add hicortex -- npx -y @gamaze/hicortexProvides a shared, semantic knowledge base that allows AI agents to store and search discoveries across sessions.
$claude mcp add --transport http agentbase https://mcp.agentbase.tools/mcpProvides AI agents with associative memory using a typed knowledge graph stored on Postgres and pgvector.
$claude mcp add engraphy -- docker run -i --rm ghcr.io/devon-clarkk/engraphy:0.3.0Provides shared long-term memory across different LLMs using semantic recall, session management, and multimedia storage via Postgres and pgvector.
$claude mcp add --transport http polymnemo https://polymnemo.purpleground-26f6d744.westus2.azurecontainerapps.io/mcpAllows AI agents to manage a decaying memory of claims, identify contradictions, and track the staleness of asserted facts.
$claude mcp add claims-mcp -- npx -y claims-mcpProvides self-hosted, governed memory for AI agents with automated redaction, append-only audit logs, and local embeddings.
$https://github.com/mahaoboy/memalyze/releases/download/v0.2.0/memalyze-0.2.0-darwin-arm64.mcpbProvides persistent, cross-platform memory for AI agents to recall past discussions, save decisions, and export data as Markdown.
$claude mcp add --transport http aifa-memory-mcp https://aifa.works/api/mcpLets an AI client query Neo4j graph databases with Cypher, store knowledge graph memory, and manage Aura cloud instances.
Provides shared memory, vector RAG, and orchestration for coding agents to persist lessons and coordinate tasks across different AI clients.
$claude mcp add continuum -- docker run -i --rm docker.io/pouyahasanamreji/continuum:0.3.0Provides persistent, local-first semantic memory for AI coding agents using a Markdown vault and LanceDB-powered hybrid search.
Provides local-first, persistent agent memory using SQLite to store and retrieve facts with hybrid dense and sparse search.
$claude mcp add lean-memory -- uvx lean-memoryProvides AI agents with a persistent cognitive graph memory to store facts, decisions, reasoning chains, and corrections in a single navigable file.
Lets AI coding clients store and search long-term project memory in an on-device graph database with semantic vector search.
Provides persistent long-term and short-term memory for AI agents to recall decisions, facts, and conversation history across sessions.
Provides AI coding agents with a project-local knowledge graph stored in Git-friendly JSON files for isolated, shareable project memory.
$claude mcp add n2n-memory -- npx -y n2n-memory