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.
Lets AI clients query Memgraph graphs and store agent memory, knowledge graphs, and document extractions.
Provides AI agents with persistent long-term memory using local SQLite storage and hybrid search.
Lets AI agents save draft memories, route them through a review gate, and recall approved, versioned records stored in a Git repository.
Provides 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/mcp
Provides AI agents with persistent graph-based memory using SurrealDB to enable multi-hop reasoning and spreading activation recall.
Provides autonomous AI agents with a dual-memory persistence architecture using hybrid search and hierarchical storage for long-term context.
Provides local-first, source-grounded memory that allows AI agents to retain decisions, evidence, and corrections across different sessions.
$claude mcp add talamus -- uvx talamusProvides 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:0.3.0
Provides 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/mcp
Provides 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/mcp
Lets an AI client query Neo4j graph databases with Cypher, store knowledge graph memory, and manage Aura cloud instances.
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-memory
Lets AI coding clients store and search long-term project memory in an on-device graph database with semantic vector search.
Provides local-first, governable long-term memory for AI coding agents to store and recall project rules, preferences, and decisions.
$claude mcp add cp-memory -- uvx cp-memory-mcp
Provides a governed experiential-memory ledger that allows AI agents to log task outcomes and promote verified lessons through multi-actor evidence.
$claude mcp add stele -- uvx stele-mcp
Provides an auditable memory layer for AI agents with provable deletion, tamper-evident audit trails, and bi-temporal time-travel recall.
$claude mcp add attestari-147fa6 -- uvx attestariProvides local-first persistent memory for AI agents with sleep-style consolidation, verifiable forgetting, and optional blockchain anchoring.
$claude mcp add padam-nocturne -- uvx padam-nocturne
Provides a local-first cognitive memory engine that uses a property graph to automatically re-evaluate downstream beliefs when upstream facts change.
Gives LLM apps a local-first memory layer that extracts, ranks and resolves facts from conversations with confidence-aware retrieval.
Indexes a Markdown vault into a local SQLite RAG store so AI clients can search notes, walk link graphs, and save memories.
$claude mcp add neurostack -- npx -y neurostack