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 AI agents with persistent, sub-quadratic topological memory and associative recall using a volumetric lattice network.
$claude mcp add --transport http icx-mcp https://icx.caleralabs.com/mcp
Gives AI agents persistent local memory with consolidation, forgetting-curve decay, and graph-based recall across sessions.
$claude mcp add yourmemory -- uvx yourmemory
Stores durable facts and preferences per agent and retrieves them with hybrid dense, sparse, and graph search.
Provides a local-first knowledge graph memory for AI agents using Markdown vaults to store and retrieve structured claims and entities.
Provides an advanced long-term memory system for AI agents using hybrid vector and knowledge graph retrieval with an LLM cognitive layer.
Provides an event-sourced, local-first long-term memory system for AI agents using semantic vector retrieval and decision guardrails.
Provides a human-like long-term memory layer for AI agents that learns and recalls information through semantic search and activation models.
Provides a graph-based memory for AI agents that extracts entities and causal relations to discover connections across independent documents and sessions.
$claude mcp add --transport http reasongraph https://memory.primaxiom.ai/mcp
Provides a Git-aware persistent memory layer for engineering agents to store decisions, invariants, and codebase context across sessions.
Provides a portable semantic memory layer for LLM agents to recall past decisions, notes, and conversations using hybrid vector and exact matching.
Provides AI assistants with long-term memory through local semantic search over Claude and ChatGPT conversation histories.
Provides AI agents with persistent memory by allowing them to save, organize, and semantically search documents, notes, and conversations.
$claude mcp add --transport http plurality-mcp-server https://app.plurality.network/mcp
Provides AI agents with persistent, searchable long-term memory using hybrid BM25 and FAISS search with built-in resilience features.
$claude mcp add mindcore-memory-mcp -- uvx mindcore-memory
Provides AI agents with persistent, structured memory through a knowledge graph combining graph storage and semantic vector search.
$claude mcp add graphmem-mcp -- uvx graphmem-mcp
Provides cross-conversation memory and sub-2ms BM25 retrieval for Antigravity workspaces by indexing local dialogue logs and markdown artifacts.
Provides AI agents with curated long-term memory using half-life decay, reinforcement on recall, and automated pruning.
Enables LLM agents to perform semantic search and text ingestion using PostgreSQL and pgvector with OpenAI-compatible embeddings.
Provides persistent, hybrid vector and full-text search memory for AI agents using a single SQLite file.
Provides a six-layer cognitive memory architecture for AI agents featuring conflict detection, temporal awareness, and Bayesian confidence scoring.
Provides long-term Markdown-based memory for coding agents using a local SQLite index for fast retrieval without network dependencies.