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 long-term associative memory for LLMs by building a persistent concept graph with vector embeddings and semantic links.
Provides a long-term memory system for AI agents using a knowledge graph with semantic embeddings and automated memory decay and growth.
Provides AI agents with persistent, searchable memory across sessions and projects using a local SQLite database.
Acts as a personal digital memory hub that allows AI assistants to store and retrieve notes, preferences, code snippets, and personal knowledge.
Provides AI agents with persistent, layered long-term memory using a local SQLite database with hybrid FTS5 and vector search capabilities.
$claude mcp add mnemon-mcp -- npx -y mnemon-mcpProvides long-term memory for AI agents by allowing them to remember, recall, or forget information using natural language sentences.
$claude mcp add --transport http sepiace https://hi.sepiace.io/api/v1/mcpProvides local-first repository memory for coding agents to save and retrieve failed test results and project decisions.
$claude mcp add vexen -- npx -y @onurbyte/vexenAllows AI clients to save conversation transcripts into long-term memory and perform semantic searches to recall past interactions.
$claude mcp add --transport http worldku-mcp https://mcp.worldku.com/mcpProvides self-hosted, cross-device long-term memory for AI agents using hybrid semantic and keyword search.
Provides shared, bi-temporal memory for AI agents using a hybrid markdown and SQLite store with full-text and vector search capabilities.
Provides AI agents with hybrid semantic search using dense vector embeddings and lexical FTS5 BM25 via AnythingLLM integration.
Provides a local, chronological memory layer that allows AI clients to query and recall user-curated, dated memory banks via MCP.
$claude mcp add localkeep -- uvx localkeepProvides a local-first persistent memory layer for AI agents with semantic search, revision history, and relationship mapping.
Provides persistent semantic memory for AI agents using PostgreSQL, pgvector, and local Ollama models for hybrid retrieval and memory management.
Provides an AI agent with durable, current-truth memory through tools for storing, recalling, and reasoning over facts and entities.
Provides a local searchable archive of chat sessions and project decisions for AI agents to maintain long-term memory on macOS.
$claude mcp add onadit -- npx -y onaditProvides a persistent, cross-vendor semantic memory store that allows AI clients to read and write facts across different LLM platforms.
$claude mcp add --transport http gnosem https://gnosem.dev/mcpProvides a shared memory infrastructure that allows AI agents and applications to store, recall, and synchronize facts across different platforms.
$claude mcp add --transport http geniffy-mcp https://api.geniffy.com/mcpLets AI assistants search a semantic knowledge graph, explore concept relationships, and check grounding confidence behind claims.
Provides distilled long-term memory for AI agents using meaning-based recall and evidence-gated writing to prevent memory poisoning.