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 agents build a persistent knowledge graph of code, docs and policies, and gate decisions with signed verdicts.
$claude mcp add graqle -- uvx graqle
Provides AI agents with persistent semantic recall, knowledge graphs, and contradiction detection across sessions.
$claude mcp add yantrikdb-mcp -- uvx yantrikdb-mcp
Provides persistent memory for AI agents using plain local markdown files with a human-in-the-loop approval system.
$claude mcp add magnemo -- uvx magnemo-mcp
Provides a local-first shared memory system for multiple AI agents using Markdown files and git to compound knowledge through usage and validation.
$claude mcp add compound-memory -- uvx compound-memory
Lets an AI agent store, organize, and recall persistent long-term memories as a versioned URI graph across sessions and models.
Indexes local documents and code so an AI client can search them with hybrid BM25 and vector retrieval plus cross-encoder reranking.
Provides local, Markdown-based memory for AI agents to capture, structure, and recall preferences, decisions, and project context.
$claude mcp add link -- uvx link-mcp
Provides persistent key-value context memory and long-term graph memory to improve context retention and retrieval for AI coding agents.
$claude mcp add ppm -- npx -y pmll-memory-mcp
Provides AI agents with a local-first knowledge graph and experience memory using intelligent context routing and progressive disclosure.
$https://github.com/primeline-ai/kairn/releases/download/v0.3.2/kairn-0.3.2.mcpb
Provides persistent, AES-256-GCM encrypted memory infrastructure for AI agents to enable cross-session and cross-agent context recall.
$claude mcp add synapse-secure-memory -- uvx synapse-layer
Provides a local markdown-based memory vault and vector storage for Claude Code agents to persist context across sessions.
$claude mcp add brain-core -- uvx brain-core-mcp
Provides persistent, local-first semantic memory for AI coding agents to retain decisions, preferences, and context across sessions.
$claude mcp add core -- uvx omega-memory
Provides long-term hierarchical memory for AI agents using a local tree of plain text files to persist decisions and context across sessions.
$claude mcp add ihmt-memory -- uvx ihmt-memory
Provides persistent semantic memory, knowledge graphs, and AST indexing to reduce AI agent token usage and improve codebase context.
$claude mcp add cognirepo -- uvx cognirepo
Provides a cross-agent memory layer that stores, connects, and retrieves knowledge using semantic search and knowledge graphs.
$claude mcp add lore -- uvx lore-sdk
Gives AI agents a persistent shared memory store with semantic search, deduplication, supersession lineage, and a knowledge graph.
Lets AI clients store, manage, and search data in Redis using natural language, including hashes, lists, sets, streams, JSON, and vector search.
Provides a local-first, federated memory engine for AI agent teams with team and project-scoped access control and associative recall.
$claude mcp add agent-memory-os -- uvx agent-memory-os
Provides AI agents with persistent, searchable memory using semantic and keyword recall across multiple MCP clients.
$claude mcp add montycat-mcp -- uvx montycat-mcpProvides AI agents with a shared, persistent, and searchable memory using semantic and keyword recall.
$claude mcp add memocat-mcp -- uvx memocat-mcp