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.
Gives AI agents a persistent hierarchical memory so they recall projects, decisions, errors and sessions across devices and providers.
$claude mcp add hmem -- npx -y hmem-mcpProvides a durable memory layer for AI agents using a temporal knowledge graph and hybrid retrieval via SQLite or PostgreSQL.
$claude mcp add engram-server -- docker run -i --rm ghcr.io/jamjet-labs/engram-server:0.5.0Provides persistent memory for AI agents using plain local markdown files with a human-in-the-loop approval system.
$claude mcp add magnemo -- uvx magnemo-mcpProvides persistent local memory for AI coding agents using a SQLite database to store decisions, bug fixes, and project conventions.
$leteoProvides 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-memoryLets an AI agent store, organize, and recall persistent long-term memories as a versioned URI graph across sessions and models.
Provides long-term, local-first memory for coding agents to prevent repetitive mistakes and maintain context across different AI tools.
$claude mcp add hippo-memory -- npx -y hippo-memoryGives AI agents a local markdown-based memory vault they can index, recall from, and forget on command.
$claude mcp add ori-mnemos -- npx -y ori-memoryIndexes local documents and code so an AI client can search them with hybrid BM25 and vector retrieval plus cross-encoder reranking.
Gives AI agents a shared local-first memory store they can read, write, correct, and recall context from across tools.
$claude mcp add remnic -- npx -y @remnic/connector-droidProvides local, Markdown-based memory for AI agents to capture, structure, and recall preferences, decisions, and project context.
$claude mcp add link -- uvx link-mcpProvides a shared, versioned, and local-first memory for multiple AI agents to read and write consistent facts.
$claude mcp add brain-oss -- npx -y @make0-ai/brainProvides 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-mcpProvides 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-layerProvides 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.mcpbProvides 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-mcpProvides persistent, local-first semantic memory for AI coding agents to retain decisions, preferences, and context across sessions.
$claude mcp add core -- uvx omega-memoryGives AI coding agents persistent session memory, local on-device inference, and an auditable token savings report.
$claude mcp add prism-coder -- npx -y prism-mcp-serverConnects code, documentation, and conversations to provide AI agents with long-term memory, project decisions, and advanced code search capabilities.
$claude mcp add mcp-server-f9f199 -- npx -y @contextstream/mcp-serverProvides 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