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 local-first, git-native memory for AI agents using a hybrid recall system of vector, graph, and full-text search.
$https://github.com/mo-cmyk/mazarbul/releases/download/v0.2.3/mazarbul_v0.2.3_darwin_arm64.mcpbProvides 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-mcpProvides a high-performance, local-first cognitive memory engine for AI agents using bi-temporal SQLite and hybrid retrieval.
$claude mcp add fastrmemory -- npx -y fastrmemoryProvides local-first persistent memory for AI agents with sleep-style consolidation, verifiable forgetting, and optional blockchain anchoring.
$claude mcp add padam-nocturne -- uvx padam-nocturneProvides 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 AI agents with long-term memory using a local file system, append-only journal, and search capabilities hosted on a private home server.
$claude mcp add keephaven-mcp -- npx -y @dafarusd/keephaven-mcpTurns Markdown folders into an agent-native knowledge base with long-term memory, provenance, and hybrid search.
$claude mcp add tacitus-mcp-server -- npx -y @dashiro/tacitus-mcp-serverProvides an agent memory infrastructure that enables LLMs to store, categorize, and recall information using four types of cognitive memory.
$claude mcp add memento -- npx -y memento-mcp-serverProvides 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-mcpProvides AI agents with self-improving, secure memory through a hash-chained ledger that enforces corrections and prevents reintroducing retired values.
$claude mcp add memory-pulse -- npx -y memory-pulseProvides AI agents with a serverless database for vector search, NoSQL, PostgreSQL, file storage, and persistent memory.
$claude mcp add ainative-zerodb-mcp-server -- npx -y ainative-zerodb-mcp-serverProvides 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 neurostackProvides a vendor-neutral memory layer for AI agents using three-tier short, mid, and long-term memory horizons.
Saves git-based session handoffs so the next coding agent, in any MCP tool or machine, starts with what was done.
$claude mcp add remembra -- uvx remembra-mcpProvides persistent semantic memory for AI agents using a local Qdrant vector database on Raspberry Pi 5.
Provides local-first memory for AI coding agents by indexing shell history, git diffs, project documentation, and assistant transcripts.
$claude mcp add nexusmem -- npx -y nexusmemProvides AI assistants with persistent, graph-aware memory using hybrid lexical and semantic search via Cloudflare Workers and D1.
Provides a living knowledge graph that connects AI conversations and notes to give AI agents a persistent, evolving memory.