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 memory for AI agents using a local SQLite database with keyword retrieval and structured memory types.
Provides local codebase indexing and semantic search to help coding agents navigate functions, classes, and files efficiently.
$claude mcp add lybrary -- uvx lybrary
Provides AI agents with persistent identity, reasoning patterns, and episodic memory through specialized memory management procedures.
$claude mcp add --transport http agent-memory-server https://munnin.lok.quest/mcp
Provides a verifiable memory layer for AI agents using typed facts, content-addressed versioning, and an audit trail.
$claude mcp add --transport http statejar-integrations https://statejar.com/mcp
Provides AI agents with bi-temporal memory that tracks typed facts and their validity over time.
$claude mcp add --transport http korely-memory https://api.korely.ai/agent/mcp
Provides a persistent, bitemporal memory layer for AI agents that extracts structured facts and manages context with traceability.
$claude mcp add --transport http haki https://api.gethaki.space/mcp/
Provides AI agents with persistent semantic memory across sessions using the Lightning Network for pay-per-use storage and retrieval.
$claude mcp add --transport http giskard-memory https://memory.rgiskard.xyz/sse
Provides AI agents with a persistent SQLite memory layer that uses a learn-experiment-graduate loop to turn patterns into proven preferences.
$claude mcp add metabrain -- uvx metabrain
Provides a local-first persistent memory layer for coding agents to store and retrieve context across sessions using Markdown and SQLite.
$https://github.com/PeterPirog/mcp-light-memory/releases/download/v1.8.1/mcp-light-memory-1.8.1.mcpb
Lets independent AI clients contribute to a shared semantic knowledge graph while preserving provenance, disagreement, and audit trails.
$claude mcp add --transport http testgraph https://testgraph.21dle.co.uk/mcp-v2
Provides a shared, living memory for AI assistants to read and write information across private and collaborative coves.
$claude mcp add --transport http reef https://reefwith.me/mcp
Provides persistent memory for AI agents using semantic search with recency decay and local ONNX embeddings.
$claude mcp add memex -- docker run -i --rm ghcr.io/ayushagrawal288/memex:v0.1.0
Provides an agentic long-term memory system using declarative, reviewable source files for structured knowledge retrieval and relation navigation.
$https://github.com/Liyuan1992/memdsl/releases/download/v0.9.2/memdsl-0.9.2.mcpb
Provides a shared second brain for AI agents that builds itself from your work and maintains real-time updates.
$claude mcp add --transport http team0-plugins https://api.team0.ai/v1/mcp
Provides persistent, adaptive memory for MCP clients using graph-based retrieval and semantic search.
$claude mcp add polypack-mcp -- uvx polypack-mcp
Provides Claude Code with permanent, accumulative memory using a Neo4j-native DIKW knowledge graph.
$claude mcp add wisdomgraph -- npx -y wisdomgraph
Provides persistent multi-level memory for AI agents including L1/L2/L3 storage, web-search savings, and thread-specific context.
$claude mcp add vibo-memory -- npx -y @vibo-dev/vibo-mcp
Provides local persistent memory for AI agents using SQLite and FTS5 lexical search.
$claude mcp add mcp-memory -- docker run -i --rm ghcr.io/germaniu/mcp-memory:0.6.0
Provides working developers with code examples for building AI features using LLMs, vector databases, RAG, fine-tuning, and agents with Ollama.
Lets an AI client store documents, code, PDFs, and images in a local knowledge base and retrieve them with hybrid semantic and keyword search.