"Persistent" matching MCP servers:

A self-hostable MCP server that provides permanent memory for AI agents using Postgres + pgvector for semantic search and Markdown file sync.

Myelin provides persistent, brain-inspired memory for AI agents, enabling cross-session and cross-tool context retention with local, private storage.

A local, fully-offline MCP memory server that enables persistent storage and retrieval of information using SQLite with both keyword and semantic vector search capabilities.

A persistent semantic memory system for Claude Code, using vector search and a judgment ledger to surface prior decisions and calibrate predictions.

Connects AI assistants to a persistent memory engine with Neo4j knowledge graph and ProMem extraction, enabling long-term context and associative memory across chats and workspaces.

A Model Context Protocol server providing vector database capabilities through Chroma, enabling semantic document search, metadata filtering, and document management with persistent storage.

A memory server for Claude that stores and retrieves knowledge graph data in DuckDB, enhancing performance and query capabilities for conversations with persistent user information.

Provides LLM clients with a persistent, scalable knowledge graph memory system that supports semantic retrieval, contextual recall, and temporal awareness.

Provides persistent knowledge graph memory for AI agents with local semantic search using Neo4j and ONNX embeddings, enabling offline operation with zero API costs.

A high-performance MCP server utilizing libSQL for persistent memory and vector search capabilities, enabling efficient entity management and semantic knowledge storage.

Provides semantic memory and persistent storage for Claude, leveraging ChromaDB and sentence transformers for enhanced search and retrieval capabilities.

Provides a plug-and-play persistent memory layer for MCP-compatible AI assistants, enabling them to store, retrieve, and delete memories across multiple databases simultaneously using semantic vector search.

Mem0-compatible persistent memory for AI agents - write facts once, recall them semantically in any session. Self-hostable open-source server, or managed cloud with a remote MCP endpoint at https://deepmem.dev/mcp.

Provides zero-knowledge, local-first persistent memory for AI assistants with on-device embeddings, cross-platform capture, and zero-RTT semantic recall.

Persistent memory MCP server for Claude Code — self-hosted, n8n + PostgreSQL + pgvector. Team memory for AI agents with multi-user roles, multi-project namespacing, and hybrid vector + keyword search. No cloud required.

Provides intelligent, persistent memory for AI assistants with semantic search, natural language queries, and OAuth-based team collaboration, enabling context-aware conversations across multiple clients.

Provides persistent, semantic memory storage for LLMs across sessions using vector embeddings and FAISS search. Features bio-inspired memory consolidation, intelligent forgetting, and semantic retrieval without API costs.

Enables MCP clients to remember user information, preferences, and behaviors across conversations using vector search technology. Built on Cloudflare infrastructure with persistent storage and semantic similarity matching.

A self-hosted, graph-aware memory server for AI assistants that provides persistent memory across sessions with hybrid search and knowledge graph capabilities.

MCP server that gives AI coding agents persistent, semantic memory via Qdrant vector search, enabling workspace-aware codebase, documentation, and decision search.