"Persistent" matching MCP servers:

Persistent AI memory with SQLite hybrid search (FTS5 + semantic), built-in Qwen3 embedding, and rclone sync across machines.

The open-source, self-organizing memory for all your AI tools. Persistent memory over MCP (remember, recall, observe): background agents extract entities, resolve conflicts, and keep cited syntheses current in an append-only, encrypted, single-tenant vault.

Cortex is a Claude Code plugin that gives Claude persistent memory across sessions. A background miner extracts durable lessons (decisions, conventions, bug fixes, preferences) from your completed sessions, stores them as markdown in an Obsidian vault, and automatically surfaces relevant ones at the start of each new session via a query-tailored briefing.

8 standalone MCP servers for SMBs — Guardrails (prompt injection, PII, secrets detection), FinOps (AI cost tracking and budgets), Observability (agent tracing), Smart Router (17+ models, 9 providers), Trust Score (governance scoring 0-100), Memory (persistent agent memory), ThinkSecure (runtime security + SOC2/GDPR audit), and A2A Lite (agent-to-agent protocol). 37 tools total, TNC credits

Persistent semantic memory for your SQL databases. The name is ironic — it remembers everything.

coldstart gives coding agents durable memory of a specific codebase, with no embeddings, no vector store, and no API key. Agents write notes after real tasks — what a file is for, how a flow spans files, which invariants hold — and those notes are surfaced automatically to a later session whose task matches, so nothing gets rediscovered from scratch. Every note is anchored to real files by content

Provides persistent, cross-project memory for Claude over the Model Context Protocol, enabling it to remember goals, decisions, and progress between sessions with deterministic briefs and supersession-aware recall.

A persistent Python REPL MCP server for AI agents with stateful execution, real timeouts, crash isolation, and an MCP bridge to call other tools in the project.

Nucleus MCP provides a local, unified memory layer that synchronizes context and decisions across different AI tools like Cursor, Claude Desktop, and Windsurf. It enables cross-platform state management and persistent knowledge storage using a shared local brain.

A local, offline memory server for AI agents that stores and retrieves memories without LLM calls, enabling persistent cross-session memory with bi-temporal querying and auditable records.

A personal memory engine and MCP server that stores durable facts in markdown files managed via git, enabling hybrid search (lexical + semantic) through an MCP interface for persistent context across LLM sessions.

Enables persistent, distilled memory for AI assistants, allowing recall and storage of durable facts across sessions and subagents via MCP.

Persistent memory management for AI assistants like Claude, enabling creation, search, and retrieval of memories with tagging and triggers.

One context engine for every AI. Persistent context from GitHub, Notion, and your decisions, delivered to Claude, ChatGPT, Cursor, VS Code, Gemini, and any MCP-compatible client.

An MCP server that gives AI models a persistent notebook backed by a folder of Markdown files, with tools to discover, read, write, edit, and delete notes.

SSH orchestration MCP server for coding agents, enabling persistent bash sessions, hash-protected remote file editing, SFTP transfers, SSH tunnels, and multi-host orchestration with connection reuse across tools.

Enables federated multi-source research by fanning out queries across web, community, and social sources, deduplicating and interleaving results, and storing a persistent corpus for cross-checking.

AI memory that works like yours. Neural pathway architecture gives your AI persistent recall, contextual awareness, and cross-session continuity the way human memory actually works. 14 MCP tools. Works with Claude Code, Cursor, Windsurf, and any MCP client. $50/mo unlimited.

Provides persistent browser tabs with tools to read, click, type, and interact with web pages, enabling local LLM agents to perform multi-step web tasks.

Persistent 3D/2D spatial world model MCP server for AI agents. Entity tracking, object permanence, AABB collision simulation & view frustum projection via local SQLite.