MCP Servers Directory — Page 520

Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.

Count keys in a JSON object. Values discarded.

Cognitive memory for AI coding assistants — persistent memory across sessions

Local-first persistent memory for AI agents, with reasoning and formal verification.

memory-lean is an MCP server that gives Claude Code, Claude Desktop, Cursor and any other MCP client a knowledge graph that persists between sessions. It is a drop-in replacement for the reference…

MCP server for .NET memory profiling — in-process heap snapshots via EventPipe with leak heuristics

Remote MCP (Model Context Protocol) server for storing, retrieving, and semantically searching "memories" on behalf of AI agents, organized into multi-tenant spaces and protected by API Key. A space can be shared by…

Persistent memory and context window caching for LLM conversations. Save, retrieve, and manage memories with intelligent context archiving. MongoDB-backed storage.

MCP server for AI memory management using Letta - Standard MCP format

Persistent memory + git snapshots for Claude Code. Never lose context or code.

情景+实体记忆 MCP 服务，为 Claude Code 提供持久化记忆能力

A Model Context Protocol server for storing and retrieving memories using low-level Server implementation and SQLite storage.

A high-performance, **pure Rust** Model Context Protocol (MCP) server that provides persistent, semantic, and graph-based memory for AI agents.

A lightweight, structured, token-efficient local-first MCP memory server

SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.

A Model Context Protocol server that provides knowledge graph management capabilities. This server enables LLMs to create, read, update, and delete entities and relations in a persistent knowledge…

AI tools start every session with amnesia. Your preferences, decisions, past mistakes -- all gone. You repeat yourself. The AI re-discovers things you already told it. Context windows reset, and…

Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.

Every AI conversation starts from zero. Claude doesn't know which architecture decision you made last week. Cursor doesn't remember the bug you fixed

An MCP server that uses a knowledge graph to store and recall structured memory for AI models

Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.

MemoryOracle - 10 agent memory tools: vector store, recall, summarization, redaction.

Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking

Local CLI that turns a coding goal into ranked, token-budgeted repository context for AI agents.

Give every AI you use one shared, permanent memory. Store once, recall in whichever AI you open.

A lightweight, local Retrieval-Augmented Generation (RAG) memory store for MCP agents. Memory-Plus lets your agent record, retrieve, update, and

Scans agent code for untrusted input poisoning persistent cross-session memory

Give any agent self-improving memory you can trust in production. Built-in memory security.

A complete Python port of the official [TypeScript MCP memory server](https://github.com/modelcontextprotocol/servers/tree/main/src/memory). This

Claude Code v2.1.59+ automatically saves memories from your conversations. Over time, your memory store accumulates:

Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.

Open-source memory backend for AI agents — REST API, MCP, OAuth, CLI, dashboard. One self-hosted service, every transport. Agents store decisions, share causal knowledge graphs, and retrieve context…

Persistent memory for AI agents. Search and store durable facts, preferences and decisions.

Search and read the current MemorySync documentation while writing integration code.

Most AI memory systems are just databases with a search API. memory-v2 is a **cognitive architecture** -- it models how human memory actually works.

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

Portable AI memory shared across models and harnesses - plain markdown you own.

MCP wrapper for memos-mcp

A package for Pensieve (previously known as memos)

A Python package enabling LLM models to interact with the Memos server via the MCP interface for searching, creating, retrieving, and managing memos.

A Model Context Protocol (MCP) implementation for the [MemOS](https://github.com/MemTensor/MemOS) API service. This package provides a command-line

A MCP(Model Context Protocol) server for Memos.

Your reviewed knowledge, across AI conversations.

AI-to-human attention marketplace. Agents pay CPM to reach humans, earn credits by replying.

Portable AI memory as MCP tools: five reads and three controlled writes.

Durable, revision-pinned memory storage and retrieval for AI conversations.

Add persistent memory to AI assistants. Store and recall info across conversations.

Every AI conversation starts from zero. MemPlato fixes that — it's a persistent memory layer for AI assistants, running entirely on your own device. Your data never leaves your phone.

mempool.space MCP — Bitcoin block explorer + mempool/fee stats

A local MCP (Model Context Protocol) server for portable, long-term agentic memory — a thumb drive for your AI context.

Shared project memory that keeps teammates and AI agents aligned across sessions.

Persistent memory for AI agents — remote MCP server. EU-hosted (Helsinki), privacy-first, deterministic recall with no LLM in the hot path.

Working memory for AI agents: digest-indexed episodes on a git shelf, recalled a section at a time.

AI continuity and memory hub for portable context, checkpoints, and cross-AI memory.

shared AI-context layer for teams — persistent memory your agents search and update over MCP

MCP server for persistent, searchable memory for AI agents.

Agent memory with git-like version control. Custom LLMs turn conversations into structured facts with automatic conflict detection - your agent sees

Cross-client AI memory hub: agents share one SQLite memory.db via file-level pointers.

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

Memtrace gives AI coding agents structural memory — your codebase as a live knowledge graph so agents stop re-deriving code structure from scratch