Memory & Knowledge MCP Servers for OpenAI Agents SDK

A model context protocol server for TriliumNext Notes

The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.

Local-first memory for AI agents: ground truths, failure firewall, negotiated recall over MCP.

Read-only, offline search over a checksum-verified memory pack, with exact cited quotes

Wontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.

DevMind MCP - AI Assistant Memory System - Pure MCP Tool

Local adaptive memory for AI coding agents through a five-tool MCP lifecycle.

Local-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 + sqlite-vec.

MCP server for BEHAVR: remember images/videos and ask questions about them

MCP server and CLI for Roam Research

Repository-native protocol and local MCP server for Work, Docs, History and durable project Memory.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

Local, private RAG second brain over your Claude Code & Codex transcripts, served back to both agents as an MCP server.

Search Raindrop.io bookmarks and review tag and collection plans. Read-only MCP by default.

MCP standards client for your own custodial SAIHM operator. Free start: @saihm/mcp-server-pro

One brain for your AI — a local-first, owned memory and configurable persona shared across Claude Code and Cowork (Claude Desktop), exposed

Local hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.

Shared, serverless, conflict-free memory for AI agents — a multi-machine drop-in for the MCP memory knowledge graph.

A Model Context Protocol (MCP) server that provides memory storage and retrieval capabilities using Mem0

Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.

MCP server for a project's context (AGENTS.md), memory, and identity — base or drop-in extension.