Memory & Knowledge MCP Servers for OpenAI Agents SDK

AI-native structured memory for agents (MCP). Built for agents, not humans.

Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.

MCP server for soul.md — your portable AI identity layer across every LLM.

Knowledge graph memory system that gives LLMs persistent, structured memory.

Local agent memory, coding loop, Cursor from Telegram, scheduled playbooks, and MCP tools.

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Your Obsidian vault, connected to AI. MCP server for bridging personal knowledge with LLMs.

Persistent developer memory MCP server — the LLM is stateless, Mnemos isn't

Shared, persistent memory for AI agents, with semantic recall and live updates.

Second-generation memory server backed by a Neo4j graph database.

MCP server for Obsidian Companion

Make your Obsidian vault a first-class knowledge source for any MCP-enabled AI assistant. Local, private, headless. Graph analysis + FTS5 +

MCP server for Claude Code and Claude Desktop to interact with Open WebUI — manage chats, RAG knowledge bases, functions, and more.

Governed, self-hosted memory for AI agents: writes queue until a named person approves.

MCP server for hierarchical agent memory

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.

PostgreSQL-based RAG Memory MCP Server with Supabase - knowledge graph + semantic search

Local-first RAG indexing and semantic search MCP server

Remembry MCP Server — manage your meeting knowledge base via AI assistants. Recording requires the Remembry desktop app to be running.

A local intelligence layer for AI coding agents. Maps your repos, matches the open-source frontier.