Memory & Knowledge MCP Servers for DeepSeek Harness

Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.

97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.

Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.

Universal Memory Plugin for OpenCode & Claude Code (Powered by mnemo-mcp)

Persistent memory for AI agents with rollback, audit trails, and semantic search.

One shared memory for every AI you use, in plain Markdown files you own.

Model Context Protocol server for long-term memory management with SQLite storage

Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.

An MCP server that gives LLMs persistent, searchable semantic memory

Durable AI memory: recall distilled facts in a later session or subagent, and remember new ones.

Local chronological memory banks you control; Claude recalls them via MCP.

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

Local MCP bridge for Obsidian vaults with filesystem-first setup

Permanent identity + encrypted, quantum-ready memory that outlives the session, for any AI agent.

Project memory across sessions for AI agents. A queryable decision log in the repo.

MCP server for AnythingLLM integration with TypingMind and other MCP-compatible clients

MCP Server for syncing Claude Code memories across devices via GitHub

Portable, local-first, markdown-based project memory — a Model Context Protocol (MCP) server + CLI shared across Claude Code, GitHub

Manage Duke Bookmark notes, categories, and plan-enabled knowledge search over MCP.

MCP server for cognitive knowledge graphs — models thought, emotion, reasoning, and episodic memory

Your own notes, searched and cited by your AI — local-only, allowlist-gated, capped, and logged.