Memento Protocol is an MCP (Model Context Protocol) server that provides persistent, structured memory for AI agents. It enables agents and AI assistants to recall, update, and manage memories (instructions, patterns, knowledge) across sessions, instead of starting from scratch each time. Memento Protocol exposes memory management functions—such as storing, recalling, consolidating, and deleting memories—accessible through tools/hooks, a REST API, and a web dashboard. It integrates with major MCP clients and coding agents (Claude Code, Gemini CLI, OpenCode, OpenAI Codex) and is ideal for developers, AI/agent builders, and teams seeking persistent, context-aware AI applications.
Visit Memento Protocol's official website for product details and getting started.