> ## Documentation Index > Fetch the complete documentation index at: https://docs.mengram.io/llms.txt > Use this file to discover all available pages before exploring further. # Mengram Documentation > The memory layer for AI apps. Persistent memory — semantic, episodic, procedural — with native quality across 23 languages. ## What is Mengram? Mengram is an API that gives your AI applications persistent, human-like memory. Instead of starting every conversation from scratch, your AI remembers users — their preferences, past interactions, and learned workflows. Mengram works **natively across 23 languages** (Russian, Chinese, Spanish, Japanese, Korean, Arabic, and more) using Cohere multilingual embeddings — not English-only retrieval bolted onto translation. Get your API key and add your first memory in under 2 minutes. Give your AI agents persistent memory with scoping, filtering, and procedural learning. Understand semantic, episodic, and procedural memory. Full reference for the Python client (61 methods). Node.js and browser SDK with TypeScript support (60 methods). ## Integrations Full memory loop — auto-save, auto-recall, session context. 29 tools for Claude Desktop, Cursor, Windsurf. MengramRetriever for RAG pipelines. Persistent memory for multi-agent crews. 12 tools for AI agents — auto-recall, auto-capture, Graph RAG. Ready-to-import workflow template. Command-line tool for setup, import, and rules. ## Reference Complete REST API with 90+ endpoints. Real-time notifications for memory events. Run Mengram on your own infrastructure.