mem0-aio
An Unraid Community Applications template and Docker image that bundles Mem0's OpenMemory memory layer with its Qdrant vector store, API, and dashboard into one self-hosted container for homelab use.
mem0-aio packages Mem0's OpenMemory project, a self-hosted long-term memory layer for AI agents, into a single Unraid-first container, bundling a precompiled Qdrant vector database, the Python FastAPI and MCP server, and a Next.js dashboard using s6-overlay, together with persistent storage for both SQLite and Qdrant state. It is meant to remove the need to wire up a separate vector database by hand on first install.
A beginner installation only requires installing the Unraid template, keeping the default storage path, and choosing either a hosted OpenAI key or a local Ollama server for language model and embedding calls, after which the wrapper can auto-detect embedding dimensions for Ollama setups. The web UI proxies API traffic through the same published port, so exposing the direct MCP or API port to other clients is a separate, deliberate configuration step rather than a default.