A memory that stays: OpenViking as a personal RAG — from any device
Every AI chat starts from zero, and your context dies with the session. What if your memory were its own layer — curated, searchable, and reachable from every client: Claude Code in the terminal, claude.ai in the browser, the Claude app on the go? That's OpenViking: a personal RAG on a small VM of your own. This article shows the infrastructure, the tool itself, and why an individual memory pays off — high-level, with infra diagrams and three real device demos.