I built a mission control dashboard for my entire Claude Code setup, and it ran itself overnight. The problem: dozens of Claude Code sessions across projects, skills buried in terminal history, no way to see what was active. Everything scattered. So I had a single overnight prompt build an Agentic OS. Here's the quick version: → One dashboard for every project, session, agent, and skill → Grouped by category so nothing gets lost → Natural-language recall to find any past session ("the one where I built X") → Rescan and resume any session straight from the UI The recall feature is the one I did not expect to love. Ask for a session from weeks ago, it finds the exact match and lets you jump back in. It reads your Claude projects folder, classifies each session, and surfaces it all in a clean web UI. Send the prompt at night, wake up to a working dashboard. Full tour here if you want to build your own: https://youtu.be/olWkpHYbS1Y Anyone else organizing their AI work in one place, or still living in terminal tabs?