Meridian

This gives Claude persistent memory across coding sessions so it can pick up where it left off, coordinate multi-step tasks, and queue up items that need human approval before proceeding. Think of it as a stateful layer on top of Claude's otherwise stateless interactions. You'd reach for this when working on longer projects where context retention matters, or when you want explicit human-in-the-loop gates before Claude executes certain operations. It runs over stdio or SSE, so you can integrate it locally or hit the hosted endpoint at usemeridian.us. Solves the "wait, didn't we already discuss this?" problem that crops up in extended AI pair programming sessions.