Onboarding: capture discrete, atomic Memories, not conglomerated blobs

The MCP onboarding flow now captures knowledge as discrete, individually titled Memories — one concept per Memory — instead of rolling composite source material like a repository map into one giant summary. Importing a list of services or systems now produces a separate, self-contained "What is X?" Memory for each entity, so every one is searchable, correctable, and readable on its own in the memsprout UI.