What's the most annoying thing your AI coding assistant forgets between sessions?

I built AI Dimag after hitting this wall repeatedly: I'd spend 30 minutes explaining architectural decisions to Claude or Cursor, then start fresh in new chat the next day and have to explain everything again.

Common things that get forgotten:

• "All database access goes through src/db/store.ts"

• "We tried microservices approach X and it failed because Y"

• "Never use library Z, it has security issues"

• "Always run tests before committing to main"

The frustrating part? These aren't just preferences—they're critical decisions with context that took hours to figure out.

I'm curious:

• What does your AI assistant keep forgetting?

• How much time do you waste re-explaining the same context?

• Have you tried workarounds like .cursorrules or CLAUDE md files?

This problem is what drove me to build AI Dimag—persistent, verified memory that proves it's still true. Every memory carries evidence (tests, shell checks, commit refs) that gets re-verified. When beliefs go stale, they get flagged instead of silently misleading your AI.

Would love to hear what you're dealing with. Maybe there are patterns I haven't thought about yet.

Checkout at https://aidimag.com/ and https://cloud.aidimag.com/