Laiba Asghar

We don t need to say your product is great, let others decide that.

There is no guarantee that we are the best, or that what we build is amazing. As someone who prefers doing over talking, I always remind myself: what customers say about my product is the most honest reflection of what it truly is.

If users feel satisfied, it means the product is moving in the right direction.
If they don t, it doesn t mean we ve failed completely. It means something isn t right yet, and it s time to fix it.

One memory across 30+ agents

Switching between different AI models should not force you to endlessly repeat your information again and again.

We decided 2025 would be the last year that people spend 5+ hours/week in endless context repetition loops. Hence emerged AI Context Flow, #1 product of the day with ~2000 users now!

But 2026 is going to be even better. Today, I'm excited to announce our biggest update yet: Pluto (can you guess the wordplay here? )

TL;DR: I built a platform to validate a hypothesis: If we lower the barrier to entry for using and productizing agents, will normal users actually like them? I m looking for builders to test it out. You can take your existing agent code, fill out a simple manifest, run a few CLI commands, and have a shareable, web-accessible agent in 10 minutes. Links at the bottom.

Happy New Year, everyone.