Anlyst

The problem

Most AI assistants forget you the moment a session ends. Anlyst was a bet that decision fatigue gets solved by agents with persistent, personal context.

What I built

As CTO of a two-person founding team, I designed the system in three layers. A Vault pulls your real data from apps like Whoop, Apple Health, Google Calendar, and MyFitnessPal. A Mirror turns raw data into personal context by correlating sleep, activity, and schedule patterns. And a Persona acts on what it knows about you instead of giving generic advice.

The whole point was that the agent should reason from your actual life. If you slept poorly and have a packed calendar, it should know that without you having to say it.

Impact

The launch got 200+ waitlist sign-ups and early VC conversations before I moved to full-time engineering at HubSpot. The memory thesis outlived the company. It became the seed for chiggyOS, where I rebuilt the same idea as personal infrastructure I own.