I want to share a project I ve been pouring my heart into for the past few months: Circa Accord.
The Backstory
Living in a hyper-fast-paced urban environment, my daily routine was completely broken. I was constantly trapped in "revenge bedtime procrastination." I tried almost every sleep and habit tracker on the App Store, but I kept running into the same issue: raw data wasn't enough to change my behavior. Seeing a beautiful chart showing I only slept 4 hours didn't stop me from doom-scrolling the next night at 2 AM. I realized I needed psychological leverage, not just analytics.
So, I spent my evenings teaching myself iOS development to build the exact tool I needed.
Hey I built Prmptree, an AI agent that connects to your Gmail and runs in the background every hour. No prompts needed.
It automatically archives clutter, unsubscribes from mailing lists, flags urgent emails, and drafts replies to personal emails. You set the trust level from full approval control to completely autonomous.
Free to try at prmptree.com. Looking for honest feedback from anyone with a messy inbox.
I woke up to a nasty bill because an agent looped overnight. All the usual tools (alerts, soft budgets) only reacted after the damage was done. So I built baar-core: lightweight library that checks budget before every API call.
Raises exception locally
No DNS, no TCP $0 charged on overrun
Semantic routing (84% savings)
Per-user SQLite quotas Just launched on Product Hunt: https://www.producthunt.com/post... Open source: pip install baar-core Would love feedback from anyone running agents or multi-tenant LLM apps in production.