Generate motivational quotes instantly with author attribution and HTML-ready output.

Hey PH

I built Purrnal a health diary for cat and senior dog owners. Log symptoms, vomit, litter box, weight, meds, and food in two taps, and it generates a clean PDF report you can hand your vet instead of scrolling through a notes app.

It's in closed testing on Google Play right now, and I need a few testers to clear Google's 14-day requirement before going live.

If you've got an Android phone and want to help:

Hey

15 years of watching teams ship the wrong thing because the spec wasn't clear. Then Cursor and Claude Code arrived and made it worse coding agents can't fill gaps the way a senior engineer can.

So I built Outlain. Drop in customer research (transcripts, recordings, support tickets). The AI extracts themes, ranks them by severity, and generates a complete spec Jira tickets, acceptance criteria in Given/When/Then, and an agent-ready prompt block for Cursor or Claude Code. Every line traces back to a real customer quote.

Two modes:

Hello there,
I am Alvin, and I am developing a meeting tool for individuals, groups and teams at the moment. Right on spot it is called Dundry. At this point I have been working and developing for a certain amount of time and I am ready to soon release the application on the web. For first release we will be having it web based and short after we will release it for desktop app download for both MacOS and Windows!
But, as always we need to try it out like a real thing before we actually release it. That is why I write this. We need more eyes on Dundry, people trying it out for bugs, the database flow and overall people who love to be a participant from the really beginning.
As I mentioned, we will be releasing Dundry on web as first launch, and so do we with the beta testing phase as well. I will drop some screenshots of Dundry down below as sneak peaks and if you feel like you are willing to be a beta tester, just reply to this thread.
Pssst.. the first 5 people that reply will get a free month of Dundry Pro plan subscription when we officially launch.
Hope to see you,
Alvin

I've been building AEGIS, an open-source defense layer for LLM apps/agents (prompt injection detection, policy enforcement, tool-permissioning for agents). Before I launch it here Tuesday, I want to share something I almost didn't publish.

Most guardrail projects report a round-1 catch rate against a fixed test set which tells you very little about a real attacker who adapts. I ran our detectors through adaptive red-team campaigns that breed new attacks from whatever got past the last round. The honest result: hardened, real-model detectors converge to roughly the same ~48% overall bypass rate as unhardened stub detectors by round 3. Full methodology and numbers are in the repo if anyone wants to pick it apart.

Genuinely asking this community: is round-1-only red-teaming basically theater at this point? Has anyone here seen a detection approach that actually holds up past round 2-3 against an adaptive attacker, rather than just looking good on a static benchmark?

Products in the top 10 are usually featured in the following day s newsletter, but Meridian was included today. It is an incredible milestone for our team and a strong signal that our launch has been featured.

Meridian is an open-source, local-first AI work journal that captures developer activity, organizes it into a clear timeline, and drafts worklogs and daily updates for approval.

We are still live and currently ranked #2 on Product Hunt. Your support and honest feedback would mean a lot to us.

Newsletter: https://www.producthunt.com/news...

a tool that turns complex medical research into simple, honest summaries.

The goal: help people actually understand what studies say (and don t say).

Still early would love feedback from anyone interested:

https://curecompass.app

Our next little companion is ready to spread its wings!
Meet the Parrot, colorful, curious, and probably a little too excited to start chatting with you.
A new friend is getting ready to join your browser, and we can't wait for you to meet it!
Parrot is coming soon!
Until then, come hang out with the other PetPat friends:
Install PetPat: chromewebstore.google.com/detail/PetPat/ppfpaggnedkhedggdgiolgeoiglaaaed
What do you think? should we teach it to say quack quack too?