This weekend holiday, I built something called Nudge.

As developers, we often talk about productivity but our systems are usually cluttered:

Too many tabs.

Too many background apps.

Hey everyone

A while ago, I came across openclaw and decided to give it a shot. On paper, it looked promising but once I actually started using it, the experience didn t really live up to expectations. It felt slow, unnecessarily complicated, and honestly not very secure. On top of that, it had a lot of limitations and couldn t handle everything I needed it to do.

That s when I thought: why not build something better?

Tired of manual logging? I deliver food 50+ hrs/week and hated it too.

So I built FitMacro the distraction-free AI calorie counter that actually feels helpful.

Snap a photo instant calories, protein, carbs & fat

Weekly AI Coaching Summary (score + adaptive targets + apply in 1 tap )

We open-sourced optimize_anything, an API that optimizes any text artifact. You provide a starting artifact (or just describe what you want) and an evaluator it handles the search.

import gepa.optimize_anything as oa result = oa.optimize_anything( seed_candidate="<your artifact>", evaluator=evaluate, # returns score + diagnostics
)

It extends GEPA (our state of the art prompt optimizer) to code, agent architectures, scheduling policies, and more. Two key ideas:
(1) diagnostic feedback (stack traces, rendered images, profiler output) is a first-class API concept the LLM proposer reads to make targeted fixes, and
(2) Pareto-efficient search across metrics preserves specialized strengths instead of

averaging them away.

Hi everyone,

If you live in Germany, you know the feeling of getting that annual "Renteninformation" letter. It s dense, only in German, and usually leaves you with more questions than answers. How much will I actually get? How does this change if I invest in ETFs? What s the "gap" I need to fill?

I spent some time diving into the math of the German pension system because I wanted to understand my own future better. I realized there wasn't a simple, modern tool that explained this in plain English (or Turkish).

Hi all! I'm Melanie, founder of Verve, a video-only dating app launching exclusively in DC to start.

Some of my friends are in the divorce season of life, and this idea was born out of so much frustration with endless texting and traditional dating apps' inability to give you a true sense of a person.

Unravl turns voice notes into organised structure. Speak naturally ramble if you want and it pulls out your tasks, events, reminders, notes, and groceries. No editing. No cleanup.

A few things worth knowing:

• Rambles become succinct notes stream of consciousness in, clean actionable output out

• Grocery list builds through the day mention milk in the morning, eggs at lunch, wine on the way home. Unravl collates everything into one running list

• 50 languages, mix and match speak in whatever comes naturally, even mid-session

• Hands-free by design built for the car, the walk, the shower thought that never survives the commute

7 days free, 60 sessions, no credit card. unravlmyspeech.com

Hey Product Hunt community!

I ve been a gamer and a dev for years, but recently, I hit a wall of frustration. We have incredible 4K graphics and ray-tracing, but the "brains" of our games still feel like they re from 2005.

Had a thought, and I must put it out here:
Over the past year, building with LLMs, I ve noticed that the big change is not necessarily that AI gives us better answers. Change your perspective and think like this: we, humans, are starting to ask better questions. And here's why:
When search engines dominated, we asked:
What is X?
How do I do Y?
Best tools for Z?
With LLMs, the questions are different:
Help me think through this decision.
Challenge my assumptions.
What am I not seeing?
Act as a product strategist and critique this.
Clarify my messy thinking.
That s not getting the information, that s cognitive augmentation.
I feel we re moving from:
Finding knowledge to extending reasoning
And this raises bigger questions for builders:
1. Are we designing AI tools that optimize for answers
or for better thinking?
2. Is the real advantage having a stronger model...
or asking better questions?
3. In a world where everyone has access to GPT-level intelligence,
does leverage come from prompting skill, system design, or taste?
4. What new human skills become valuable when execution becomes cheap?
It feels like we re entering a phase where:
Curiosity > credentials
Clarity > speed
Systems thinking > single outputs
If you re building in AI right now:
What types of questions are your users asking that they couldn t (or wouldn t) ask before?
And are you building for answers or for thinking?
Would love to hear what patterns you're seeing.
______________________
www.zackapp.space
Download Zack from the App Store and soon from Google Play: https://apps.apple.com/us/app/za...

Interior designers still spend too much time rebuilding drawings. You receive 2D floor plans and Blueprints. You trace, you model, you clean up. Only then can you start real design work.

Foursite by VirtualSpaces attacks that bottleneck. It is built for teams who want to go from 2D to 3D in minutes and then live entirely in an AI visualization and AI 3D visualization workflow.