Self-Promotion
p/self-promotionShow off what you're working on
trending
Adana Marukhyan

10d ago

Is there a chance for a product with zero AI on Product Hunt?

I've already have 24 days streak here in Product Hunt and watching almost all daily launches.

The pattern is hard to ignore - nothing ships without an AI angle anymore.

It seems like a must have in every single product.

What do you think, does a plain, well-crafted and useful product even have a chance in this market?

Robat Das

10d ago

How I stopped surprise $40+ LLM bills from agent loops (pre-call hard limits)

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.
Mukesh Reddy

2mo ago

I built FounderScope — a lightweight real-time founder movement dashboard.

Hey PH community

As someone building in the Indian startup ecosystem (Hyderabad), I kept missing key founder signals. One founder raises in Mumbai, another visits my city, someone starts hiring talent or drops a podcast and I only find out days later.

That frustration led me to ship FounderScope in just a few days using Lovable + Supabase.

It aggregates founder activity across the internet social posts, podcasts, launches, events, hiring signals, and even city-visit alerts into one clean, actionable dashboard.

Roland Becker

10d ago

Can web designers reliably check BFSG conformity without a full legal audit?

I am validating a product idea for web designers and small agencies.

Problem:

Accessibility scanners find issues, but they do not tell you whether a client website is actually BFSG-ready or what prevents conformity.

I’m building a tool to make YouTube workflow less annoying — what would you want tested?

I ve been building a project called GetVidForge because I kept jumping between different tools for scripts, titles, thumbnails, and keyword research.It s not finished yet, but a few parts already work and I d love feedback from other creators. I m especially interested in what feels useful, what feels unnecessary, and what would make you actually use something like this.If you were testing an early YouTube workflow tool, what would you want it to do first?
Nodminger

10d ago

60 to 70% customer support tickets are repetitive. So we built a tool to handle them.

We kept seeing support teams answer the same questions over and over again every day.

Traditional chatbots didn t solve the problem well:

  • too robotic

  • too limited

  • too frustrating for customers

So we built RecallAssist. An AI-powered support platform trained on your docs, FAQs, and knowledge base to instantly respond to repetitive customer queries.

Van Nguyen

10d ago

How are you mocking APIs during frontend development today?

I ve tried a lot of workflows over the years:

  • editing local JSON files

  • hardcoding mock states

  • running proxy tools

  • setting up mock servers

  • intercepting requests with external apps

But I still felt the workflow was slower than it should be especially when debugging edge cases like:

  • empty states

  • failed requests

  • slow APIs

  • malformed payloads

  • role-based responses

Snapdocx

22d ago

Snapdocx — Free PDF & AI Image Tool for Android. Would love feedback!

Hi Product Hunt community! I built Snapdocx a free all-in-one PDF & AI image tool for Android. Key features: PDF merge, split, compress OCR in multiple languages AI background remover Document scanner Encrypted vault 100% offline no data collected ever Playstore link : https://play.google.com/store/ap... Would love your honest feedback what features would you want added?
Ali Berk Canli

10d ago

I built an agent that "thinks" in front of you, but never leaves your room.

The most interesting part of automation isn't the execution it's the recovery.

I built @SignalForge to be a sovereign execution layer. Instead of a "black box" cloud API, it uses a local observation loop. If you pull the internet plug, it keeps working. If the UI changes, it doesn't crash; it "looks" again, builds a new evidence model, and finds a workaround.

It s like giving your browser a pair of eyes and a local brain that actually learns from its mistakes. No data tax, no cloud leaks. Just pure, deterministic execution on your own hardware.
"I m looking for the most hostile, 'un-automatable' web interfaces to test our recovery logic any suggestions?"

First
Previous
•••
383940
•••
Next
Last