Ethan Samul

Ethan Samul

Customer Support Specialist

Forums

What would you build or benchmark with 5M free tokens on a reasoning model?

To encourage real experimentation, we re offering 5 million free tokens on first API usage so devs and teams can test Alpie Core over Christmas and the New Year.

Alpie Core is a 32B reasoning model trained and served at 4-bit precision, offering 65K context, OpenAI-compatible APIs, and high-throughput, low-latency inference.

If you were evaluating or using a model like this:
What would you benchmark first?
What workloads matter most to you?
What comparisons would you want to see?

Build a Personal AI Assistant with n8n on Bult.ai

We ve just published a new n8n tutorial for Bult.ai.

It shows how to deploy n8n on Bult.ai in minutes and build a personal AI assistant connected to Telegram, Gmail, Google Tasks, Google Contacts, and Calendar. The guide covers deployment, importing a ready-made workflow, credentials setup, and testing text and voice prompts.

Supabasep/supabasefmerian

1mo ago

Supabase in the Top 100 most-starred repositories on GitHub

Some metrics shared by @copple on X:

  • 10,953 forks

  • 95,435 stars

  • 1,640 contributors

First launched on Product Hunt 5 years ago, [1] this growth rate is insane.

What's coming next

Hey folks,

Here's what we're working on actively & planning to release with next update:

  • Automatic capture of memories/data entered by users.

  • Support for select/radio/checkbox fields

  • Alternate fill modes that trigger superfill.ai autofill directly from webpage without the need to open extension UI

Nikechukwum Ene

1mo ago

Hello👋, I'm Nikechukwum (Nike for short) - Creator of Story Grandeur

Hi. I'm a Software Engineer and I've spent the last three years making an app to make the narrative planning and development process a bit more efficient. I initially planned on making Story Grandeur just for myself, I do want to write my own massive story after all, but I eventually decided to make it for public use. Perhaps writers and game designers might find it useful. I've built everything from scratch solo so far, it would be a pleasure if you check it out Story Grandeur

Just Launched My Second Extension - SEO Copilot

Hey everyone! Some of you supported Email Buttons when it launched (thank you! ). Just wanted to share that I launched my second product today - SEO Copilot. Different space (Chrome extension for SEO analysis), but wanted to let you all know. Appreciate any upvotes if it's relevant to you!

SEO Copilot - Product Hunt Launch

We finished at #16 for the day - huge thank you to everyone 🙏 I'd love to hear your honest feedback

Hey everyone

I wanted to take a moment to say a huge thank you to everyone who checked out Loomoz on launch day

Mekup/mekuMusharof Chowdhury

2mo ago

Meku just crossed 10k users!

Meku just crossed 10,000 registered users, it's a big milestone for us and hits different

The AI coding and dev tool space is loud and very competitive, but seeing so many people try Meku and actually stay shows we re building something that genuinely helps devs and teams ship faster and build better web apps

Massive love to the Meku team for grinding and polishing every day, and heartfelt thanks to our early users for trusting what we re creating

Nika

2mo ago

What is the right age for a child to use the internet and social media?

I see many countries promoting social media to raise the age for using it (e.g., Australia, the UK, etc.).

The sad thing is that some parents are already giving their toddlers a tablet to "entertain" them. This hurts the child's brain development. Not to mention when they get on social media and are exposed to various trends.

GraphBitp/graphbitMusa Molla

2mo ago

The most dangerous failure in AI is the one you don’t measure

Here s something uncomfortable I ve learned building AI agent systems:

AI rarely fails at the step we re watching.

It fails somewhere quieter
a retry that hides a timeout,
a queue that grows by every hour,
a memory leak that only matters at scale,
a slow drift that looks like variation until it s too late.

Most teams measure accuracy.
Some measure latency.

GraphBitp/graphbitMusa Molla

2mo ago

The most dangerous failure in AI is the one you don’t measure

Here s something uncomfortable I ve learned building AI agent systems:

AI rarely fails at the step we re watching.

It fails somewhere quieter
a retry that hides a timeout,
a queue that grows by every hour,
a memory leak that only matters at scale,
a slow drift that looks like variation until it s too late.

Most teams measure accuracy.
Some measure latency.

Nika

2mo ago

How many of you are planning to invest in AI influencers in the future?

Many brands have their long-standing mascots (McDonald's, Mr Clean, Michelin), etc. But with the development of AI, physical forms are moving online, and AI avatars look promising in this.

On one hand, it feels less human (authentic), on the other hand, AI influencers are a "cheaper" solution.

Meet-Ting Team In The Wild: Web Summit + San Fran

Hey all,

Me & @marianaprazeres will be at Web Summit in Lisbon (presenting on Weds on Alpha) this week and we're in San Fran (16-20) next week - if any builders want to connect with us, we'd love to say hello!

Dan

Is MindPal just ChatGPT with extra steps?

We just launched MindPal today on Product Hunt, and as a no-code AI agent builder platform, one of the questions we got asked the most is: Why do I need MindPal when I have ChatGPT + Claude?

Fair question. Except it's comparing a personal assistant to a business multiplication engine.

Dropstonep/dropstone-2Santosh Arron

2mo ago

Why we built Dropstone — the AI IDE that remembers

Every AI coding tool today suffers from the same flaw amnesia.
It forgets what you ve done, what you re building, and how you think.

Welcoming Feedback!

Hey Product Hunt

You know how AI search is eating everyone's Google traffic? We kept watching brands show up everywhere on Google then completely disappear when people asked ChatGPT or Perplexity the same question.

Storesmanger got a new upgrade !!!

Store Manager is an all-in-one e-commerce SaaS platform designed for creators and small sellers who want to run their business without technical hassle. From managing inventory and tracking orders to analyzing customer behavior, everything happens in one clean, easy-to-use dashboard.

Our newest update introduces custom storefronts, allowing sellers to design their own branded online shops with themes, colors, and layouts no coding required. It s the fastest way to turn your idea into a professional online store.

Each account includes a personal AI Store Manager, your built-in assistant that helps answer customer queries, gives business insights, and automates tasks. Try it free for your first month!

Shotgun is now open source 🎊

Shotgun writes codebase-aware specs for AI coding agents so they don't derail.

The problem we're solving: AI agents made developers fast at building. Also made them fast at building the wrong things. Cursor, Claude Code, Copilot they generate code immediately without asking: does this already exist in your codebase? Does a better solution exist externally?

What Shotgun does:

Research Specify Plan Tasks Export

What if AI frameworks worked like flight systems, not magic tricks?

Think about it.
When a pilot takes off, they don t hope it ll work.
Every system has a checklist. Every fault has a fallback.

But in AI?
We still deploy and pray.

When AI stops being your tool… and starts being your teammate

Here s a weird shift happening quietly:
AI isn t helping us anymore, it s working with us.

We used to build tools that waited for instructions.
Now, we build agents that make decisions.