Hi Product Hunt!

I m building Gold Dashboard at COPI TOOLS, a research-first dashboard for people who follow the gold market.

We've been running a data pipeline for about 18 months now, and one metric I keep coming back to is the real cost per successful request not just the price per GB, but the total cost including retries, failed requests, and the engineering time spent debugging.

Here's what I've learned about calculating the true cost:

1. Sticker price is only half the story

Most providers advertise a per-GB rate, but that number doesn't include the requests that fail and get retried. If your provider charges for bandwidth and you're burning bandwidth on failed requests, your effective cost per successful request can be 2 3 higher than the advertised rate.

Hey Product Hunt

Over the past few months, I ve been building Meridian Allocation.

The idea came from a problem I kept running into myself.

There is no shortage of investing content online. There are stock picks, market calls, trade ideas, macro predictions, and constant reasons to react.

Hey Product Hunt!

I built rebrief after losing days more than once to reverse-engineering someone else's codebase (including my own vibe-coded ones) - figuring out the stack, hunting for stray TODOs, wondering if a secret got left in somewhere.

rebrief scan . - and in about 30 seconds you get a REBRIEF.md: stack, a filtered history of real decisions, a risk map, and a checklist of where to start. Fully local, free, open source.

Genuinely curious: what other signals would you want in a report like this? Already thinking about a .rebriefignore file and a GitHub Action for auto-scanning PRs.

Books became digital. Music became interactive. Games became massive social worlds.

But storytelling still seems divided into two extremes: traditional books, where the reader observes the story, and games, where interaction often comes with the complexity of building an entire game.

We think there s a huge space between them.

Stories where readers make meaningful choices, explore different paths and endings, build relationships with characters, interact with RPG mechanics, and experience illustrations, music, and sound while the story itself remains at the center.

Hey Product Hunt

I've been building FlowLogic.AI solo since April, and wanted to get this community's take before I go further.

The problem: every SOP/process documentation tool I looked at (Scribe, Tango, etc.) makes you re-record your screen to capture a workflow even if you've already explained that exact process to a teammate in Slack an hour ago.

So I built something that skips that step: paste in the messy text (a Slack thread, a rambling explanation, whatever), and it generates a clean, structured SOP steps, owners, time estimates, all of it. You can edit, save, and export to Word from there.

Hey Product Hunt I built Picsabc (https://www.picsabc.com), a fully free browser-based image tool suite for creators, marketers & freelancers.

The pain I solved

I was tired of jumping between multiple sites to edit photos:

• Compressors force sign-ups or add ugly watermarks

• AI background removers charge expensive per-image credits

• Most tools upload all your files to servers with zero privacy guarantees

• No all-in-one lightweight toolkit for quick daily edits

Three weeks after launching Consile, we shipped native MCP integration, our AI assistant Otto now connects directly inside Claude and ChatGPT, so users can manage tasks and pull workspace context without switching tools.

Genuinely curious how other builders here are thinking about MCP right now, is this something you're actively building toward, or still waiting to see if it's a real pattern versus a passing trend? Would love to hear what others are seeing, especially outside the HR/ops space.

(consile.app if anyone wants to poke around, but mostly interested in the MCP conversation itself.)

We ve launched Sentinal AI a simple, functional AI assistant that you can run locally or online.

It s designed as a starting point for developers, students, and anyone curious about building their own AI system.

Basic voice interaction
Simple automation capabilities
Clean and customizable codebase
Works locally with optional online features

It s not over-engineered it s meant to be simple, understandable, and usable right away.