Connect with the Product Hunt community

FinderGit 0.57.0: groups inside groups

The sidebar's groups used to be one level deep. Now a group can hold other groups, as deep as you like: Work Clients Acme, with your repos wherever you put them.

I come from corporate finance. Before starting my app, I had basically zero coding experience.

Fast forward to today, and I've managed to build and launch an actual iOS app using AI-assisted coding.

I'm still learning every day, but there are some things I've realized that I rarely see people talking about when discussing vibe coding.

1. AI can build something you don't understand. And that's dangerous.

FinderGit 0.56.12 is a fixes release

Got a branch and a tag with the same name? FinderGit used to list the branch as heads/main, and Checkout left you on a detached HEAD. Now it shows main, Checkout keeps you on the branch, and merging, rebasing or branching from it uses the branch's commit, never the tag's.

Our first Product Hunt launch landed us #5 Product of the Day. Not bad for our first try.

Tomorrow, we're back with Causo 1.0. And this time, we're launching something much bigger.

Last time, we launched our fundraising tool. Since then, we've built an entire sales product, redesigned the platform, and rebuilt much of the engine behind it.

Here's what Causo does now:

A landing page on static hosting almost never goes down. The API, the app and the database behind it do, and the homepage stays green the whole time.

A brand might appear frequently in ChatGPT or Perplexity answers, but that doesn't necessarily mean it's being recommended as the best choice.

There's a difference between being listed among several options and being positioned as the solution a buyer should consider.

Hey PH

Small release this week!

Improving a follow-up prompt in ChatGPT, now uses the whole conversation as context.

Hi everyone,

today I want to share some exciting news with you about Basket Score something that will completely revolutionize the way games are streamed.

Introducing the new AI-powered scoreboard reader.

Quick build-in-public update from Sponkly (real-time voice translation for chat, calls and meetings in 32 languages).

This week, as a solo bootstrapped founder:

• NVIDIA Inception: accepted

• AssemblyAI Startup Program: accepted

• AWS Activate: $10,000 in credits

• LiveKit Startup Program: approved today, $17,000 in credits + a year of the Scale plan

What I will use it for: Sponkly's calls and meetings are peer to peer today (WebRTC mesh). Great for 1:1, heavy beyond 5 6 people. Moving meetings to LiveKit rooms means one upload per person, so translated meetings can grow, and the live interpreter can join as a LiveKit agent that hears each speaker directly and translates once per language instead of once per listener. 1:1 calls stay peer to peer (cheapest, end-to-end).

Hey PH
One use case keeps coming up with agencies, so we wrote it up properly so others can reuse the template.
The problem: an agency runs 10 clients through ChatGPT, Claude and Gemini. Every writer pastes a different version of the style guide, two clients end up in the same thread, and freelancers take their prompts with them when they leave. The result is voice bleed: Client A's copy starts sounding like Client B.
How teams are solving it with AI Context Flow:
One memory bucket per client: voice rules, audience, banned terms, on-brand and rejected examples, compliance limits
Shared buckets: contributor and viewer roles, an activity log of who changed what, and version restore
The MCP server: the same client voice in Claude, ChatGPT, Cursor, Copilot, Windsurf and headless agents. The AI pulls only the relevant context and writes client feedback back to the bucket
Full playbook, including a copyable voice-bucket checklist: https://plurality.network/blogs/...
If you run an agency or a multi-brand content team, I'd love to know how you handle client voices today, and what's still breaking, maybe we could make a custom built setup done-for-you. lmk below

We always hear about Silicon Valley, San Francisco and others.

But lately it seems like there are more emerging...

Hi everyone, Ashish here from Atlaso.

This week GitHub shipped Copilot Fusion, which routes one coding task across several models and lets a second model critique the first. Gemini 4 Carbon is also near the top of Product Hunt today. Switching models is quickly becoming the default.

A Semrush analysis of 1,094 US commercial categories found that only 15.2% had a clear brand leader in ChatGPT recommendations.

The study also found that 89.3% of estimated search demand belonged to categories where no single brand consistently led recommendations.

I recently launched Pinky Promise, a little app for making promises with friends.

The feedback has been lovely. People call it cute, say it's a great idea, and seem to like the concept.

But here's the thing: I'm not sure people would actually use it.

what kind of checks and balances to you implement to make sure the numbers are accurate, at least the critical ones. Anomalies are easier to spot, but minor but important inaccuracies are tough to identify.

I used to describe a feature and let the agent build immediately. It felt fast. It wasn't. The architecture got decided implicitly by whatever the agent tried first.

When that first approach was wrong, everything built on top of it was wrong too.

Your website tells one story about your brand. Reviews, comparison articles, industry publications, and community discussions might tell another.

When buyers ask AI for recommendations, these external sources can influence which brands appear and how they're described.

I recently saw a reel where a girl was recording a Skill with Claude to find newly posted real-estate apartments every day.

She had specific filters - location, price, etc. and Claude would go through the new listings, find the ones that matched, collect all the relevant information, and create a spreadsheet with the results every day.

I can't say that these routines will make me a mega-effective weapon, but at least they clear my head, and I work better when I incorporate the same things into my day:

• for example, an hour of exercise (physical activity)

• a daily walk outside I've noticed walking among several founders who also have a fairly sedentary job at a PC when they develop

• at least 7 hours of sleep

• a bar of dark chocolate (it contains quite a few important nutrients  zinc, iron etc.)

Is there anything interesting in your repertoire that improves your performance? It could be completely "negligible" hacks.

you're moving fast, you've shipped login, it works, users are in. and then an enterprise prospect shows up and the first thing they ask is 'do you support SSO?' and suddenly the thing you built in a weekend is blocking a six-figure deal.

but SSO is usually just the first question. after that comes the security questionnaire. then someone asks about audit logs. then their IT team wants to know how they'll provision and deprovision users at scale. then legal asks about data residency.

Why Dots isn't just another notch music player

Most notch apps focus on media controls, battery indicators, or simple bounce animations. We wanted to build something that actually drives daily productivity no matter what field you're in.

Dots transforms your Mac notch into a customizable workspace HUD that adapts to diverse workflows:

• Developers & Engineers: Monitor live AI agent workflows, background scripts, and Apple Shortcuts without context-switching.

• Creators & Editors: Drop files into the top-edge shelf for instant conversions, or trigger picture-in-picture videos while keeping your main timeline clear.

• Managers & Presenters: Use built-in screen highlighting tools to spotlight key data during live calls and screen-shares.

• Students & Professionals: Stay locked into deep work with discrete Pomodoro focus timers right in your line of sight.

As search becomes a core part of AI workflows, things like data coverage, QPS, and cost start to matter, especially when your agent needs to search repeatedly across different sources.

That's why we've launched AnySearch Pro , built for developers and teams running AI agents and search-heavy applications.

68% of US Google searches in early 2026 ended without a click. For every 1,000 searches, only 276 clicks reached the open web.

But fewer clicks don't necessarily mean fewer opportunities for brands to get discovered.

we keep getting surprised by what people do with their calendars once an agent can read them. so far we've seen home automation arming the alarm when nobody should be home, families running their shared iCloud calendar through ChatGPT, and people letting Claude set up their syncs.

mine: "find me 2h of focus time this week and block it everywhere"

what's yours? something you already do, or something you wish worked. we read every reply and it shapes what we build next

TL;DR: every fact in our graph is its own node, with properties on it. The vocabulary behind those nodes is RDF/OWL. Neither camp would call this clean, and Wikidata is not strictly one or the other either.

Here is why we ended up there.

What forced it

Our facts need to carry things that are not part of the fact: where it came from, how confident we are, whether a human has reviewed it, and when it was true. Not this document mentions X , but this specific assertion came from page 4 of this version of this document, confidence 0.8, reviewed by nobody yet, valid from March .