Connect with the Product Hunt community

Founders ! drop your startup below :)

I'm gonna check every single one and give you feedback.

Here is mine : Murmell, it's basically google docs for AI coding agents, you can collaborate with your friend in the same board and use multi providers coding agents in the same rooms, and all that, in the cloud.

Hi product hunt !

We re currently building a multi-provider cloud alternative to Grokbot, and there s one feature we keep debating internally.

I am at the stage of building a landing page for my Chrome extension tool.

That one will be created via vibecoding.

Hi everyone,

I have been researching and building a mobile utility for field contractors and service workers. During the development process, one major architectural decision came up: Cloud vs 100% Offline.

Many field professionals (contractors, technicians, inspectors) work in areas with poor or zero cellular coverage. Cloud-based SaaS tools often freeze or fail to sync in these conditions.

On the other hand, an offline-first approach keeps all data, documents, and photos strictly local on the device, ensuring instant speed and complete privacy.

Hey everyone

Netfox 0.22.0 is out, and it is about one thing: the window finally behaves when you tile it.

It used to refuse to go narrower than 960 points. So if you put it beside the thing you were actually working on, its right edge went off the screen. It was an app you opened, glanced at, and closed

Two weeks of SkillDocs
I launched SkillDocs on August 12 collaborative markdown for the files that teach your agents how to work. Live cursors, inline comments, and an MCP server so the agent works the same loop you do.
Here's what's landed since. Full changelog with screenshots: https://skilldocs.dev/changelog
New things:

• tables are a live grid you edit in place, not a picture that falls apart the moment you click into it.

• Focus mode on F. Try it. it's beautiful.

• Nested folders, and any folder opens as a sortable table.

• `skilldocs_find`, so an agent coming back tomorrow can ask "which doc is this file?" instead of needing an id it no longer has.

• MCP moved to a URL nothing to install, works in any client with OAuth, so no year-long token travels through your shell history.

• Paste a GitHub repo URL and pick what to import.

• Comments now pin to characters in the CRDT, so editing inside a quoted phrase stops orphaning the thread.
  Here are three of my favorite improvements:
  Dark theme

  

  It toggles from three places: the next to the wordmark, the on the style bar, and Appearance in the settings menu. One state, three doors. Each cycles Light Dark Match system, and Match system follows the OS live. Plus - I love how the logo looks in dark mode.
  The skill listener

  

  Nobody knows which skills their team actually uses. You can guess from the repo, but the repo tells you what exists, not what runs.
  Merge a two-file hook into your skills repo and counting starts for everyone no per-person setup, no token to paste. Identity comes from git email, and the server accepts a claimed count only when the named repo is a connected source of that workspace, so nobody can inflate someone else's numbers. It sends the skill name, the repo, a git email and a timestamp. Never prompts, never arguments, never file contents. `SKILLDOCS_LISTENER=off` opts out.
  The same beacon carries a hash of your local skill file. If it differs from the doc's latest published version, your agent gets one short note, at most twice per version, then it stays quiet. Nothing ever writes a skill file for you.
  K palette

  

  Jump to a doc, run a command, enter focus mode, format the selection, or change the theme. All from K. h/t @Superhuman
  ---
  If you're writing skills with other people, I'd genuinely like to know where this breaks for you. I'm trying to make this the most collaborative, beautiful way to review and edit skills.

How do you test a workflow that spans four services?

Been hitting the same wall for a while and curious how others handle it.

What's the failure shape?

Someone books a flight to London. Four things have to happen: confirm the booking, send a Slack message, fire a confirmation email, block the calendar. Travel is one vendor, messaging is another, email is another, calendar is another.

Hey everyone

Netfox 0.21.0 is out, and it is mostly one feature plus a confession.

The struggles you may face in terms of Product Hunt discussions are:

Your post wasn't approved

You do not know what to post about (we talked about it yesterday)

Your post was approved, but nobody interacts

I m curious how people are actually using coding agents today.

Do you mostly use them directly in the terminal, or through an app/interface like Cursor, Claude Code, Codex, etc.?

Been working on this update for a while, and I wanted to share what s new in 3.0.

As Termexo s maintainer, I am focusing on a practical problem: several agents can be working while the developer is still finding terminals, checking who needs approval and reconstructing task context.

For individual developers, Termexo groups real terminals by project, surfaces agent status, organizes tasks and helps resume supported native sessions. Handoff packages can carry a reviewed summary of progress and next steps.

Hello guys,

While building Murmell, my Co-Founder tried gemini 3.8 and damnnnnnn it's insane

it's way too fast and efficient,

Use this command in ChatGPT:

/visualize my codex usage

Play's Age Signals terms limit the signal to age-appropriate experiences and name advertising, marketing, profiling and analytics as prohibited uses, with app takedown as the stated penalty. Apple's version hands you the age plus how it was proven. Both are live now in a widening list of regions, and the default engineering reflex is wrong for both.

There's a new field arriving in mobile apps this year and almost nobody is treating it as a product decision. It's the user's age, handed to you by the store instead of asked for in your onboarding.

Small maker update: Local Music Organizer 1.1.19 is now out.

The biggest change is a major update to the Live Spectrum Player, but there s also a lot of work under the hood around large library performance, Library Index restore, Health Check, File Maintenance, and reliability.

I also fixed an annoying edge case where Music.app could repeatedly open Locate for a missing local file.

The user manual has been completely reworked as well it s now a much more detailed, illustrated guide covering the current workflows, controls, safety boundaries, and the intended way to work with large local/offline Music.app libraries.

After building and launching 4 B2C macOS apps, I decided to release one of our internal tools that helps us evaluate and track marketing channels.

Days of preparing for the launch, setting up onboarding, landing page, redesigning the dashboard, testing, and more.

Converting an internal tool built for our needs into a standalone product is not as straightforward as you might think.

Existing workbench screenshot (v0.8.0), shown for context.

I'm the maintainer of Termexo, an MIT-licensed Windows workspace for Claude Code, Codex and OpenCode.

v0.8.7 focuses on a frustrating reliability problem: an agent could keep running while its terminal went blank and appeared stopped. Resizing around a wide character could trigger a parser panic, poison the screen mutex and leave subsequent screen reads failing. Switching between clients could reproduce that combination.

Since our last launch we've been heads-down on one thing: making "this integration works" actually mean something. Here's what changed, and why we're more confident than a month ago.

What we shipped?

Five integrations now recognize the bugs people actually hit and prove the fix with a real before/after:

Imagine an AI agent responsible for routing inbound leads. Nothing crashes. No alerts fire. The workflow keeps running exactly as expected.

The problem is that the agent has slowly started sending high-value leads to the wrong queue. Maybe a few customer issues are being summarized inaccurately. Maybe records are being updated with small mistakes that seem harmless on their own. Each individual error is easy to miss. Over time, though, the impact starts to compound.

Those are the AI failures that interest me most because they rarely look like failures at first. There is no outage, no red warning message, and no obvious signal that something is wrong. The workflow continues operating, but the quality of the outcomes quietly drifts away from what the team intended.

That makes detection a different challenge altogether. It's less about system uptime and more about observation. Are there feedback loops? Quality checks? Escalation paths? Can someone spot a pattern before customers, revenue, or operations start feeling the effects?

Before Harden: approve every action.

After Harden: let it run.

it starts clean. admin, editor, viewer. three roles, clear boundaries, everyone knows what they can do.

then the product grows. a customer needs access to one thing but not another. a team member needs editor rights in one context and read-only in another. someone asks for a role that's basically admin but without the billing tab. and suddenly you have eleven roles, three of them named some variation of 'editor-but-not-really,' and nobody is confident the permissions are actually right anymore.

Running four AI tools means four tools that each know a different half of what you told them. On a team it gets worse, because the half your colleague explained on Tuesday never reaches you at all.

I have been building Second Brain around that problem for a while. Today the team version went live: every member gets a private layer, the team gets a shared one, and recall reads across both. It runs in your own Cloudflare account and it is still MIT.

i can never tell what is a genuine from a real user versus someone just hyping up their friend's project. Some discussion threads feel authentic, where people ask tough questions, offer genuine feedback, and point out potential issues. Other times, the whole section is just a wall of generic praise like "congrats on the launch" and "this looks incredible" without any real substance.
It makes it hard to gauge whether a tool is actually solid or if people are just being polite. I find myself ignoring most of the surface-level compliments and actively searching for the few comments that bring up actual use cases, flaws, or comparisons to existing tools.

How do you evaluate the feedback on a launch page? Do the comments ever actually change your mind about giving a product a shot, or do you ignore them entirely and just test things out yourself?