Connect with the Product Hunt community

We teamed up with @GoogleCloud for a Cloud Run Hackathon October 14th!

To kick things off, we're celebrating on the leaderboard so you can meet the people behind Cloud Run.

I opened our invoices this morning... and closed them right away hehe

Claude Max for the whole team, the API on top for our agents, a few other tools here and there...

I guess most of us started the same way...

One person, one laptop, one agent!

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:

What started with a simple idea is growing into a community of people who want to move money across borders more easily.

For us, RunEvr is the environment where we actually build RunEvr =)

For me, that s one of the most beautiful parts of having a product - using it while continuing to build and improve it.

We do our everyday calls there, share ideas, chat, store files, do reviews, complete tasks

And all of this is happening inside the same environment we re building to help other teams do exactly that!
Kind of a mirror within a mirror =D

Hi Product Hunt! AgentDock launched here on 10 October. Since then it has had eleven updates, and the latest one is the biggest: AgentDock now works with many more agents than Claude Code and Codex.

New in 1.3: more agents

• Beyond Claude Code, Codex and Grok, AgentDock now reads Gemini CLI, GitHub Copilot CLI, OpenCode, Kilo Code, Antigravity CLI and Claude Cowork, and shows Cursor's agent under its own name. Their dots show when they're working, waiting for you and done, and their finished turns go into History, Activity and Tokens. Nothing to install.

• They're in preview until each one is checked in a live session: turn them on in Settings Agents. Answering from the Inbox and typing replies stay with Claude Code, Codex and Grok for now.

• Tokens from the other agents get their own series in the hover card and the Tokens widget.

• The full list, and what AgentDock reads for each agent: agentdockapp.com/agents

You asked, it shipped

Whenever I travel abroad, I can usually get by with English.

In the rare cases when I visit countries where very few people speak English, I can still manage with a translation app.
And now, AI can even translate conversations in real time.

I only learn foreign languages these days to fill my free time (if I have any left).

The one where a new email no longer holds you in a queue behind itself. You tap the notification, Skim was already downloading that exact message, and it used to make you wait for that download, give up on it, then start again from scratch. Efficiency!

Fixed

• Opening a message you just got is quick again. Clicking a message that had just arrived could hang on "Fetching from the server " for up to a minute. Your click used to wait in line behind the background download that runs when mail lands, including the download of the very message you clicked. Now clicks go first.

• Work in progress isn't thrown away. If you open the message Skim is already downloading, the open waits for that download to finish and uses it. Before, it cancelled the download, reconnected and fetched the same message again.

• Bursts of mail don't pile up. When several messages land at once, their background downloads merge into one batch with one time limit. They used to queue up one after another, each with its own 15 seconds.

Housekeeping

Lancetta 0.62.0 is out Maintenance now cleans up after your coding agents, and reads Claude Code's settings the way Claude Code does.

1. Storage

Codex installs that stopped halfway, old server releases, empty git folders, files ChatGPT copied out, build caches of ended sessions, Chrome's clones: each with what it frees and why it can go. Nothing a running program holds is offered, and it all goes to the Trash.

Hey makers

"Why are my emails going to spam?" is a question people now ask ChatGPT instead of Google. Until now, the answer was a generic checklist, because ChatGPT can't read your DNS.

Hi,

FinderGit 0.54.0 is about the Agents dashboard. It already reads what your coding agents load before they start; now it also finds what they leave behind on disk, helps with a skill listing that has grown past its room, and reads Claude Code's settings, and your organization's policy, the way Claude Code itself does.

What the agents leave behind

I came across this question in the YC application:

Please tell us about the time you most successfully hacked some (non-computer) system to your advantage.

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 zero-click search happens when users get the information they need directly from search results without clicking through to another website.

Zero-click searches accounted for 60.45% of Google searches in 2024, rising to 68% in early 2026.

Quick poll for founders (and anyone who tests out new SaaS tools): do you ask for a credit card upfront, or let people straight in?

We went with requiring a card for k dlo. The thinking was pretty simple: fewer signups overall, but higher intent people actually kick the tires instead of bouncing after two minutes. Without a card, you get a flood of accounts that log in once and ghost.

But I m genuinely torn here. A card wall definitely kills casual curiosity, especially when you're an unknown product. On the flip side, no-card trials often just give you vanity metrics that don't convert.

Two quick questions:

To build something, expand an idea into a working plan, or simply give life to something new, we need conversations.

But what happens when you're building alone?

Making a product is one big challenge. But shifting your mindset from building to marketing it might be an even bigger one.
As makers, we spend so much time improving the product. Then comes the question: How do we get people to discover it - and ultimately turn that attention into real customers and sales?
I'm not sure traditional approaches like email marketing and constantly posting on social media are enough anymore. The way people discover products is changing.
So I'm curious:

How do you approach marketing your product?
And for the marketers here:
What would you consider a modern marketing approach in 2026-2027? What would you advise an early-stage founder to focus on?
I'd love to hear different perspectives...

You are halfway through debugging on a remote host. A command is still running, but you need another shell to inspect a log. Do you reconnect, pass through the jump host again, and find your working directory all over again?

This small interruption is why I added Duplicate Tab to xtty. It opens an independent SSH connection to the same host in the same remote directory, while the original session stays where it is. Watch that moment in our walkthrough:

I would love to compare workflows: do you use tmux, another terminal tab, an IDE, or something else for a second remote shell? What part still feels unnecessarily repetitive?

DungeonQ's goal is to give security teams and authorized defender agents time and space to respond while a designated suspicious session works in a persistent synthetic world.

v0.15.0 adds a reproducible console showing the next step: what happens after an alert?

1. A real MCP client enters the workspace, checks conflicting claims and saves a note that survives restart. Wrong Tickets remain useful only inside their issuing world. A claimed "source restored" message does not change the route. Follow-up work is bounded and offers a stop; participant text cannot authorize operator changes.

2. A separate local receiver acknowledges an alert and rotates a temporary connector credential. Readbacks check that old authority and old-ticket use are denied, authorized new reads work, and those results survive restart.

After enough "can I run the tests?" prompts, "can I send this to your customer?" risks becoming another button to clear.

Five months ago I asked here how people keep track of their agents. The replies went well beyond coding. In a later discussion, a builder running customer support agents made a point that stuck: people stop reviewing when checking the draft takes longer than writing the reply themselves.

One thing I've been thinking about while building tooling for AI agents is that a budget and a cost estimate solve two very different problems.

A budget tells you what you're willing to spend. A prediction tells you what a task is likely to cost. Neither guarantees that the task will finish within that amount.

Hey makers

On launch day, most of us email our users, our list, our network. Almost nobody checks where that email actually lands.

Two days out. The Google Cloud Run Hackathon is this Wednesday, October 14, and submissions close at midnight PT tomorrow.

The mechanics, one more time:
- Deploy and run your product on Google Cloud Run that's what makes you eligible
- Schedule your launch for Wednesday, October 14
- Get it in before midnight PT tomorrow

Every eligible launch picks up $50 in Google Cloud credits. Winners take $500 in credits, a spotlight on Google Cloud's own channels, and a 1:1 with the Cloud Run team.

I just walked out of the gym, and I feel ready to move mountains! =D

For a while, I gave up exercising. And yesterday, the bell rang when my teammate asked the whole team: When was the last time you did some sport?