Connect with the Product Hunt community

CipherLock is going on hold for a while, and I wanted to say it here instead of just going quiet.

This week I started a software development internship, on top of my university courses and my undergraduate thesis. Right now I can't give the project the time it deserves, and I'd rather pause it honestly than keep it half alive. My thesis is on lightweight cryptography, so I'm not leaving the subject, just this project for a bit.

Hi everyone, Takahiro here. Chronock brings Google Calendar and Outlook together with scheduling links and automatic event copying.

WP Bones is back on Product Hunt: 33 releases since the first launch

On August 5, 2024 WP Bones launched here at 1.5.5: a framework that brings Laravel's habits to WordPress plugins. Two years and 33 releases later (1.6.0 3.0.0), here's what's new

Secure by default (3.0)

Hello! Thank you all for the support with our launch today.
I know a lot of you follow OpenSEO from our launch back in July.
If you've been using the product and you enjoy it, a review would help a bunch:
https://www.producthunt.com/prod...
I just learned that Product Hunt has "Best SEO Tool" Style listicles and its based on reviews more than anything else.
Curious if we can get by and get AI mentions just from Product Hunt instead of asking people to click through those super long G2 / Trustpilot reviews.
Anyways, figured I would ask + let me know if you've all had success getting reviews some other way.
Appreciate it!

DungeonQ now includes a small MCP client you can copy into another Node project. It uses the official MCP SDK and Node built-ins, connects through the public MCP interface, and imports no DungeonQ runtime code.

The example follows a concrete task: read an artificial order and its review policy, save a multiline review, read it back, then issue and use a one-use world ticket. The ticket works inside its synthetic world. Shipping stays pending.

The client receives only an actor endpoint and token. An operator can observe the session and explicitly apply a finite adaptation policy through a separate interface. A "continue" message simply resumes the client; it cannot approve that policy or give the client operator authority.

This is a reusable integration example for DungeonQ's defensive deception runtime: give a designated suspicious session a persistent world to work in while people or authorized defender agents prepare a response. Creating that time and space is the product goal; measured defensive effectiveness remains unproven.

DevCleaner started as a macOS app with a simple goal: help developers understand where their disk space is going and safely clean up files left behind by development tools.

Build artifacts, caches, dependencies, simulators, package managers and other development data can quietly grow to tens or even hundreds of gigabytes.

We borrowed a GPU. Now we're experimenting with borrowing the Internet.

Kanverse started with a simple question:

What if computing resources didn't have to belong to the device using them?

We've already been experimenting with borrowing remote GPU capability.

We've taken the huge step of releasing the Upsolve free plan! Now anyone can get access to high quality data analysis with state-of-the-art continuous context management absolutely free. With our generous AI credit offer (2,000 credits, $100+ worth of LLM calls), you can build as many charts and reports as you need without worrying about your token spend. Give it a spin at https://upsolve.ai/

I've been reading the Product Hunt Forum Guidelines repeatedly, trying to understand why some threads get through and others don't.

The guidelines say: "If it's not a genuine question or a genuine insight, we won't approve the comment or we'll put it in self-promotion."

I've been thinking about the "insight" part. A genuine insight isn't a lesson. It's not a framework. It's not "10 things I learned." It's an observation that helps someone see something differently.

The difference between "here's what I learned about pricing" and "I raised my prices and lost zero customers here's what actually happened" is that the second one is an insight. The first is content.

WP Bones 3.1 is out your generators, your templates

Your stubs come first. Every make:* command reads the stubs/ folder of your plugin before the framework's, and tells you when it does.

Loqua is LIVE on Product Hunt today, and welcome to the family!
AI keeps getting smarter yet using it feels more tiring: prompting, switching apps, screenshotting, explaining context again and again. Often the problem isn't the AI; it's that we still have to learn how to talk to it.
So we built more than better voice typing. Just say what you want, and Loqua understands your app, screen, language, and tone dictate in Gmail, ask about a chart you're looking at, tell Codex or Claude Code what to change, set reminders, open apps, or have a page read aloud.
We believe voice agents are a necessary path to AGI and a core part of physical AI. As a model-first team, Loqua is our first step: our own multimodal model for better transcription, translation, and multimodal Q&A, with deeper agentic, long-horizon abilities rolling out.
If this resonates, we'd love your support
An upvote unlocks a promo code, and sharing earns extra days. Try it and tell us what you'd want it to do next.
Upvote & try Loqua:
[Website link]: https://theloqua.ai/
[Product Hunt link]: https://www.producthunt.com/prod...

rhun 0.17.7 is out. It s the largest minor release I ve put together so far, and the one that received the most help from the community.

For anyone new to rhun: it s a small, fast code editor written in Assembly, with a built-in terminal, Git tools, and a panel for Claude Code and Codex sessions. It runs on Linux, macOS, and Windows.

A few highlights:

• Agent sessions across Git worktrees now show up in the Agents panel, with more reliable discovery and refreshes.

• Click file paths in the terminal to open them in the editor, including line and column references. Use Cmd+click on macOS or Ctrl+click on Linux and Windows.

• Smoother touchpad scrolling, adjustable scroll sensitivity, and horizontal scrollbars for long lines when word wrap is off.

• Better panel resizing, scrollbar auto-hide, and a scrollbar in Settings.

• Shift+Enter now works as expected in terminal tools that use the kitty keyboard protocol, including Pi.

Six months ago, we launched Naoma on Product Hunt.

You made us #1 Product of the Day and then #1 Product of the Month in Marketing.

Since then, we ve been watching people use the product, talking to customers, and learning what an AI demo agent actually needs to replace the first part of a sales conversation.

On Monday, we re launching Naoma V2.

WhaleRead 1.19.1 is now available for Apple Silicon Macs running macOS 15 or later. If you tried the 1.18 preview or 1.19.0, please update from the GitHub release.

October 6 maintenance update: 1.19.1 fixes overlapping source letters and translation in original-position reading of scanned PDFs with a hidden OCR text layer. Saved translations and the original PDF are retained; the display refreshes automatically without translating again. Untranslated passages and figures stay visible.

The application is now free and open source under GPL-3.0, with optional donations instead of paid unlocks or a subscription.

What's new in 1.19:

Version 1.2 is live and now you can use all .wsz skins that you remember from back in the day! Enjoy!

Here's a workflow I've found worth experimenting with when working on existing codebases.

Instead of immediately asking AI to fix something, separate the process into three stages.

Stage 1: Investigation

Ask:

WP Bones 2.1.1 is out a small patch, two fixes

Activation sees its own plugin. Since 1.8.0 the activation hook ran with an empty slug and no version, so the options it aligned were saved to a row with no name. Fixed.

I've spent a lot of time thinking about the difference between testing a product and validating it.

When you're building software, there are so many things you can measure. Does the functionality work? Are the calculations correct? Can users complete the workflow? Are the security controls working as intended?

Those are important questions, and you can spend months getting them right.

But there's another question that technical testing can't fully answer:

Guys, as i said we will be always transparent, after months and months and building, i got this stripe notification !
It's a small milestone but it means a lot for us !
We aim 10k by the end of the year !

I dont know why when i am comment and engagement , my commentes got hiddent even though i dont use any automation ai i just want to participate and learn help on that

i tried to mail product hunt team got reply but still same issue how this algo work ? how they classify which is genuine comment and which is not

Hey everyone! We're thrilled to launch AuthMonster to the world, and we're eager to hear what you think - try it out on Android and iOS and share your feedback with us here. Anything is useful - what you love, what you hate, and what you think is missing. Let us hear it!

Launched earlier this month with support for @GitHub, @Linear, and @Slack, Mastra Factory now supports three new intakes: @Jira, @GitLab, and @incident.io, giving you more ways to manage and resolve issues, feature requests, and incident follow-ups.

Get started:

npm install @mastra/factory@latest

We keep talking about AI agent costs as: model price tokens requests

But agentic systems add another cost: uncontrolled execution.

• An agent retries a tool 5 times.

• Calls an expensive model when a cheaper one would work.

• Loops through unnecessary steps. Hits APIs it didn't need.

• Delegates work to another agent.

WP Bones 2.1.0 is out the bones CLI that ships inside every plugin gets sturdier

Runs from any folder. php my-plugin/bones used to stop with a TypeError anywhere but the plugin root. Now it works, custom commands included.

I've been thinking about what the next stage of working with AI should look like.

Most of what I see focuses on making AI do more work. It writes code, generates designs, analyzes data, and automates workflows. Humans provide instructions, review the output, and decide what happens next.

But I think there's a more interesting problem to solve.

How can I combine human and AI intelligence to achieve better outcomes than either could achieve alone?