Connect with the Product Hunt community

AI can get me to a working app in a day, but "it works on my machine" and "it's safe for real users" are very different things.

The part that worries me is the boring stuff that's easy to miss when the code looks clean and everything runs: API keys sitting in the frontend, auth checks that exist on the page but not on the endpoint, database rules left wide open from the prototype stage, no rate limits on anything. The AI rarely warns you about these unless you ask, and by the time you think to ask, you've already moved on to the next feature.

Right now my pre-launch process is mostly manual and a bit random: I skim through the auth flow, search the repo for hardcoded secrets, and try to break things as a logged-out user. It catches some things, but I never feel fully confident.

I'd love to hear how others handle it:

Hey everyone, Aryan here

A few of you asked for more agents today. Right now Agent Pets works with Claude Code, OpenCode and omp, and Codex, Gemini CLI and Hermes have all come up in the comments.

Which one do you actually use day to day? I'll build the most asked one first.

Over the last year I went from one side project to 7+. Shipping got cheap; keeping an eye on everything didn't. So I built the screen I wanted: every project in one place, sorted by what needs me first.

Today it covers, for every project from one script tag:

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

I'd been putting this off for eight months. Every time I opened the pricing page I closed it again. Last month I finally did it 40% across all plans, grandfathered existing users for 60 days, and sent a plain-text email to 312 customers.

Zero churned. Three replied thanking me. One asked why I hadn't done it sooner.

The email wasn't clever. It was four paragraphs: what's changing, when, why (I was honest support load had tripled), and what stays the same. No "exciting news" language, no discount code to soften it.

I'm posting because I see a lot of "should I raise prices" threads and almost no "here's what actually happened" threads. So: what actually happened, with numbers.

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

Hi, I m Andrei, the maker of SplitHub. We re launching our coding-agent workflow on October 15.

A coding agent can build three versions of a page quickly. Choosing which version actually helps still needs real traffic and a well-defined conversion goal.

SplitHub gives Claude Code, Cursor and Codex skills, CLI and MCP tools to create experiments, manage them, and read the results. React and Next.js SDKs assign variants locally. The SDK is MIT licensed; self-hosting provides raw counts, while SplitHub Cloud adds statistical analysis and verdicts.

Explore the dashboard without signing in: https://app.splithub.io/demo

Hey everyone, Said here, the maker of CrewTower.

On October 1, Claude Code shipped mods. Hooks could already tell an outside app what Claude was doing and answer a permission prompt. They could never talk back. A mod can.

A mod is a small JavaScript or TypeScript file that Claude Code loads into its own process. It gets called on every event (a tool call, a prompt, a turn ending, part of the screen being drawn) and can watch it, rewrite it, or take it over. It can draw panes and buttons, add slash commands, read context numbers directly, and reach outside Claude Code.

That last part is what I needed. CrewTower lives in the MacBook notch and shows every agent session you run. With a small mod, each Claude card in the notch can now talk to its session:

I m Abbas, the founder of Palance. We build portfolio analytics for people who want to know why a portfolio did what it did, not just what it s worth today. Attribution, sensitivities, simulation, and an AI assistant for when you d rather ask than click.

I m curious how people actually use this stuff. When your portfolio jumps or drops, what do you reach for first? A breakdown of what drove it, a stress test, or a quick look and a deep breath? And what s the question you wish your portfolio tool could answer but can t? The weirder the better. Some of our best ideas started as this is probably too niche and turned out to be what everyone wanted.

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.

I keep seeing people draw parallels between Obsidian and Make0 Brain. And honestly, I get why.

Both store context. Both can connect to AI agents. Both can help AI work with information you've accumulated over time.

But there's a fundamental difference in how they approach memory.

Open the terminal where your agent is running. Do it now, before you read the rest.

Is something sitting there waiting for you? How long has it been there?

Hey Product Hunt

We ve launched Noodle Seed here twice this year, and I wanted to thank this community and everyone who has tried the product and shared feedback with us. You ve helped shape what we re building next.

Across those launches, we learned two lessons. Our first product was easy to get started with, but left too little room for different business needs. Our second gave engineers more flexibility, but getting started still required technical work that many businesses couldn t take on.

Your feedback has helped us focus our roadmap on bringing those qualities together: making Noodle Seed approachable for a business owner / founder, with enough flexibility to adapt as their needs grow.

I recently designed and vibe coded my portfolio. It has an animated intro, project pages, and a guestbook built with React and Firebase.
The site works, but it loads on my laptop is a low bar. If you ve shipped a vibe-coded website, what did you catch in your final review that you missed while building?
I m deciding how to review mine and would rather learn from real mistakes than follow a huge generic checklist.

I've used ChatGPT and other AI tools while building my startup, and they've made it possible to take on work that would normally require a much larger team. Research, technical problem-solving, planning, and exploring new ideas can happen much faster. But one thing I've learned is that completing more work doesn't necessarily mean the business is moving forward at the same speed. You can build faster, solve technical problems faster, and make improvements faster, while the harder questions about customers, adoption, and business growth still take time to answer. It's changed how I think about productivity as a founder. I'm learning to distinguish between how much work gets completed and whether that work is actually moving the business forward.

For founders building with AI, what's one lesson you've learned about the difference between moving faster and making real business progress?

A. "Gorgeous little spot in Silver Lake. Great pastries, lovely place to sit"

B. "Order the 12oz, not the 16oz. Pistachio milk and no sweetener. Go before 9am or you won't get a seat."

Which one actually makes you go? And what is it about a recommendation in general that makes you trust it?

Hey Product Hunt!
I m Oskar, the creator of TravelerMap.
I started building it a few years ago with my brother Kacper. He helped bring the original version to life, but eventually had to focus on his other project, Veloplanner. TravelerMap then sat untouched for quite a while.
Now I m back with my business partner Lukas, and we re working on it every day.
TravelerMap is a 100% free interactive map for discovering national parks worldwide, plus other parks across the US, Canada, the UK, and Poland.
Right now, we re focusing on the US. We ve added campground and parking locations, and we re improving park descriptions with practical information for visitors.
Our biggest priority is the travel planner. We re working hard to have it ready on launch day, so you can choose parks, discover nearby stops, and save your itinerary. Alongside that, we re adding more locations, developing new features, and gradually expanding functionality worldwide.
I d love to hear what you think. What s missing, what feels confusing, and what would make planning your next park trip easier?
Thanks for checking out TravelerMap!

A few months ago, I started building a terminal app with vibe coding.

I spent a week giving AI instructions, asking it to implement features, fix bugs, and keep going. The codebase grew quickly. There were thousands of lines of code, a UI, and what looked like a working application.

Except the terminal barely worked.

The first Electron version wouldn't even launch properly. I moved to Tauri, tried replacing xterm.js with a custom terminal renderer, and ended up dealing with ANSI parsing, screen buffers, Unicode widths, and Vim rendering bugs.

Curious how other builders handle the everyday S3 stuff: uploading assets, checking what s in a bucket, invalidating CloudFront after a deploy.

For me it was always a mix of the AWS console (slow for small tasks) and the CLI (fast, but I never remember the flags). Most GUI clients I tried felt dated or were closed source, which made me uneasy about handing them AWS credentials.

That frustration is why I built Hoistbay, a free, open-source desktop app that treats S3 like a regular folder and keeps CloudFront one click away. It s live on Product Hunt today if you want to take a look: Hoistbay
But I m genuinely more interested in your workflow. What do you use, and what s the one S3 task that still annoys you?

I maintain Termexo, a local-first Windows workbench for coding agents. This is an AI-assisted update, checked against the release notes.

One design choice in 0.10.14 is to stop treating the user opened the window as the user handled the message. Approval requests, input requests and completed tasks now keep the Windows taskbar reminder active until the corresponding message is acknowledged or cleared.

The same principle applies to setup: an install or update result remains available after closing and reopening Settings. Version, command and log details are available under advanced options. If the available version cannot be queried, the UI offers retry and network settings instead of claiming an update is available.

The setup panel covers Claude Code, Codex CLI, OpenCode, Pi Agent, Grok Build and Antigravity. Pi is new in this release, including native session restore, task execution, status events and local MCP integration. Thanks to wuyh410 for PR #33.

@Supabase. @Langflow. @Nuxt. @Plane. @Mastra.

600,000+ GitHub stars between them, and CodeRabbit reviews it all, for free.

When my programming agent makes an error and I point out the wrong part, the corrections don't just stay in the chat but are stored as files, so the next session doesn't trip over the same thing again. I spent quite a while figuring that out actually.

In this way, I have 100 incident notes which the agent has written, and it also keeps memory notes in the project, with one fact for each file. A one-line index of those notes is loaded each time a session starts. Should the same mistake occur another time, it won't merely be a memory but a hook. That hook runs on every tool call and every reply, whether the agent remembers it or not. At the moment I have 63 hooks.

I ve been asking sales teams this on demo calls lately, and the answers are always unintentionally hilarious.

The pricing breakdown? Trapped in a spreadsheet only one person knows how to read.
The real reason we lost that massive deal last spring? Locked in someone s head.
Objection handling? Buried in a Notion doc that hasn't seen daylight since 2024.
And the best advice for week one? "Just shadow our top rep and take notes."

So new hires spend weeks piecing puzzle context together before they actually feel ready to talk to buyers. And whenever they hit a wall, a senior rep gets pulled in to bail them out.

If you ve ever trained a sales rep (or been the new hire):

Agent capabilities are improving incredibly fast, but there s still a big gap between the agent can do this and I m comfortable letting it do this completely unsupervised.

For me, anything involving production infrastructure, credentials, modifying or deleting data, deployments, or actions with external consequences still feels like it needs some kind of oversight.

Curious where others draw the line. What tasks do you still keep a human in the loop for, and what would need to change for you to trust an agent with them autonomously?