Fivefold Type is a personality web app inspired by the ancient eastern philosophy such as the five natural elements, zodiac and "Yin Yang". It bridges ancient philosophy with modern personality psychology.
The goal is to create an MBTI-like identity experience, instead of answering a set of questions, Fivefold type only needs your birthday/birth time(only for type calculation, won't save your personal info). You will have your type code and a visual persona. After having the result, you can check your daily energy vibe based on the date and your current location. I'm still early and trying to learn: Would people understand the result?
Whether the daily reflection feels useful enough to revisit?
Do these Eastern calendar concepts feel confusing?
Out of 1.3m+ members here, sitting at #80 right now. sounds small to a lot of you probably? But honestly i'm just enjoying the ride, whether it ends at #1 or #100 doesn't change how real this feels.
I'm new here, still figuring out how launches actually work on this platform, so if i'm missing something obvious that's probably why.
If you have a minute, check out banalo.business and tell me what you think. genuinely want the feedback, good or bad. would mean a lot .
The fashion industry has a $550B returns problem. I'm trying to kill it.
I'm Markus, based in Sweden and obsessed with making online shopping smarter. It started with not knowing what colors suited my tone so i created a tool for color analysis... then it evolved in to something much much bigger.
I built FlickClaw because I was spending hours configuring the same AI agents over and over for different tools. Every time I switched between Claude Code, Cursor, Codex, or my local Ollama setup, I'd rewrite the same agent rules from scratch. FlickClaw solves this with pre-packaged agent configs: 150 specialist agents each with identity, operating rules, workflow instructions, quality gates, and output contracts Native exports Claude Code, Cursor, Codex, Aider, Ollama, OpenClaw, Windsurf, Hermes No lock-in bring your own API key (OpenAI, Anthropic) or use local models. We don't sell tokens. We don't host your AI. Free plan with ads, Pro without transparent pricing, no hidden fees This is a solo build. I ship it myself from a Linux VPS, audit every release, and keep the catalog honest. No "coming soon" badges on things that don't exist yet. Happy to answer questions about the agent model, export pipeline, or anything else. Feedback very welcome!
I ve created a creative tool that resizes any banner to all the sizes needed to run online campaigns.
I m looking for businesses and designers who want to try it out and give me feedback. At the moment, there isn t a free trial available, but I ll select a few people from here who are interested and offer them free access.
I made a short video showing how easy is to resize a banner
No subscriptions, no paywalls. one cap, ai chatbot at 15 requests/day. rest is open.
Anyone who paid before today keeps it forever, unlimited ai chats, lifetime. wasn't going to let early trust turn into a downgrade.
Got our first angel investor on board recently, so there's actual runway to spend right now. Rs499 from a handful of people teaches me less than hundreds of people actually using this and telling me what's wrong. easy trade. Go poke around, break something, tell me what sucks.
We're a team of builders. Years ago, we co-founded a dev shop that became the core contractor for a major US company. We built their platform backbone. That company grew to 50,000+ contractors, valuation went 20x, crossed a billion dollars.
Hey everyone I'm Alex, and I'm about to launch Unstuck here on Product Hunt. It's a desktop AI co-pilot that watches your screen and helps you get past exactly these moments: boss fights, puzzles, builds, "where do I even go now."
But before I do, I'm genuinely curious about yours. What's the game wall that nearly broke you? The boss you threw your controller over, the puzzle you Googled at 2am, the build you respec'd five times?
We build a PDF toolkit that runs entirely client side. There is no upload endpoint on the domain, so documents are never transmitted. That constraint is the whole product.
Two months ago we added on-device AI: summarize a PDF, ask it questions, translate it. The setup:
- A 1.5B parameter model running in the browser through WebGPU
- Executes on the user's own GPU, inside a sandboxed worker
I kept watching people hit creative tools and get asked for an email before they had made anything. So I changed Picorn's editor: it now opens straight into the canvas. You can design an image or carousel and export PNG, JPG, SVG, or PDF without an account or watermark.
The signup line is later: saving a project and using the server-side AI tools.
