Rebuilding the CogniFocus Experience Before Launch

Currently doing a massive polish/rework pass across the entire app before launch on June 1.

We ve been moving away from static screens, dead UI and generic productivity flows towards living scenes, reactive motion, behavioral atmosphere, and emotionally aware interactions.

Over the last days we redesigned:
onboarding flow architecture
focus interruption moments
companion reveal pacing
Shield activation flows
app blocking setup
CTA motion systems
atmospheric transitions
reactive UI behavior
motion hierarchy across screens

Hi Product Hunt!

I m building Gold Dashboard at TR-MATE Global, a research-first interface for exploring XAUUSD price data, multi-timeframe charts, gold news, observed support and resistance levels, and market context.

Hey PH!

I'm an independent developer and software engineer from China. I spend most of my time working with Python, APIs, and trying to turn messy problems into clean solutions.

I built three Chrome extensions in my spare time each one born from a real need I ran into during work or daily life. Thought I'd share them here. Hope they're useful to some of you too.

1. Virtual Camera - Video Replacement

I kept giving up on expense tracking apps. Too many taps, too many screens just to log a coffee. So I built VoiceOnlyLedger - you long-press the mic, say something like "coffee 5 dollars", release, and it's done. Auto-categorized into Food, Transport, Shopping, etc. What makes it different: - All processing happens on-device. No cloud, no accounts, zero data collection - Optional iCloud sync across your Apple devices - $0.99 one-time purchase. No subscriptions, no ads - Tiny 1.2 MB app size It's on the App Store for iPhone, iPad, and Mac. Would love to hear what you think - especially what features would make you actually stick with expense tracking long-term.

I built idemkit after cleaning up duplicate charges one too many times.

The version everyone writes checks whether a key has been seen and replays the stored response. Two requests a millisecond apart both find nothing and both charge the card. And if the worker dies between charging and recording it, the retry charges again. Neither reproduces locally.

idemkit does it properly: an atomic claim instead of check-then-act, a lease that expires on the storage server's clock, and a fencing token so a stalled worker can't overwrite a good result.

We built DocDot and are getting close to launch. I m posting because I still want a round of honest product feedback before we put it in front of more people.

DocDot is a local PDF parsing workflow for macOS. You can install multiple parsers with one simple command: curl -fsSL https://docdot.ai/install.sh | bash, compare outputs side-by-side with our web UI, switch parsers them depending on the file, and plug directly into agents. Right now we support NanoDoc (our in-house parser), PaddleOCR, GLM-OCR, LiteParse, and MinerU.

What I m still trying to get right is the product feel on first use. When someone opens a tool like this, what matters most, and where do you need more guidance?

If you work with PDFs a lot, where do tools in this category usually start to get annoying?

I keep a daily probe that asks the assistants the buying questions in my category and records every source behind every answer. Last week I pointed it at Google's two AI surfaces, the AI Overview box and the fuller AI Mode, and counted.

Thirteen answers. 168 citations. Every single answer used a different domain for each of its sources. Not one domain was cited twice, in any answer, the whole week. Thirteen of thirteen, no repeats.

That stopped me, because it is the opposite of how a normal search results page behaves. On the ten blue links, one strong site often takes three or four of the top spots. A page that ranks well ranks well repeatedly. Here, ranking well once seemed to use up the domain for that answer.

Why an AI answer looks like this
An assistant does not hand you a ranked list. It breaks your question into several smaller ones, runs those, and assembles an answer from the best source it found for each. Google's own patent on query variants (US11663201B2) describes dynamic control that "can often lead to a relatively large (e.g., more than 5, more than 10, or more than 15) quantity of variants."

I m an indie developer too. AI helps me code, debug, research, and turn ideas into products but the token bills often grow long before a project earns anything.

I ve seen individual developers turn small side projects into real businesses and achieve things that once seemed impossible. I built Mustham API because I don t want promising ideas to be abandoned simply because using AI became too expensive.

Mustham API provides access to GPT, Claude, Gemini, and Grok through one platform. By combining capacity from different accounts and routes, many routes are priced at less than half of the corresponding official API price, while users can still choose the specific model and route they want.

I have already invested a significant amount in capacity and stability testing, and the platform is still costing me more than it earns. We also provide direct support if you encounter stability, integration, or usage problems, we will help investigate them as quickly as possible.

Candor is my free, MIT-licensed Claude Code plugin: twelve work-mode "personas" that make an AI assistant direct, verification-driven, and honest instead of agreeable. A debugging persona that demands a reproduction before guessing. A data persona that reads numbers skeptically. A decision persona willing to say no. Each one is documented, benchmarked with eval scripts, and installable in minutes.
I built it because of what I learned running AI workflows on a real business (my mom's Shopify boutique, the Krafty Bandit project below): the failure mode of AI at work is not wrong answers, it is confident agreement. The workflows that shipped 2,861 catalog fixes in one weekend only worked because every call got checked by a human, and Candor bakes that discipline into the assistant itself. The repo includes twelve skill definitions, evals with published benchmark results, full documentation, and contribution guidelines.
It is labeled experimental (v0.5.x) and actively maintained. Free forever. It is also the companion tool for my YouTube channel, where I show the personas doing real work on a live store. github.com/itsryanlenk/candor
See more at my website https://www.ryanlenk.com where I log my whole journey giving the inside and sometimes not so glamorous stats behind SEO.
Try them out and let me know what you think!

Hey everyone,

As backend developers, we ve long been frustrated with managing dozens of different third-party APIs. Separate API keys, inconsistent response formats, scattered billing systems, and repeated integration work waste tons of development time.

To solve this pain point, we built AsRouter, a one-stop API aggregation gateway.

Access multiple third-party services with just one API key