web - Moozonian Search

github.com• Apr 7, 2026• 1 min read

Show HN: Frontend-VisualQA — give coding agents eyes to verify their own UI workCoding agents today are blind.They write “valid” HTML/CSS code but can still ship a broken layout, a clipped dropdown, or a page at the wrong URL. Playwright scripts can assert modal.isVisible() without knowing the modal is rendered off-screen.Essentially, coding agents need “eyes” to verify their own UI work.frontend-visualqa is a CLI + MCP server for Claude Code and Codex for visual testing, verification, and QA of a website.You give it a URL and natural-language claims: frontend-visualqa verify http://localhost:8000/dashboard.html \ --claims \ 'The API status indicator shows Active' \ 'The monthly quota progress bar is completely filled' # → first claim passes, second fails (label says 100% but bar is ~65% full) It catches visualDOM disagreements that selectors are blind to.You can also test interactive flows without hardcoded data: frontend-visualqa verify 'http://localhost:8000/booking_form.html' \ --claims 'The date on the confirmation page matches the date selected on the calend

github.com• Apr 7, 2026• 1 min read

Show HN: Testreel – Programmatic product demo videos from JSON and PlaywrightI made Testreel as a programmatic alternative to ScreenStudio.This has two primary value props: 1. Not having to manual re-record a demo because of a typo or misclick; just update the config and regenerate 2. Allows LLM agents to generate demo videos for your web app, complete with cursor overlay, and a customizable desktop backgroundTestreel is an npm package that lets you describe interactions (click, type, scroll, zoom etc.) in JSON, YAML or Playwright. Then generate a polished webm/mp4/gif video with cursor overlay, click ripples, gradient background etc.Made with Claude Code. Built on Playwright + FFMPEG. MIT License.Repo: https://github.com/greentfrapp/testreel

onboardly-ruddy.vercel.app• Apr 7, 2026• 1 min read

Show HN: Onboardly – Ask questions about any GitHub codebase in plain EnglishA few months ago, I asked HN about the biggest pain points when joining a new team (https://news.ycombinator.com/item?id=47368472). Most people said it was the tribal knowledge buried in the code.I've spent my time as a student building Onboardly to solve this. It’s a web app that indexes your GitHub repo and lets you ask questions in plain English. Unlike a general LLM, it cites the exact files it’s looking at so you can verify the logic.Tech stack: FastAPI backend, Next.js frontend, and a RAG architecture for the indexing. I’m currently hosting it on Render's free tier, so there might be a slight delay on the first login—I'm working on that!I’d love for you guys to break it and tell me where the answers feel 'off' or what features a dev actually needs for onboarding.It's free to try — would love feedback on answer quality across different repo types and languages.https://onboardly-ruddy.vercel.app

alternatelife.xyz• Apr 6, 2026• 1 min read

Show HN: I built a site that turns your Steam gaming hours into a RL skill treeHey,A bit of context..So I think last week was my last straw, I hit 8k hours with dota and holy ** It finally hit me how much time I wasted on that game.I'm a software developer, I always wanted to develop something and put it out but was scared shitless to do so, I was kinda afraid to get bad traction, to fail or even worse to be completely ignored.so I decided to address two of these issues at once, stop playing dota and spend the weekend building a website that let you see what you could've done with your gaming hours.As an avid gamer for the last 20+ years, I know that it's only theoretical, cause sometimes, after a long day u just wanna chill infront of a game and you wouldn't go get a pilot license, obviously.but, a lot of other times, I would spend my days off, weekend, just gaming 10 hours straight like a mad man.In any case, hope u like it and maybe it sparks something in u!

news.ycombinator.com• Apr 6, 2026• 1 min read

Zooming UIs in 2026: Prezi, impress.js, and why I built something differentThere are essentially two established ways to use zooming in web interfaces today. They serve different purposes and make different tradeoffs. I built a third one, so I'll try to be fair about what each does well and where it falls short.* Prezi Prezi pioneered the zooming canvas for presentations and remains the market leader in that space. It recently added AI-powered generation and text editing tools. It's a polished product with real traction.But Prezi is a closed platform, not a library. You can't use its zoom engine in your own app. Pricing starts at $15/month for meaningful features, and exporting to PowerPoint flattens all zoom effects into static slides. A recurring complaint from users is that the zooming and panning transitions cause motion sickness. And fundamentally, Prezi uses zoom as a storytelling device between pre-arranged frames. It's not a navigation model. It's a presentation model.* impress.js impress.js brought Prezi-like zooming to the open web. It's a presentat

reversecam.com• Apr 6, 2026• 1 min read

Show HN: ReverseCam – See yourself as others see youThe front camera apps always show the mirror preview. Most of us hate photos others take of us, but love our selfies. It's because we groom ourselves and find our perfect angles using the mirror preview. So it's jarring when we see the photos of us taken by others. I always wanted a camera app that showed the non-mirror preview. Surprisingly most camera apps don't have this option. So I created this app to scratch my own itch:)Note: Photos and videos are only stored in the browser. No data is sent to any servers. You can also install this as an app from your browser since it's a progressive web app.

predictionhunt.com• Apr 6, 2026• 1 min read

Show HN: Prediction Hunt API – A unified layer for Polymarket, Kalshi, and moreI’m launching the Prediction Hunt API because I got tired of managing five different WebSocket connections and manually mapping event IDs across fragmented markets. It’s designed to be a unified infra layer for prediction markets, solving the "event matching" problem so you don't have to guess if a Polymarket contract and a Kalshi trade represent the same real-world outcome.Here’s our feature offering:-Real-Time Data with Event Matching: We make it trivial for you to pull real-time prices from 5 different prediction markets (and counting)-Live Orderbook Proxy: We’ve wrapped our internal fetchers into a unified orderbook endpoint. It proxies the full bid/ask ladder in real-time from the source platforms.We offer a generous free API tier (no expiration date) so you can see how much easier it is to query prediction markets with a single, unified API.I’m aiming for this to be the best, most robust prediction market unified API out there - an alternative to Dome (now that it's been acquired

github.com• Apr 5, 2026• 1 min read

Show HN: Pure Go mosh client, server, and WASM build for the browserGo implementation of mosh (mobile shell) both client and server and wire-compatible with the core C implementation.The full mosh protocol is implemented including but not limited to AES-128-OCB3, SSP transport with sequencing and retransmission, datagram fragmentation, protobuf state sync, local echo prediction, etc.It compiles to WASM, which is how we run mosh in the browser at UnixShells.com (WebTransport (HTTP/3) carries the datagrams instead of UDP). This is how things feel instant, despite being wherever you are.https://github.com/unixshells/mosh-go

news.ycombinator.com• Apr 4, 2026• 1 min read

it's not Ai if the LLM is not in controlI always thought that the frontend of "Ai" is awful, but now I know it for sure:OAI5.1+ is good, but chatgpt sucks, it doesn't have gmail integration and barely able to do anything but basic retrieval from the integrations it actually has.Opus is amazing, but claude web is mediocre at best. It has a very limited set of integrations even after 2 years, some don't even work (clay), and it uses way too many tokens to do basic stuff.XAi is ok for social queries but grok is very bad. Its memory is basic, and the grok teams takes ship features 18 months later.in 2024, i thought the problem is that all of this is new. "they just need a little more time" I told myself, but the truth is that the scaffolding is truly rubbish. Other the claude (which is barely good), these products are not what we were promised in this cycle. If we allowed any Ai, even the most basic models to build the frontend for chatgpt or grok, it would have done a better job! At the very least it would have shipped more fea

news.ycombinator.com• Apr 4, 2026• 1 min read

Tell HN: YouTube history setting privacy implicationsAs user viewer (not channel owner) I have setup YouTube history to be only for max 3 months. Then auto-delete. Today I checked that this setting applies only to users' Video Watch History.One has to manually go https://myactivity.google.com/page?page=youtube_comment_likes to delete Your Likes and Dislikes on YouTube anddelete comments at https://myactivity.google.com/page?hl=en&utm_medium=web&utm_source=youtube&page=youtube_comments for deleting Youtube Comments.

reviewskits.com• Apr 2, 2026• 1 min read

Show HN: Reviewskits – Open-source, headless, and self-hostable social proofHi HN,I built Reviewskits because of a recurring frustration I faced while working for a web agency in Switzerland.Our designers created beautiful, pixel-perfect layouts, but when it came to testimonials, we were stuck with rigid, pre-made widgets from tools like Senja or Trustpilot. Hacking them with CSS to match our UI was a nightmare. When we looked at their API pricing to build our own components for 100+ clients, the cost was astronomical ($90 to $300+/mo).Later, as an indie dev building my own SaaS, I simply couldn’t afford those prices.So I built Reviewskits: High Performance: The API is built with Bun and Hono for ultra-low latency. Self-Hostable: You own your data. Period. No more black boxes. Headless first: We provide the API and SDK. You build the UI that matches your design perfectly. Open-Core: The core engine is open-source. I’m looking for two things today: Contributors: I want to turn this into a web standard for social proof. If you're into Bun, Hono, or React, I'd lo

news.ycombinator.com• Apr 2, 2026• 1 min read

Google banned our mobile AI agent app for doing what Gemini should do,but doesntHi HN,My brother and I built Sova AI (https://ayconic.io/sova), an Android agent that actually controls your installed apps.We were incredibly frustrated with the current state of mobile AI. Built-in assistants like Gemini are deeply integrated into the OS, yet if you ask them to "Order an Uber to the airport" or "Send a Telegram message to friends group I'm late", they mostly just give you web search results or a button to open the app yourself. They don't do the work. (The Perplexity "assistant" is just a browser agent :/ )So, we built an agent that does operate your phone. (NO root, NO adb, NO PC, NO appium/whatever, NO usb, NO browser)How it works: You give Sova a prompt - either voice or text, you can make it a default assistant if you like. Instead of relying on non-existent official app APIs, Sova acts as a virtual human - clicks, scrolls, types etc. It uses the Android Accessibility API to read the screen's UI node tree. About AI models - currently we support main AI cloud prov

news.ycombinator.com• Apr 2, 2026• 1 min read

Ask HN: How are you choosing the model when using pi.dev?I've been using pi.dev for a while, and I find myself choosing the models based on anecdata.I would love to be a bit better at it, and I did try a few of these 'battle of models' websites, but couldn't find much.I'm interested on knowing your experience when selecting a model for different parts of your agentic SDLC.Thus far, I'm using + sonnet for code reviews. + haiku for code searches/analysis. + flash 3.5 when LLM as judge is required + Opus to generate content. + K2.5 seldomly as alpha testing (right now for unti test generation is ok)Ideas?

computerpoker.ai• Apr 1, 2026• 1 min read

Show HN: ComputerPoker.ai – Learn GTO tournament poker strategy vs. GTO botsComputerPoker.ai is a website where users can play simulated poker tournaments against GTO Bots to learn GTO poker strategy in a fun and low-risk environment.My motivation for creating CompterPoker.ai was feeling a bit overwhelmed by some of the professional poker tools out there for learning GTO play. For some tools, learning how to simply operate the tool itself felt like a second job. With ComputerPoker.ai players can play against bots themselves simulating GTO play to learn what it "feels like" to play GTO vs. GTO opponents without having to turn any knobs or dials (feedback is real-time as you play).The Beta tester code for HN Users is: HackerNews2026. All feedback is welcome! Please send suggestions for improvement or bugs to contact@computerpoker.ai or alternatively leave a comment below. Any questions I will do my best to answer.As for the product offering the website is designed to teach players how to play optimal poker strategy (GTO) in simulated Texas Hold 'Em poker tournam

thedream.work• Apr 1, 2026• 1 min read

Show HN: A platform to help you find the best tech jobsHey everyone,Long time lurker finally took the leap to share something with the community.From a long time I wanted to build something and I had this idea about a job board but not just a simple aggregator or just a job board. Basically I don't like any of the existing websites for jobs and most of the job boards are just aggregators that you constantly get redirected to third party links not the best experience. I also don't have the best experience with recruiters been ghosted, conversation looping in meaningless question and so on.And the current job market is kind of disheartening non existing entry level jobs pretty brutal stuff.The idea of the platform is to an extent to be fully autonomous in terms of you as user not browsing jobs but you automatically get matched with opportunities. Also companies looking for talent will have the same ability to view the people who are best matches. One of the main aspects is to basically to get a really good starter conversation between the co

interfaze.ai• Apr 1, 2026• 1 min read

Show HN: A new model architecture because transformers are not enoughMost AI products are built around the same idea.Take a giant model. Add a prompt and hope it does the whole job. The AI equivalent of spray-n-pray.That works great for chatbots for creative outputs like code generation, website design and email writing. BUT, It breaks down fast for developer work that requires highly deterministic output. Think of OCR for KYC at banks or Audio recognition for patient-doctor notes.We have been training SLMs for specific tasks for a while now. During which we kept seeing the same pattern. A SOTA language model with great benchmarks, failing on the parts that actually matter: reading a dense PDF like Form-1040, pulling clean data from a highly protected website, transcribing a long call with speakers in seconds, or returning output in a format code can trust.So we spent a year researching how we can solve determinism. As many of us thought, more data was the solution. But not really… While data is part of the problem, re-thinking the architecture is the k

0xdead.space• Apr 1, 2026• 1 min read

Show HN: 0XDEAD.space: A cryptographic succession protocol for the AT Protocol> "On the Revocation of Meatspace Certificates"As devs get older, and we see more of our fellow maintainers sadly pass away, I can't help but think of the mess those types of events typically leave in their wake. Not only are they sad, tragic events, but they have real world consequences for the work and projects they leave behind.I started brainstorming with Claude and other chatbots (as is the fashion) on this and hit upon the idea that the AT Protocol pretty much already solves this ... it just doesn't know it yet (or, maybe they do and this is all a moot point): `did:plc` supports key rotation with a 72-hour override (https://web.plc.directory/spec/v0.1/did-plc). That's how PDS migration works. Succession is the same primitive: rotate the keys to a new person instead of a new server.0xDEAD.space is my attempt to build that. Two custom lexicons. Blinded heartbeats from entities like your lawyer, your family, your services, strangers you "street-pass" with ... all quietly offering va

supertommy.com• Apr 1, 2026• 1 min read

Show HN: I made a Mario Galaxy game with Claude Code and Three.js in 53 daysI'm the developer. Happy to share the process and learnings.Architecture:- Custom SoA ECS for cache-friendly iteration, zero allocations in hot loops. Benchmarked against bitECS/miniplex.- Process manager inspired by Game Code Complete's but data-oriented so processes are pure data, systems contain the logic.- Multi-field gravity with 5 types (point, parallel, segment, cylinder, convex hull) with spring-damped transitions between fields.- Rapier3D WASM with SIMD. Gravity-aware fake shadow system for playability.- WebGL 2 shared context between Three.js and Pixi.js.- Debug editor for placing objects, configuring settings, visualizing colliders, etc (Tweakpane + Three.js helpers)76K lines of TypeScript. 735 commits. Runs on mobile. Plays best with gamepads.The AI Process:Claude Code (Opus) wrote ~95% of the code. I provided architecture, constraints, and direction; looked at some but not much of what it wrote.My process for every feature: braindump what I want, relevant technical details

news.ycombinator.com• Apr 1, 2026• 1 min read

Show HN: I built a full LLM chat client as a Neovim filetypeI started Flemma because I wanted to bring my AI workload into Neovim.My workflow started with me living in developer portals - Claude Workbench, OpenAI Platform, Vertex (the horrors of GCP's Console UI!) I would spend hours in these web UIs crafting prompts, iterating on system instructions, maintaining a carefully curated library of sessions. But the browser really wasn't optimised for this kind of interaction. Editing was clunky (muscle memory would close the tab instead and wipe my work), going back and forth between the LLM and myself felt off. So I had an idea: what if I could turn a Markdown document into an LLM chat interface?At first I thought that would be enough - just do what I was already doing in the browser... but in Neovim. And sure enough having been accustomed to my own setup for the last decade I immediately felt a productivity boost. Writing functional requirement documents, statements of work, deep research across different systems - all of it felt better in "my" e

github.com• Mar 31, 2026• 1 min read

Show HN: Dograh – voice agents that pick Recordings over TTS using LLMTL;DR: Dograh is an open-source platform to build voice AI agents with drag-and-drop workflows. New in v1.20: Gemini 3.1 live support, Pre-recorded audio support for lower latency and more natural responses. Fully self-hostable, no vendor lock-in.Hi HN,We’re the Dograh team (YC alumni). While building voice bots, we found that wiring WebRTC/ Telephony + STT + LLM + TTS took more time than the bots themselves. Teams are spending weeks on plumbing - handling call flows, extracting variables, dealing with telephony edge cases, and redeploying for small changes. Tools like Vapi/Retell are easy to start with but come with lock-in and platform fees. So we built Dograh: a 100% open-source platform that handles the full stack, with a visual workflow builder and self-hosting by default.Dograh v1.20 introduces two major additions: 1. Gemini 3.1 Live support Run fully real-time voice agents using Gemini’s streaming APIs, without stitching together separate STT + LLM + TTS components. 2. Pre-recor