nowfound

Alternatives

Products that do what A portfolio that re-architects its React DOM based on LLM intent does

Hi HN, Added a raw 45-second demo showing the DOM re-architecture in real-time: https:&#x2F;&#x2F;streamable.com&#x2F;vw133i I got tired of the "Context Problem" with static portfolios—Recruiters want a resume, Founders want a pitch deck, and Engineers want to see architecture. Instead of building three sites, I hooked up my React frontend to Llama-3 (via Groq for <100ms latency). It analyzes natural language intent from the search bar and physically re-architects the Component Tree to prioritize the most relevant modules using Framer Motion. The hardest part was stabilizing the Cumulative…

  1. 1AJ

    with affinity you can make multiple apps (components eventually) and store (ala redux) - while a store can be shared through apps. This started as a case study and as a small reusable code for creating self contained dom elements with functionality - during the time of development, ideas and inspiration came from angular, react and vuejs. suggestions and feedback is mostly welcomed. The interesting challenges were finding ways for these topics: 1. create a component lib using dom and js only, without any 3rd party . 2. producing semantic html in dom . 3. allow template micro syntax (using…

    2018

  2. 2
    Reapp89

    A new way to build hybrid apps with React, Webpack, and JS.

    2015

  3. 3RA

    I wanted to have a framework that would let me build web apps faster than ever before. I didn’t care if it was a little hacky or didn’t use best practices — I wanted to be able to get a multi-user application out the door in hours instead of months. I researched the CMS space for months before deciding to build something from scratch. My goal was to be 90% done building a web app once I had the static HTML and CSS finished. I’m not a big fan of building out API endpoints over and over again for every new app, fiddling with a database, or doing lots of config. What I ended up with was a…

    2020

  4. 4NR
  5. 5IM

    Hi HN! Solo developer here. 10 days ago, I started building this after spending countless hours copying&#x2F;pasting marketing sections and fighting to keep them consistent with our design system. I wondered: "What if AI could understand our design system and generate React components that actually match it?" Current progress (10 days in): - Can generate hero sections that follow your design tokens - Uses your actual component variants and styles - Works with Next.js, Tailwind, shadcn&#x2F;ui It's very early days, but I'm excited to share it with other devs who: - Are tired of rebuilding…

    2024 · robustlaunch.com

  6. 6RJ

    I've been working in the couple of months on an experiment, trying to make GPT-4 much more useful for web development &#x2F; React, writing production code that is relevant to any repository without copy pasta from ChatGPT or having small snippets of auto-complete from Copilot that are not in your context. The agent is taking a user story text and generating and composing multiple react components to generate the relevant screens, based on atomic design principles, with Typescript, TailwindCSS and RadixUI. Is is still experimental but very interesting results, I would like to get your…

    2023 · github.com

  7. 7IB

    Hey everyone! Some time ago I was analyzing why React apps are so hard to optimize, and came to a conclusion that the lack of atomic updates is the culprit. I made an experimental library which basically updates everything in place directly in HTML. At some point I became aware that Solidjs exists, which is a very similar idea, but at the end of the day I realized my approach to API is quite different and warrants the existence of my library (my state primitive allows selector subscriptions, array iterators return a state primitive with the element, allowing to never re-render the whole…

    2024 · github.com

  8. 8EL

    Hey HN! I built Experiment to solve a common frustration in LLM development: the lack of proper tools for prompt engineering experimentation. Here's what makes it different: Key Features: - Load and edit chat completion logs from CSV files - Fork and modify specific conversation entries - Run inference via Anthropic, Mistral, and OpenAI - Define custom tools using JSONSchema format - Visual tool usage analysis with collapsible, sorted key-value pairs - Full mobile support and available as installable PWA Technical Highlights: - Built with React using custom isomorphic architecture -…

    2025 · github.com

  9. 9IH

    Hello HN, I had some christmas free time over the last two weeks (Merry Christmas btw ;-)) and used that time to completely recreate the website of my app[1]. I used all the fancy new tools. I didn't know some of them when I started. What was my goal? * Pretty website * Blazing fast * Mobile first * SSR * Webp support * Generally all the best website practices (high lighthouse score) What did I use? * Tailwindcss (https:&#x2F;&#x2F;tailwindcss.com&#x2F;) * Tailwind Components (https:&#x2F;&#x2F;tailwindui.com&#x2F;) * React (https:&#x2F;&#x2F;reactjs.org&#x2F;) * ViteJs…

    2021

  10. 10PR

    Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch&#x2F;transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!

    Dec 2025 · github.com

  11. 11CT
  12. 12IR

    Hey HN, A few years ago, when I was working as a freelance web developer, there were many projects that used repetitive layouts and designs That's when I built my own collection of basic UI components like buttons and all. At that time, I was using CSS, so I styled my components using CSS. Later, I decided to open-source these components, and that’s when I created HextaUI After a few months, I found out about Tailwind CSS, so I decided to recreate all components with better design, modularity, and accessibility. This time, I also added animated components, not just base components. After…

    2025 · hextaui.com

  13. 13NJ

    Hey, I'm absolutely thrilled to introduce my meticulously crafted Next.js Boilerplate, a project I've maintained for over 2 years. Recently, this project has achieved a huge milestone, over 4500+ stars on GitHub! Initially, I've build the boilerplate for my own use case. A template that allows me to kickstart a new React project with all the necessary tooling. The idea is to setup once and then reuse the template for all my future web projects, eliminating the need to start from scratch each time. This approach tremendously saves time, sparing me from repeatedly configuring and integrating…

    2023

  14. 14AD

    Hi everyone, After four years, I'm finally open sourcing my little markup language that compiles directly to HTML, and has all the "modern" features built into the core, (reactive components, server side rendering, modules, bundling, etc.). No metaframework required! Feels like I really have something here, I'd love your feedback :)

    2023 · a-dom.io

  15. 15AS

    I built this to help developers create UI faster. Just search for a component, make quick visual edits, then export the code.

    2022 · aspect.app

  16. 16RS
  17. 17ET

    We built a browser extension (Chrome + Firefox) that captures the runtime DOM and exports it as JSON. Not the pre-render source (HTML&#x2F;CSS&#x2F;JS, templates, bundles) and not a screenshot — but the live, post-render state the browser is actually displaying: - visibility&#x2F;hidden, disabled&#x2F;required - current input values and validation&#x2F;validationMessage - dataset attributes - trimmed text - stable selector paths Why: LLMs often miss or guess UI state. Screenshots are too opaque, pre-render source is too noisy. A structured snapshot gives reproducible context for debugging…

    2025

  18. 18CA

    I wrote a small "game" to showcase concurrent agents (via a library) working in a React app. It demonstrates how a React program can be written with DOD-inspired pattern to make it easy to reason about, straightforward in re-render instruction semantic. Thus as the side effect the program is performant. You're invited to view the source to examine the neat design pattern underneath as well as the agent management library that powers the app. Caveat: it doesn't work well in mobile yet, so switch to desktop site mode.

    2023 · codesandbox.io

  19. 19DT
  20. 20RM
  21. 21RD
  22. 22AA

    As an indie hacker, I used to spend hours creating landing pages for my side projects and SaaS. So, in the past few months, I built Webifier.io. It converts prompts into full blown landing pages that are customized for you. This includes: animations, custom sections, etc. You can then export a clean React&#x2F;Next project. Can’t wait to hear what you think!

    2024 · webifier.io

  23. 23AH

    Hi! My name is David and I wanted to show you a react (and solidjs) library I've built over the last months. The intention behind it is, that there are some actually useful use cases for AI on the frontend that are largely unexploited still. LLMs are particularly good at extracting structured information from unstructured text and thats really useful for any types of forms - which can be multimodal. Setting up server side logic for AI usage can take time. Streaming data to the frontend and parsing it there to make it usable can be frustrating. Imho thats one of the reasons why people…

    2025 · ai-hooks.dev

  24. 24IM

    Frustrated by AI assistants that can only suggest actions but never take them, I built Merlio (https:&#x2F;&#x2F;merlio.app) - an AI that generates charts, searches the web, creates images, and analyzes YouTube videos directly within conversations. Built with React, it functions as an AI hub providing access to multiple models (Claude, GPT, Gemini) through a unified interface. The custom LLM orchestration layer enables the AI to execute tools with proper parameters and process results while maintaining conversation flow. Users are visualizing data, generating designs, and summarizing…

    2025 · merlio.app

Ranked by how close each launch is in meaning, then by votes. Refine with a description →