Alternatives
Products that do what Element to LLM – Extension That Turns Runtime DOM into JSON for LLMs does
We built a browser extension (Chrome + Firefox) that captures the runtime DOM and exports it as JSON. Not the pre-render source (HTML/CSS/JS, templates, bundles) and not a screenshot — but the live, post-render state the browser is actually displaying: - visibility/hidden, disabled/required - current input values and validation/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…
- 1CH
2024 · github.com
- 2RL
We've been building data pipelines that scrape websites and extract structured data for a while now. If you've done this, you know the drill: you write CSS selectors, the site changes its layout, everything breaks at 2am, and you spend your morning rewriting parsers. LLMs seemed like the obvious fix — just throw the HTML at GPT and ask for JSON. Except in practice, it's more painful than that: - Raw HTML is full of nav bars, footers, and tracking junk that eats your token budget. A typical product page is 80% noise. - LLMs return malformed JSON more often than you'd expect, especially with…
Mar 2026 · github.com
- 3IM
Hello HN! I'm the creator and solo developer of Extension.js, a development tool for browser extensions with built-in support for TypeScript, WebAssembly, React, and modern JavaScript. Developers use it to spend less time configuring the compilation config or learning new frameworks and more time actually writing code. Most projects similar to Extension.js rely on some sort of abstraction or configuration to get started, making the initial development process slow given the extra learning curve and setup guidelines. By using Extension.js, adding the package to your npm scripts is all it…
2024 · github.com
- 4LL
Hey HN, I just built an experimental VSCode extension called LLM Debugger. It’s a proof-of-concept that lets a large language model take charge of debugging. Instead of only looking at the static code, the LLM also gets to see the live runtime state—actual variable values, function calls, branch decisions, and more. The idea is to give it enough context to help diagnose issues faster and even generate synthetic data from running programs. Here’s what it does: * Active Debugging: It integrates with Node.js debug sessions to gather runtime info (like variable states and stack traces). *…
2025 · github.com
- 5BH
Hey HN, We got tired of browser frameworks restricting the LLM, so we removed the framework and gave the LLM maximum freedom to do whatever it's trained on. We gave the harness the ability to self correct and add new tools if the LLM wants (is pre-trained on) that. Our Browser Use library is tens of thousands of lines of deterministic heuristics wrapping Chrome (CDP websocket). Element extractors, click helpers, target managemenet (SUPER painful), watchdogs (crash handling, file downloads, alerts), cross origin iframes (if you want to click on an element you have to switch the target first,…
Apr 2026 · github.com
- 6IW
Hey HN, I made Browser-Use, an open-source tool that lets (all Langchain supported) LLMs execute tasks directly in the browser just with function calling. It allows you to build agents that interact with web elements using natural language prompts. We created a layer that simplifies website interaction for LLMs by extracting xPaths and interactive elements like buttons and input fields (and other fancy things). This enables you to design custom web automation and scraping functions without manual inspection through DevTools. Hasn't this been done a lot of times? Good question, as a general…
2024 · github.com
- 7
- 8MJ
Hey HN, I'd like to share a fun project I've been working on: mizu.js. It's a js library that add functional attributes support into your html, designed to be a simple and flexible alternative to fully-fledged web frameworks (such as Vue, React, and Angular), while offering more capabilities than other lightweight options (like Alpine.js and htmx). As it's written using modern ES features and due to its isomorphic nature, it can be run in both browsers and runtimes (Node, Deno, Bun) without any changes. This makes it ideal for client-side and server-side rendering, as well as static site…
2024 · mizu.sh
- 9TN
https://github.com/thi-ng/umbrella/blob/master/packages/hdom... Lightweight UI component tree definition syntax, DOM creation and differential updates using only vanilla JS data structures (arrays, iterators, closures, attribute objects or objects with life cycle functions, closures). By default targets the browser's native DOM, but supports other arbitrary target implementations in a branch-local manner, e.g. to define scene graphs for a canvas element as part of the normal UI tree. Benefits: - Use the full expressiveness of ES6 / TypeScript to…
2018
- 10JF
(spoiler: its XSLT) I've been working on a little demo for how to avoid copy-pasting header/footer boilerplate on a simple static webpage. My goal is to approximate the experience of Jekyll/Hugo but eliminate the need for a build step before publishing. This demo shows how to get basic templating features with XSL so you could write a blog post which looks like My Article some content hello hello Some properties which set this approach apart from other methods: - no build step (no need to setup Jekyll on the client or configure Github/Gitlab actions) - works on any webserver…
2025 · github.com
- 11RL
While working with LLMs for structured web data extraction, we saw issues with invalid JSON and broken links in the output. This led me to build a library focused on robust extraction and enrichment: - Clean HTML conversion: transforms HTML into LLM-friendly markdown with an option to extract just the main content - LLM structured output: Uses Gemini 2.5 flash or GPT-4o mini to balance accuracy and cost. Can also also use custom prompt - JSON sanitization: If the LLM structured output fails or doesn't fully match your schema, a sanitization process attempts to recover and fix the data,…
2025 · github.com
- 12OV
2020 · github.com
- 13WE
Browser LLM demo working on JavaScript and WebGPU. WebGPU is already supported in Chrome, Safari, Firefox, iOS (v26) and Android. Demo, similar to ChatGPT https://andreinwald.github.io/browser-llm/ Code https://github.com/andreinwald/browser-llm - No need to use your OPENAI_API_KEY - its local model that runs on your device - No network requests to any API - No need to install any program - No need to download files on your device (model is cached in browser) - Site will ask before downloading large files (llm model) to browser cache - Hosted on Github…
2025 · andreinwald.github.io
- 14AC
2018 · github.com
- 15UG
Hi all, I'm currently working on my hobby project, and one of the fun constraints I put in was to build using as less dependencies as possible. I chose Go as it has a really good standard library, and all went well for building backend. But for frontend, I was wondering whether I should break the constraint and go for React. I tried options like Web Components, but I really didn't like the ergonomics and I didn't want to use jQuery either. Out of curiosity, I was exploring Go's html/template package to see if I can write UIs in a React-like manner. I found most of the online docs using…
2024
- 16
- 17BR
Check out this impressive project that enables running LLMs entirely in the browser using WebGPU. Key features: - Zero token costs, no cloud infrastructure required - Complete data privacy through local processing - Simple 3-line code integration - Built on MLC and Transformer.js The benchmarks show smaller models can effectively handle many common tasks. Currently the project roadmap includes: - No-code AI pipeline builder - Browser-based RAG for document chat - Analytics/logging - Model fine-tuning interface
2025 · github.com
- 18LB
I built this browser extension to solve a daily frustration: copying documentation from websites to feed into AI coding assistants like Cursor, Windsurf, or ChatGPT, only to get a mess of ads, popups, and navigation junk mixed in with the actual content. LLMFeeder uses Mozilla's Readability.js (same tech as Firefox Reader Mode) to extract just the main article content, converts it to clean markdown with Turndown.js, and copies it to your clipboard with a single keyboard shortcut (Alt+Shift+M or ⌥ ⇧ M). No clicking through popups, no selecting around ads, no fighting with modern web clutter.…
2025 · github.com
- 19OA
Thesys just open-sourced their generative UI rendering engine. Interesting timing given where Google a2ui and Vercel's json-render are headed. The difference worth noting: a2ui and json-render both treat JSONL as the contract between the LLM and the renderer. Thesys is betting that's the wrong primitive. Their engine uses a code-like syntax (OpenUI Lang) instead — LLM writes it, renderer executes it. The argument is that LLMs are fundamentally better at generating code than generating structured data, so you get cleaner output and ~67% fewer tokens. The broader vision seems to be a…
Mar 2026 · openui.com
- 20AJ
I've been building a web UI library for a side project of mine. I thought it might be useful to others, so I'm releasing it as open source. To put it simply, I realized that most of my pain points with React come from its declarative model ui=f(state). So I'm trying something that I'm calling "imperative JSX." Instead of treating JSX as the source of truth for your UI, it essentially becomes a query interface for DOM manipulation. I first had the idea for it a few months ago, and only began writing it in earnest last week, so it's extremely early and nowhere near production-ready. Still, I'd…
2024 · npmjs.com
- 21AR
Hey HN, I wanted to share a UI toolkit project I’ve been working on recently, born out of how difficult I found it to build a great UX on top of LLMs, and keep application state in sync. I’ve built: - A React/JS front-end library for conversational interfaces, which makes it super easy to bootstrap AI assistants and ChatGPT style UX: https://github.com/nlkitai/nlux - A set of adapters that simplify integration with AI backends such as LangServe and HuggingFace The library is highly configurable, easy to theme, supports markdown streaming (that was tough to get…
2024 · github.com
- 22AN
When building workflows that rely on LLMs, we commonly use structured output for programmatic use cases like converting an invoice into rows or meeting transcripts into tickets or even complex PDFs into database entries. The model may return the schema you want, but with hallucinated values like `invoice_date` being off by 2 months or the transcript array ordered wrongly. The JSON is valid, but the values are not. Structured output today is a big part of using LLMs, especially when building deterministic workflows. Current structured output benchmarks (e.g., JSONSchemaBench) only validate…
Apr 2026 · interfaze.ai
- 23VC
Hi HN, Simple online tools on the web have become unnecessary greedy. For example, * https://jsonformatter.org/ displays 7 ads on page load * https://convertcase.net/ had 4 ads plus a Google Vignette. And many more sites do the same thing. It's just noisy, which is why I created this VS Code Extension where you don't need to even leave your editor for your small web operations. I also built a Desktop app and an online version, which can be reached or downloaded at smallonlinetools.net. Both of which will be ad-free forever. So far smallonlinetools.net has over…
2024 · marketplace.visualstudio.com
- 24DS
Oct 2025 · substack.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →