Show HN: European Accessibility Act – Simple CLI Checker https://ift.tt/dfwTWRE

Show HN: European Accessibility Act – Simple CLI Checker https://ift.tt/xLu2AhG May 29, 2025 at 12:35AM

Show HN: Octogen: e-commerce capabilities for agents https://ift.tt/LRw48a5

Show HN: Octogen: e-commerce capabilities for agents Hi HN, We just released a public beta of e-commerce capabilities for AI agents — aimed at developers building shopping agents or personal assistants. It’s early and buggy, but we’d love your feedback. Try a live demo here: https://ift.tt/A65DnU8 --- ## Why we built this We believe the biggest *technical* bottleneck in building consumer e-commerce agents is fragmented product data and inconsistent schemas across online stores. So we created a high-fidelity yet unified interface for *e-commerce catalog + checkout*, regardless of the underlying platform. --- ## What it does We currently offer two core capabilities: ### 1. Unified product catalog (for LLM-style search) - Octogen automatically wrangles any ecommerce site into a common schema — a superset of `schema.org/Product`. - It works across platforms and is available today for hundreds of sites. - You can request new stores — ~95% are processed fully autonomously. - Useful for agents doing RAG-based product search with rich attribute awareness. ### 2. Agentic checkout (closed beta) - Works on *any ecommerce site* using virtual cards (Visa only for now). - Enables agents to complete checkout flows much faster than browser-based "computer agents." - We're working on support for additional vaults/wallets/payment APIs. --- If you’re working on agentic commerce, autonomous checkout, or personal AI shoppers — we’d love your feedback and ideas. More at: https://octogen.ai https://octogen.ai May 29, 2025 at 12:25AM

Show HN: Free mammogram analysis tool combining deep learning and vision LLM https://ift.tt/ZQMDXmW

Show HN: Free mammogram analysis tool combining deep learning and vision LLM I've built Neuralrad Mammo AI, a free research tool that combines deep learning object detection with vision language models to analyze mammograms. The goal is to provide researchers and medical professionals with a secondary analysis tool for investigation purposes. Important Disclaimers: - NOT FDA 510(k) cleared - this is purely for research investigation - Not for clinical diagnosis - results should only be used as a secondary opinion - Completely free - no registration, no payment, no data retention What it does: 1. Upload a mammogram image (JPEG/PNG) 2. AI identifies potential masses and calcifications 3. Vision LLM provides radiologist-style analysis 4. Interactive viewer with zoom/pan capabilities You can try it with any mass / calcification mammo images, e.g. by searching Google: mammogram images mass Key Features: - Detects and classifies masses (benign/malignant) - Identifies calcifications (benign/malignant) - Provides confidence scores and size assessments - Generates detailed analysis using vision LLM - No data storage - images processed and discarded Use Cases: - Medical research and education - Second opinion for researchers - Algorithm comparison studies - Teaching tool for radiology training - Academic research validation The system is designed specifically for research investigation purposes and to complement (never replace) professional medical judgment. I'm hoping this can be useful for the medical AI research community and welcome feedback on the approach. Address: https://ift.tt/XPsud8m https://ift.tt/XPsud8m May 27, 2025 at 08:43PM

Show HN: JSON Commenter, add comments with valid JSON syntax https://ift.tt/Gx9fZ78

Show HN: JSON Commenter, add comments with valid JSON syntax JSON Commenter is a vscode extension that lets you create inline comments in a JSON file while keeping valid syntax. You create a block with a command that places the comment anywhere legal in the JSON. The text is edited inline and supports word wrap, padding, margins, etc. The comment is in a somewhat good-looking box with minimal extra characters. Zero-width unicode chars give keys that only show two quotes. This is a sample comment block... " ":"----------------------", " ":" This is a comment. ", " ":"----------------------", https://ift.tt/plmXN4R May 27, 2025 at 04:03AM

Show HN: Remove AI Job Spam from Indeed and LinkedIn https://ift.tt/Jrzcgot

Show HN: Remove AI Job Spam from Indeed and LinkedIn https://ift.tt/hMAp42O May 27, 2025 at 02:09AM

Show HN: CodeNow – CoderPad over WebRTC and WASM https://ift.tt/xJVTioq

Show HN: CodeNow – CoderPad over WebRTC and WASM I was doing a lot of Leetcode this winter, and got the idea of building something like it that used wasm in the browser rather than having to manage the complexity of executing remote code securely on a server. Once I figured that out, I thought it would be neat to make it collaborative, like Coderpad — that part was a bit tougher, but it mostly works now, using WebRTC. I'm not sure whether other people will think this is cool, but I had fun building it and learning more about wasm + WebRTC. https://ift.tt/wGRrpzv May 27, 2025 at 02:08AM

Show HN: XOff an open source Chrome extension to change X links to Xcancel https://ift.tt/VzT8ifX

Show HN: XOff an open source Chrome extension to change X links to Xcancel Basic, but works afaics. https://ift.tt/QzyDlVo May 27, 2025 at 12:12AM

Show HN : A noise free Hackers News newsletters + catch up page https://ift.tt/xiH5bnt

Show HN : A noise free Hackers News newsletters + catch up page Hey HN, I built HN500 because I wanted a no-fuss way to stay updated on major HN stories — especially after taking time off. It’s a newsletter and a catch-up tool with a few handy features: Set your own point threshold (250/500/750/1000) to get only the most upvoted posts. - Choose daily or weekly email updates. - Each email includes 3 random stories to help surface underrated gems. - The catch-up page lets you filter by points, time range, sort order, and more — great if you’ve been away for a while. It’s free, lightweight, and designed to stay out of your way. Feedback is welcome! https://ift.tt/xX9iI5U May 26, 2025 at 01:47AM

Show HN: Tincture – A Color-Matching Puzzle Game I Vibe-Coded with AI in 4 Hours https://ift.tt/xKL73Cs

Show HN: Tincture – A Color-Matching Puzzle Game I Vibe-Coded with AI in 4 Hours Hi, Eight years ago, I had an idea for a color-matching puzzle game. I taught myself Swift and Xcode, spent months building an MVP… and then abandoned it. Last week, I decided to revisit the concept to see how far AI coding tools have come. So I played around with an assistant, and vibe-coded a playable version in about 4 hours. It’s called Tincture. It’s a calm, minimalist puzzle game. There are no timers, or ads, just a grid of colors and some simple rules that prioritize efficiency and pattern retention. What began as a random thought, turned into something that’s actually pretty satisfying to play. Turns out you can use math (modular arithmetic) to optimize the solution of the basic mechanics, so I added some complexity in later levels. I followed what felt fun and used a free AI-powered IDE to reach an MVP that would've taken me MUCH longer to dust off my Swift version or start from scratch learning JavaScript. I’d love your thoughts: • Is the core mechanic intuitive? • Did it hit a “this is kinda fun” moment? • Is it worth polishing further, or should it stay a weird little side project? Thanks for taking a look! https://ift.tt/ghvTR7U May 26, 2025 at 02:26AM

Show HN: ToDoRoulette https://ift.tt/wWObf78

Show HN: ToDoRoulette This is a super simple tool to help stop procrastinating by randomly choosing a task to work on. This was built with almost no effort using vibe coding. https://ift.tt/omB3zIF May 26, 2025 at 01:52AM

Show HN: Generate SVGs with AI https://ift.tt/dZYmzwc

Show HN: Generate SVGs with AI https://vectorart.ai May 26, 2025 at 12:47AM

Show HN: I built a chill place online to work on your ideas https://ift.tt/qbYIoNH

Show HN: I built a chill place online to work on your ideas I used to watch hundreds of hours of lofi beats on youtube while I was coding, but I got really sick of all the ads. I decided to build a better alternative - It's a configurable space for you to hang out online while you work, with a ton of relaxing music and backgrounds. Its got useful tools built in like a timer to keep track of how long you've been locked in, and a notepad for todos or scribbling down ideas while you work. Honestly this is the first tool I've built that I personally use every day, so I'm hoping some of you out there can get some use out of it too! https://lofizone.com May 25, 2025 at 04:08AM

Show HN: 1min Workouts for People Who Sit All Day https://ift.tt/G9lSxeZ

Show HN: 1min Workouts for People Who Sit All Day I am a software developer and in the last few months after recently becoming a father I was barely finding time for a proper workout. Recently I was reading about new research on Snack Exercises and how beneficial mini workouts of less than 2mins every so often, during the day are to our body. So, I decided to build an iOS App for me and others to help with this. The app generates a list of exercises that I need to tick to complete daily or loose my streak. The algorithm takes into account muscle groups and balancing the exercises to hit most main muscles. I also stayed going through all exercises and adding a couple of alternative exercises in case I don't feel like the recommended exercise. Since I'm not a trainer I commissioned professional exercise posture video guides and animations by an exercise expert which I attached to each exercise. I uploaded the app on the app store for free and no ads. If this is something that interests you, I want to hear how you balance a long day on your desk vs exercise. https://shortreps.com May 25, 2025 at 02:11AM

Show HN: Can AI Help Designers Ideate Better? We Spent 5 Wks Finding Out https://ift.tt/HG3mfSJ

Show HN: Can AI Help Designers Ideate Better? We Spent 5 Wks Finding Out We set out to answer a simple but deep question: Can AI actually practically help product designers improve during the discovery and ideation phase of the design process? So we spent 5 weeks running an experiment. We mapped every tool we use for discovery: Mobbin, Dribbble, Pinterest, Twitter, Behance We broke down typical design thinking and brainstorming workflows We reviewed every prototyping or idea-capturing tool we’ve used Then we tried building lightweight AI workflows with various LLM tools and frameworks Result: Yes. Used well, AI can significantly improve design thinking — especially for junior/mid-level designers — by offering faster idea generation, design critiques, and creative merges. Out of that research, we built Moonchild: A discovery-stage design ideation tool that: Generates thoughtful UI concepts from minimal prompts Allows asking design questions and getting structured critique Merges styles, flows, and interaction patterns from multiple directions Outputs great Figma-ready screens and UX flows, fast Try it (private beta): https://moonchild.ai Use code 'hackernews' for early access. Would love feedback — especially from product designers, PMs, and UX folks doing early-stage work. May 25, 2025 at 12:36AM

Show HN: Advanced Chunking in JavaScript/TypeScript with Chonkie https://ift.tt/labBS0s

Show HN: Advanced Chunking in JavaScript/TypeScript with Chonkie Hi HN, We’re Shreyash and Bhavnick. We built Chonkie, an open-source library for advanced chunking and embedding of text and code. It was previously Python-only, but we just released a TypeScript version: https://ift.tt/2fhaCnQ Many AI projects in JS/TS (like those using Vercel's AI SDK or Mastra) rely on basic text splitters. But better chunking = better retrieval = better performance. That’s what Chonkie is built for. Current native chunkers (in TS): - Code Chunker – handles Python, TypeScript, etc. - Recursive Chunker – rule-based, hierarchical splitting - Token Chunker – split by token count (fully customizable) - Sentence Chunker – split on sentence boundaries. Delimiters are customizable, so it works for multiple languages. All chunkers support custom tokenizers, chunk overlap, delimiters, and more. Coming soon in native TS (already available via the API client): - Semantic Chunker – splits texts wherever it detects a shift in meaning. - SDPM Chunker – merges semantically similar disjoint chunks - Late Chunker – generates context-aware embeddings for each chunk - Slumber Chunker – LLM-refined recursive chunks. Significantly reduces token usage (and thus cost) while maximizing chunk quality. - Embeddings Refinery - Embed chunks with any embedding model - Overlap Refinery – Create overlaps between consecutive chunks for better context preservation. Chonkie is free, open-source, and MIT licensed. GitHub: https://ift.tt/2fhaCnQ We’d love your feedback, ideas, or contributions. Thanks! May 24, 2025 at 01:33AM

Show HN: hcker.news – an ergonomic, timeline-based Hacker News front page https://ift.tt/OAxJf3X

Show HN: hcker.news – an ergonomic, timeline-based Hacker News front page Hi folks, I've built an alternative Hacker News front page. It is inspired by and meant to be a replacement for hckrnews.com. I built this because HN is woefully underfeatured, but most sites that try to improve it seem to assume that the visual design is the problem. hcker.news tries to maintain HN's familiarity while adding useful enhancements. There are three primary views: - Timeline View: Browse top stories by votes or comments grouped by day, week, or month (e.g., top 20 per day, top 100 per week). - Aggregate View: See top stories by votes or comments over custom time ranges. - Front Page View: The original HN front page, untouched. Feed Filtering: - Custom Keyword Filters: Include/exclude keywords (e.g., include "Rust," exclude "DOGE") or set a minimum score threshold. - No HN Algorithm: Timeline and Aggregate Views show stories usually downranked by the HN algo (e.g., flagged posts or those with too many comments). UI: - Unread Flags: Quickly spot new stories or ones you haven't seen. - Two Layouts: Classic HN style or a compact story view inspired by hckrnews.com. - Multi-column & High-density Modes: Fit more content on screen. - Themes: Light, Dark, and Manila. I'd love your feedback and suggestions. Cheers! https://hcker.news May 24, 2025 at 12:14AM

Show HN: 8-Bit Spelling Game I Built for My Daughter Using Claude AI https://ift.tt/ckSsEWv

Show HN: 8-Bit Spelling Game I Built for My Daughter Using Claude AI I had a lot of fun with this one. She's used it several times, and I watch, to see what subtle bugs or ux issues there may be. And when she gets on the bus I fix them quickly before work. It's been a fun game to create where it gives here immediate feedback and she's willing to study more. Her test is this Friday. fingers crossed that it helped her! https://ift.tt/8tUSmC7 May 22, 2025 at 07:44PM

Show HN: Free Text-to-Video for Learning Anything(Inspired by 3Blue1Brown) https://ift.tt/6KsD4L9

Show HN: Free Text-to-Video for Learning Anything(Inspired by 3Blue1Brown) I'm a huge fan of 3B1B and how he creates appealing and easy-to-understand videos. But he doesn't have a video for every single topic. Whenever I needed help in math or physics, I would try to watch his videos but the issue is that are just not specific enough to my content or curriculum. This issue applies to every single video explanation out there, they just aren't personalized. Most educational videos explain general topics, but they don’t align perfectly with the specific question I have or the way I need it explained. That’s the gap I wanted to fill. So I built a tool that generates high-quality, visually engaging explainer videos that are tailored exactly to the question you ask. Whether it's a niche math problem, a concept from your physics class, or something your textbook didn't explain well, this tool creates a custom explanation in the style of channels like 3B1B, but made just for you. The tool is free to use for some time. Me and my cofounder have dedicated a portion of our savings to this project and unless we get external funding in the near future, we would have to add a paid tier for the product or completely shut it down. Also, would love it if you show some support at our discord server. Thanks for your time! The tool is free to use for some time. Me and my cofounder have dedicated a portion of our savings to this project and unless we get external funding in the near future, we would have to add a paid tier for the product or completely shut it down. You can try it out yourself here --> https://trytorial.com/ . Also, would love it if you show some support at our discord server. Thanks for your time! https://trytorial.com/ May 22, 2025 at 11:30PM

Show HN: Super (YC W18) - Turn company data into answers & agents for your team https://ift.tt/Xjg6dWs

Show HN: Super (YC W18) - Turn company data into answers & agents for your team Hey there, Chris here We're known for our straightforward yet powerful Knowledge Base, Slite(YCW18).We launched our AI-powered search in Feb 2023 and after getting great response and usage, we dove deeper into solving the challenge of knowledge retrieval in daily work. That's why we're now launching our second major product, Super( https://www.super.work ). Super seamlessly connects your existing tools, providing accurate answers, streamlined workflows, automated digests, and much more. You might wonder: Why not just link your apps together using something like an MCP? The problem is that MCPs can't handle complex knowledge retrieval effectively. MCPs are basically LLMs equipped with API toolbelts. If you've ever tried asking a complicated question through an MCP, one that needs data from multiple different tools, you've likely faced frustrating delays. MCPs slowly make API calls one after another, causing long waits while they collect data from each endpoint. By contrast, Super quickly searches through all the data that actually matters from all of your tools simultaneously. This means you'll get your accurate answer in seconds, not minutes. The limitations of MCP-based solutions become clear when you try to deploy them reliably within a team. They either won't index your critical content effectively, won't do it fast enough, or won't cover all your tools at once. Properly chunking, embedding, querying, and filtering data from various sources is still essential. MCPs triggering APIs can't match this integrated approach for speed and accuracy. Moreover, Super understands the value of running multiple tasks simultaneously through LLMs. For example, one step may involve identifying search filters, while another simultaneously uses an LLM to aggregate and refine information. This parallel process quickly shapes the final, accurate answer for users. Additionally, MCPs aren't designed for enterprise-grade use. Businesses need standardized experiences, fine-grained user permissions, and consistent access controls across multiple tools. Super addresses these requirements by indexing data beforehand while still respecting each user's access permissions. Super offers: - Perplexity-like search experience on your team data - A growing selection of integrations with popular data sources - Customizable AI assistants tailored to your specific needs - An extension to embed Super directly into external websites you're already using - A clear path for your company to adopt AI strategically, rather than letting individual employees scatter across different, incompatible tools. And of course... It does comes with its MCP, which makes your agentic workflows actually able to properly tap on your data. Here's a quick video showing Super in action: https://www.youtube.com/watch?v=L5A6BRW90K4 Have you hit such walls with standard MCPs? Have you try building your own solutions? https://super.work May 21, 2025 at 07:48PM

Show HN: Appwrite Sites – the open-source vercel alternative https://ift.tt/FJmvNeZ

Show HN: Appwrite Sites – the open-source vercel alternative https://ift.tt/s6yb1MQ May 19, 2025 at 05:53PM