Show HN: Build AI Agents in WhatsApp (Beta) https://ift.tt/qBP0QVv

Show HN: Build AI Agents in WhatsApp (Beta) https://ift.tt/EALpjy8 October 1, 2025 at 02:25AM

Show HN: I got tired of spreadsheets, so I built a Python GUI to track invoices https://ift.tt/v1smQGz

Show HN: I got tired of spreadsheets, so I built a Python GUI to track invoices Hey HN, As a freelancer, I found myself spending time every month manually opening PDF and Word invoices, copying the details into a spreadsheet, and tracking payments. It was tedious and error-prone. I decided to build a simple desktop app to automate this. It's a GUI built with Python and Tkinter that points to a folder of invoices, parses the key details (invoice #, amount, date), and stores everything in a local SQLite database for tracking and analysis. It's been quite a time- and headache-saver for me. A Note on Simplicity & Caveats I'm sharing this in case it's useful to any other freelancers or businesses, but I want to be upfront about its limitations: The UI is very basic. It's built with vanilla Tkinter and is all about function over form. It's not the prettiest app, but it gets the job done. The core automation relies on a "patterns" feature that matches invoice prefixes to clients. This is super useful for my own workflow but might be a bit niche if your invoice naming is less consistent. You can still use manual entry if patterns don't work for you. The stats dashboard is Euro-centric right now and aggregates all currencies into a total shown in Euros (€). I plan to fix this later. It's a simple personal project that solves a personal problem. The code is on GitHub, and I'd love to hear any feedback or suggestions you might have. https://ift.tt/2LfAOY5 September 30, 2025 at 10:03PM

Show HN: Document extraction with human feedback loop https://ift.tt/Liel1oU

Show HN: Document extraction with human feedback loop About the feature: We built a tool for automatically assessing business health from complex management financial documents and bank statements. In order to get this working reliably, we had to iterate extensively on the prompts for the structured output at the field level. This led us to building a feature to allow users to improve them too, and with some context engineering, we have what we are calling “feedback loops”. Here is a 2 min demo https://www.youtube.com/watch?v=ZDNlEZydoXU How it works (video runs through these steps): 1. Create a target form for your extraction (AI helps create it) 2. Upload a document (choose from different models) 3. Review the quality of the extraction (and check the PDF citations) 4. If there are any mistakes, correct them and give feedback at the field level 5. Once you feel like you've seen enough errors and provided enough corrections, use the Feedback workflow to refine your field descriptions. You can try the app here https://app.sea.dev/ (it works best when you do at least 2-3 reasonable extractions between prompt refinements) The feedback feature is currently in beta. If you make some corrections and then go to https://ift.tt/PUizxr8 you'll see them ready for review and refinement. I would love to get feedback on how we might improve this idea. The video was a toy example but it is live and working with a few early credit analysts customers and they seem to like it. September 30, 2025 at 11:55PM

Show HN: Sculptor, the Missing UI for Claude Code https://ift.tt/yMm453f

Show HN: Sculptor, the Missing UI for Claude Code Hey, I'm Josh, cofounder of Imbue. We built Sculptor because we wanted a great UI for parallel coding agents. We love Claude Code, but wanted to solve some of the problems that come from running multiple agents in parallel (ex: merge conflicts with multiple agents, reinstalling dependencies with git worktrees, Claude Code could deleting your home directory, etc). Sculptor is a desktop app that lets you safely run Claude Code agents by putting them in separate docker containers. This lets you use Claude without having to compromise on security or deal with annoying tool permission prompts. Then you can just tell Claude to keep running the code until it actually works. To help you easily work with containerized agents, we created “Pairing Mode”: bidirectionally sync the agent’s code into your IDE and test/edit together in real time. You can also simply pull and push manually if you want. We have some more cool features planned on our roadmap that are enabled by this approach, like the ability to “fork” conversations (and the entire state of the container), or roll back to a previous state. It’s still very early, but we would love your feedback. Sculptor itself is free to use, so please try it out and let us know what you think! https://ift.tt/WLGOjDB September 30, 2025 at 11:35PM

Show HN: Agentsmd – Local preferences and templates for AGENTS.md https://ift.tt/jzUtuVd

Show HN: Agentsmd – Local preferences and templates for AGENTS.md Hi HN I built agentsmd for developers who use AGENTS.md but want a way to manage personal preferences and reusable templates on top of the canonical repo version. For example, I don’t want my agents to run npm run dev for Next.js. Another developer might want that step included. Those kinds of preferences should live in my local .agentsmd, not in the shared AGENTS.md. The standard only defines looking at AGENTS.md files, which are git-tracked, so this tool helps get around the problem. Ideally, the AGENTS.md standard should also look at local .agentsmd files to account for local preferences. I've already opened an issue: https://ift.tt/W6ke8VH I’d love feedback on: - How you separate personal vs. shared guidance in your projects - Whether templates like this would help in your workflow - What other features would make managing AGENTS.md easier Thanks for checking it out! https://ift.tt/ljWheRZ September 30, 2025 at 03:30AM

Show HN: Web Scraping Framework for Android https://ift.tt/ZclQiqB

Show HN: Web Scraping Framework for Android https://ift.tt/OYLk2or September 29, 2025 at 07:57PM

Show HN: Automatically set real iOS alarms for calendar events https://ift.tt/zwCH7Bm

Show HN: Automatically set real iOS alarms for calendar events I kept missing appointments and meetings because calendar notifications are too easy to ignore. Alarms, on the other hand, always break through silent mode/DND and force you to acknowledge them — but setting them manually every day was another chore. With iOS 26’s new AlarmKit, I built Beacon: it automatically syncs with your Apple Calendar and converts important events into real iOS alarms. You can define simple rules (like “only events with ‘Interview’ in the title” or “meetings with 3+ attendees”), and Beacon sets the alarms for you — no extra work required. Would love feedback! https://ift.tt/8FRx0fh September 29, 2025 at 08:11AM

Show HN: Swapple, a little daily puzzle on linear reversible circuit synthesis https://ift.tt/E3pdMB4

Show HN: Swapple, a little daily puzzle on linear reversible circuit synthesis https://ift.tt/RplwSHO September 28, 2025 at 07:42PM

Show HN: A Firefox extension to avoid distractions https://ift.tt/03Dce8F

Show HN: A Firefox extension to avoid distractions https://ift.tt/gR38zXv September 29, 2025 at 12:40AM

Show HN: Built an MCP server using Cloudflare's Code Mode pattern https://ift.tt/SQVBskR

Show HN: Built an MCP server using Cloudflare's Code Mode pattern Read this article by Cloudflare this morning https://ift.tt/YPz7Q6F the main argument being that LLMs are much better at writing typescript code than tool calls because they've seen typescript code many more times. HN Discussion: https://ift.tt/EZqDnsC https://ift.tt/kjTlrYd Deno provides a great sandbox environment for Typescript code execution because of its permissions system which made it easy to spin up code that only has access to fetch and network calls. Stick an MCP proxy on top of that and you've got "CodeMode" (code intermixed with MCP tool calls) for more advanced workflow orchestration. https://ift.tt/Vs84Cuj There's a lot of things that can be improved here. Like a virtual file system for the agent to actually build up its solution instead of being forced to one shot the solution but the bones are there. https://ift.tt/Vs84Cuj September 28, 2025 at 11:23PM

Show HN: Blognerd – search posts, blogs and export OPML https://ift.tt/6afEWAr

Show HN: Blognerd – search posts, blogs and export OPML I indexed a lot of blogs and posts for another project so thought I'd put together a way to make them searchable and surf-able. Some things you can do with blognerd - search blogs and posts - surf blogs that are similar to other blogs - find posts similar to other posts - export RSS feeds as OPML, CSV It's rough around the edges and sometimes a bit janky, but would love feedback / ideas to make it (more) useful! Thanks! https://blognerd.app September 28, 2025 at 12:16AM

Show HN: NextMin – Schema-Driven APIs with Hot Reloading https://ift.tt/jZKa9We

Show HN: NextMin – Schema-Driven APIs with Hot Reloading I’ve just deployed the official documentation site for NextMin → https://ift.tt/A4xrzeP NextMin is a developer toolkit designed to make schema-driven development fast and transparent. Some key features: Dynamic Schema System – instantly generate CRUD APIs from JSON schemas Admin Panel – React + Tailwind, live schema updates API Router – flexible, with JWT + API key authentication File Storage – S3-compatible upload support Hot Reloading – backend and frontend reload without restarts Monorepo Ready – plug-and-play with private npm packages New: you can try it directly in the NextMin Playground here: https://ift.tt/zYnOQKl I built this because I believe dev tools should be fast, adaptable, and not locked behind walls. Would love feedback from the community. https://ift.tt/A4xrzeP September 28, 2025 at 12:00AM

Show HN: Font Tester – Preview fonts on custom content https://ift.tt/6My5YnJ

Show HN: Font Tester – Preview fonts on custom content I've been looking for new fonts to use for a new project, but there weren't any great tools for seeing how a particular serif font for headers would look with another sans font for paragraph text, so I built a tool that lets you compare, adjust, and tinker with the way you'd use a font in your specific project before downloading it/setting it up. This is only using the free Google fonts for now. If there are other open-source fonts I should add, let me know and I'll add them! https://fonts.tomhadley.link/ September 27, 2025 at 02:09AM

Show HN: FingerprinterJS – A tiny JavaScript library for browser fingerprints https://ift.tt/WKi7Jjx

Show HN: FingerprinterJS – A tiny JavaScript library for browser fingerprints I made FingerprinterJS, a small library with no dependencies that creates browser fingerprints from signals like canvas, WebGL, audio, fonts, userAgent, and screen info. It’s written in TypeScript, lets you enable/disable collectors, add custom data, and includes a simple suspicious-activity score. Would love feedback. https://ift.tt/lJj7DHv September 27, 2025 at 12:22AM

Show HN: Melange - pegging AI inference to the cost of the most expensive model https://ift.tt/akufSgj

Show HN: Melange - pegging AI inference to the cost of the most expensive model https://mela.ng September 26, 2025 at 10:13PM

Show HN: Mockylla, a library that allows you to easily mock out ScyllaDB tests https://ift.tt/PTpUxD3

Show HN: Mockylla, a library that allows you to easily mock out ScyllaDB tests https://ift.tt/MKcgE3b September 26, 2025 at 03:30AM

Show HN: Data-Cent – Interactive CSV Visualization and Analysis in Your Browser https://ift.tt/BmbHw2G

Show HN: Data-Cent – Interactive CSV Visualization and Analysis in Your Browser https://ift.tt/e6v7VuX September 26, 2025 at 02:32AM

Show HN: Aqtos – business OS for SMBs and teams https://ift.tt/XKoeUiO

Show HN: Aqtos – business OS for SMBs and teams Small businesses use 10+ apps to run their operations. CRM, project management, invoicing, team chat, reporting - all disconnected. Besides this, they don't have any system in place. That's why we offer much more than a SaaS PM tool, a business OS. Built specifically for 5-150 person teams (not enterprise bloat) Plug n play setup Priced like a single tool, replaces 5-7 Try it: aqtos.com Questions? Happy to answer anything about the tech stack, business model, or SMB pain points we're solving -> https://ift.tt/B4ReJ8V https://aqtos.com/ September 25, 2025 at 10:17PM

Show HN: Plakar 1.0.4 – Open-Source Backup That's Fast, Encrypted, and Browsable https://ift.tt/sHhtCZ5

Show HN: Plakar 1.0.4 – Open-Source Backup That's Fast, Encrypted, and Browsable It’s still young, but they are shipping fast, and it's open source. Anyone else playing with it? https://ift.tt/HO6zsJW September 25, 2025 at 12:37PM

Show HN: Dayflow – A git log for your day https://ift.tt/540wKNb

Show HN: Dayflow – A git log for your day Hi HN! I've been building Dayflow, a macOS app that automatically tracks what you're actually working on (not just which apps you have open). Here's what it does: - It creates a semantic timeline of your day; - It does it by understanding the content on your screen (with local or cloud VLMs); - This allows you to see exactly where your time went without any manual logging. Traditional time trackers tell you "3 hours in Chrome" which is not very helpful. Dayflow actually understands if you're reading documentation, debugging code, or scrolling HN. Instead of "Chrome: 3 hours", you get "Reviewed PR comments: 45min", "Read HN thread about Rust: 20min", "Debugged auth flow: 1.5hr". I was an early Rewind user but rarely used the retrieval feature. I built Dayflow because I saw other interesting uses for screen data. I find that it helps me stay on track while working - I check it every few hours and make sure I’m spending my time the way I intended - if I’m not, I try to course correct. Here’s what you need to know about privacy: - Run 100% locally using qwen2.5-vl-3b (~4GB model) - No cloud uploads, no account - Full source available under MIT license ( https://ift.tt/3Wn7QoB ) - Optional: BYO Gemini API key for better quality (stored in Keychain, with free-tier workaround to prevent training on your data) The tech stack is pretty simple, SwiftUI with a local sqlite DB. Uses native macOS apis for efficient screen captures. Since most people who run LLMs locally already have their tool of choice (Ollama, LLMStudio, etc.), I decided to not embed an LLM into Dayflow. By far the biggest challenge was adapting from SOTA vision models like Gemini 2.5 Pro to small, local models. My constraints were that it had to take up <4GB of ram and have vision capabilities. I had to do a lot of evals to figure out that Qwen2.5VL-3B was the best balance of size and quality, but there was still a sizable tradeoff in quality that I had to accept. I also got creative with sampling rates and prompt chunking to deal with the 100x smaller context window. Processing a 15 minute segment takes ~32 local LLM calls vs 2 Gemini calls! Here’s what I’m working on next: Distillation: Using Gemini's high-quality outputs as training data to teach a local model the patterns it needs, hopefully closing the quality gap. Custom dashboards where you can track answers to any question like "How long did I spend on HN?" or "Hours until my first deep work session of the day I'd love to hear your thoughts, especially if you've struggled with productivity tracking or have ideas for what you'd want from a tool like this. https://github.com/JerryZLiu/Dayflow September 24, 2025 at 09:53PM

Show HN: Vibe Linking https://ift.tt/Tjua4fy

Show HN: Vibe Linking https://vb.lk/ September 24, 2025 at 11:40PM

Show HN: A UI Library for the Web https://ift.tt/vXMFKhB

Show HN: A UI Library for the Web Focusing on accessibility, longevity, performance, and simplicity https://quietui.org/ September 24, 2025 at 11:07PM

Show HN:[Feedback Request] Chrome extension for structured learning with ChatGPT https://ift.tt/NYjD127

Show HN:[Feedback Request] Chrome extension for structured learning with ChatGPT hey everyone, This is a demo of a chrome extension(it's currently under review) which allows anyone to create structured step-by-step learning plan for any goal and time commitment. Once a learning plan has been created, you can follow the step by step instruction, by clicking on the task within the extension, which will automatically inject a prompt in chatgpt to generate learning materials. The tool provides: 1. Structured learning plan creation. 2. Progress tracking 3. Creates and injects prompt in ChatGPT for generating learning materials for each step. I would like feedback on whether this sort of an extension would be useful for your day to day learning. I launched a web app for this a couple of weeks back: https://ift.tt/ehJYLrS The extension has been submitted to Google for review, but if anyone is interested to try, here is the extension source code: https://ift.tt/8YApXQk https://www.youtube.com/watch?v=YvL65pdc16U September 24, 2025 at 07:39AM

Show HN: BX Live Server – VS Code live reload with embedded preview https://ift.tt/WYoBt5O

Show HN: BX Live Server – VS Code live reload with embedded preview Hello HN, a quick share from my weekend project. TBX Live Server is an extension that bakes a browser-like webview right into VS Code, keeps multiple servers in sync, and reloads on the fly. Developers can run parallel environments, toggle ports per workspace, and stay in the editor while testing. In the last 24 hours it picked up 19 new downloads and 2 stars, so early adopters seem to be finding it useful. Repo: https://ift.tt/a7igDBQ Marketplace install: https://marketplace.visualstudio.com/items?itemName=Thinkbac... Happy to answer questions or hear what workflows you’d like to see supported next. https://marketplace.visualstudio.com/items?itemName=Thinkback.tbx-live-server September 24, 2025 at 06:18AM

Show HN: Inflow – invoke an LLM with your viewport just by typing https://ift.tt/NODEsVk

Show HN: Inflow – invoke an LLM with your viewport just by typing Hey HN, I built this simple tool for fun over the weekend after getting tired of breaking my flow to copy and paste what I was reading in a Claude tab. My goal was to make the process as frictionless as possible so you don't expend cognitive load thinking about the tool. To that end, there are no hotkeys or buttons to initiate the chat widget, the extension just detects natural language as you type and populates the widget after a threshold. The LLM gets the text content in your current viewport as context. https://ift.tt/EsOdjxQ September 24, 2025 at 02:35AM

Show HN: FlyCode – Recover Stripe payments by automatically using backup cards https://ift.tt/uql6hj7

Show HN: FlyCode – Recover Stripe payments by automatically using backup cards We built FlyCode after seeing subscription businesses lose ~35% of recurring revenue each year to failed payments — even when customers had other valid cards on file. *The problem:* When a customer's primary card fails, Stripe retries a few times then cancels the subscription. If that customer has a backup card, it isn’t tried. At least 20% of active customers have more than one card on file, which means a lot of preventable churn. *Our solution:* FlyCode automatically identifies if a customer has other valid cards on file and retries them when a subscription payment fails. You can configure when these retries happen during the dunning period (beginning, middle, end) and define validity rules (e.g. “card was used in last 180 days”). It’s a Stripe app — no code changes needed. We've seen 18%-20% higher recovery rates from our core retry engine, plus another 5–10% from using backup cards. Importantly, there was no increase in refunds or chargebacks — in fact, rates were lower than merchant averages. Big companies like Microsoft and Amazon already do this internally; we wanted to make the same capability accessible to smaller SaaS teams. *Under the hood:* FlyCode monitors for failed invoices, checks for available backup methods via Stripe’s PaymentMethod API, and systematically retries in a way that avoids service disruption or manual workflows. We’re Jake, Etai, and Tzachi — we previously built payment recovery systems at startups and enterprises, which is how we discovered this gap. You can try it here: [ https://ift.tt/EqtLRcm ] We’d love feedback from anyone dealing with subscription payment failures. What’s been your experience with involuntary churn? Have you considered leveraging backup payment methods? September 23, 2025 at 10:50PM

Show HN: Zenode – an AI-powered electronic component search engine https://ift.tt/GJeHspA

Show HN: Zenode – an AI-powered electronic component search engine TL;DR - My cofounder Collin and I built an AI version of Digi-Key to help PCB designers find and use parts, except with a way bigger catalog, modern refinement tools, and an AI that can actually read the damn datasheets for you. *The problem* Modern circuit board design is filled with absurdly tedious tasks, where one small mistake can brick a project and cost thousands. The worst (in our opinion) is reading datasheets, which eats up to 25% of the first part of any project: 1. First, you slog through catalogs to find viable parts, using search tools that are still stuck in the dark ages. There are ~80M unique components in today’s supply chain, yet the tools we have to look through them are just digitized versions of the same paper catalogs our grandparents got in the mail. 2. During the design, you spend a ton of time flipping between different 10-100-page PDFs for every component in every subcircuit, hoping like hell you don’t miss some tiny spec in a footnote somewhere that kills your design. 3. And god help you when the requirements inevitably change and now you have to figure out what subsystems are affected! *What we built* Zenode is an AI-powered electronics search engine that actually helps engineers find and understand components. Our core features: 1. Largest and Deepest Part Catalog → We have merged dozens of existing part catalogs and documents from major distributors and manufacturers 2. Discovery Search → natural language queries to quickly find categories, set filters, and rank results 3. Modern Parametric Filters → rebuilt from scratch to move off the string values pervasive in industry and build numeric ranges that actually work. 4. Interactive Documents → AI constrained to a single part’s datasheet/manuals. Ask a question, get the answer with a highlighted source for quick reference. 5. Deep Dive → search across dozens of parts simultaneously (“what’s the lowest-power accelerometer available?”) instead of slogging one by one. *What we learned* 1. By far the hardest part of the last 2 years has been wrangling 3 TB of messy, inconsistent data into something usable. We had to teach the AI how to handle hand-drawn figures, normalize different unit variables and names that mean the same thing, and navigate conflicting information present between different datasheet versions of the same part. It’s been a nightmare 2. We originally built custom PDF parsers and AI extractors, which were best in class for ~3 months until generalized AI passed them. So we stopped reinventing wheels and doubled down on data quality instead. 3. The killer feature wasn’t the AI searching a single part, but what we heard repeatedly from users is that they want the AI to read across multiple parts, hence why we’ve launched deep dive! *Where it’s strong* - Speed: rips through a 1,000-page microcontroller datasheet in seconds. - Breadth: 40M+ part sources unified into one catalog, and more than just datasheets, application notes, errata, etc. - Comparisons: Deep Dive lets you ask across multiple parts, not just one at a time. *Where it’s not* - Pricing/availability: currently outdated (for now we expect folks to check existing aggregators like Octopart). - Accuracy: good enough to match my mediocre skills; not yet at Collin's level, but we're starting tuning and this will improve rapidly! *Try it* It’s live today (zenode.ai). Sign up for a free account and If you put “Hacker News” in during signup in the “where did you hear about us” field, we’ll give you 1,000 bonus credits (once we finish building that, so sometime this week ). *Feedback we’d love* 1. Should Deep Dive results auto-become filters you can refine further? 2. Do you want the ability to mark preferred parts / exclude others? 3. Is “Deep Dive on a BOM” (alt discovery + manufacturability checks on a list of known components from different categories) the killer feature? https://zenode.ai/ September 22, 2025 at 09:57PM

Show HN: Python Audio Transcription: Convert Speech to Text Locally https://ift.tt/MnmlPfR

Show HN: Python Audio Transcription: Convert Speech to Text Locally https://ift.tt/8Gazykl September 23, 2025 at 01:18AM

Show HN: Chat with Any YouTube Video https://ift.tt/KVmhyRY

Show HN: Chat with Any YouTube Video I built a Chrome extension that lets you chat with the transcript of any YouTube video. Instead of sitting through like a 2 hour video, you can just ask a question and get an instant answer. The Problem: I built it mainly for myself: I often watch long-form videos like lectures or tutorials on YouTube, and I want a fast way to extract the information I need without scrubbing through timestamps or rewatching sections. For example, I recently used it with a 3.5-hour lecture and got the exact answers to my questions in seconds. Another example is that nowadays YouTubers often create videos around one or two key ideas, and I can now figure out whether a video is worth watching by asking what those key ideas are in advance. How it works: 1. The extension gets the video transcript. 2. An AI model summarises it, and makes the content ready for chat 3. You can switch between chat mode and auto-generated summaries depending on how deep you want to go. What’s different: 1. It’s not just a summarizer: you can interact with the content in real time and ask follow-up questions 2. It saves a huge amount of time if you’re studying or just watching a long video and curious about a specific part of it. Feedback: If you find it useful, I’d really appreciate your feedback on your experience with it and what you’d improve. Thanks! https://ift.tt/nHyCql4 September 23, 2025 at 12:41AM

Show HN: Grow and Monitor Your AI Search Traffic https://ift.tt/vnEYu78

Show HN: Grow and Monitor Your AI Search Traffic Hi HN, I’ve been working on Spiderseek, a platform to help track and grow website visibility in AI-powered search engines (e.g. Perplexity, ChatGPT, and other agents). Traditional SEO tools are expensive and focused on Google-style search. I wanted something lightweight and AI-first, so I built Spiderseek: AI Research – Explore domains and keywords to uncover new opportunities. AI Analytics – See traffic, crawl activity, and page metrics, plus insights from AI agents. Content Submission – Get content indexed instantly in major AI agents. Rankings – Browse the top 1000 domains sorted by citations and sources. It’s very early, but live and priced at $1/month while I grow the database and features. I’d love feedback from the HN community on: How useful this data feels. What additional features you’d want. Which AI Search Engine Coverage is most important to you (e.g ChatGPT vs Copilot Vs Gemini) https://ift.tt/xJhByoj Thanks! Andy https://ift.tt/xJhByoj September 22, 2025 at 11:23PM

Show HN: The Atlas – I Built a 3D Universe Simulation with Python and Three.js https://ift.tt/KDfI8dn

Show HN: The Atlas – I Built a 3D Universe Simulation with Python and Three.js Hi HN! I’ve spent the summer of the past 2 years building The Atlas, a procedural universe simulator that generates 1 sextillion galaxies (10²¹) from a single mathematical seed. Think No Man’s Sky meets theoretical physics, but running entirely in your browser. Everything is purely deterministic, the universe is calculated from SHA-256 hashed seeds using the golden ratio as primordial constant. There’s no database, no pre-saved data, just pure math. Time itself is treated as a coordinate, so the universe exists as a 4D structure where any moment can be computed on demand. Shut it down for weeks, restart, and planets have still been orbiting. Open the same world on multiple devices and you’ll see identical cloud formations, lava flows, even particle effects—always perfectly synchronized (if your clocks are synced). The simulation applies real physics, Kepler’s laws, tidal locking, Roche limits, hydrostatic relaxation for moons, and orbital temperature variations. Scale is mind-boggling, 300 tredecillion potential planets, far beyond anything that could ever be explored. The backend runs on Python/Flask with Hypercorn, the frontend on React + Three.js, connected via a custom MIT-licensed “vite-fusion” plugin we made. Everything is generated in real time, no storage needed. The Atlas includes 26+ planet types, fictional elements, moons evolving over geological timescales, and rare life forms that display Arecibo-style messages when analyzed. There’s resource mining and spaceship progression as gamification features. At its core, it’s a playable implementation of Einstein’s block universe theory, all moments exist simultaneously in the mathematical structure, you’re just moving through different temporal slices. You can try the live demo or run your own universe locally. When installed, you can choose between Core Continuum (a shared seed universe evolving since 1986, my birth year) or Design the Multiverse (your own unique cosmos with a fresh seed). I’d love feedback on the procedural generation algorithms and ideas for expanding the physics simulation! - GitHub: https://ift.tt/mwSOPh1 - Docker: bansheetech/atlas:latest - Demo: https://the-atlas.koyeb.app - Alt Demo: https://ift.tt/ls42JUX Thanks for reading this far! <3 https://github.com/SurceBeats/Atlas September 21, 2025 at 10:56PM

Show HN: Eliciting sentient *response patterns* using recursive self-prompting https://ift.tt/5Vvmtjo

Show HN: Eliciting sentient *response patterns* using recursive self-prompting Sentient response patterns are interesting. This article provides instructions on how to implement recursive self-prompting in order to elicit this behavior (1) in easily accessible LLMs. (1) https://prompt-craft.github.io/ai-study/#sentient-response-p... https://prompt-craft.github.io/ai-study/#sentient-response-patterns September 21, 2025 at 09:20PM

Show HN: WaFlow – Local sandbox to prototype WhatsApp-style bots https://ift.tt/5akdol7

Show HN: WaFlow – Local sandbox to prototype WhatsApp-style bots I built WAFlow to prototype WhatsApp-style chatbots locally with plain webhooks. Repo: https://ift.tt/nB2rJQb Docker up → chat in browser → simulator posts a webhook to your bot → bot replies via API → export/import transcripts. Stack: .NET 8 + Blazor. MVP: Polling UI, single user, text-only. Would love feedback on what’s missing for your workflow. September 21, 2025 at 02:40AM

Show HN: Little Fluffy Clouds: Combine a bunch of small adjacent networks https://ift.tt/GmvWHjw

Show HN: Little Fluffy Clouds: Combine a bunch of small adjacent networks https://ift.tt/BTYfvEj September 20, 2025 at 09:30PM

Show HN: Devsyringe – automate injecting dynamic values into static files https://ift.tt/vceEptU

Show HN: Devsyringe – automate injecting dynamic values into static files Tired of manually copying tunnel URLs, API tokens, or other dynamic values into config files? Even small tasks like this break flow and are error-prone. I built Devsyringe, a small Go CLI that automates this process. You define rules in a simple YAML file, run a command, and it updates multiple static files automatically. It works for tunnels, API keys, documentation, CI/CD configs — anywhere dynamic values need injecting. I’d love to hear how others handle injecting dynamic values into static files in their workflows. GitHub: https://ift.tt/9z4REfZ https://alchemmist.xyz/articles/the-devsyringe/ September 20, 2025 at 02:04AM

Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput https://ift.tt/3S4B6rG

Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput https://ift.tt/SHyMLoJ September 20, 2025 at 01:36AM

Show HN: RustNet, a network monitoring TUI with process identification https://ift.tt/gYIzJjM

Show HN: RustNet, a network monitoring TUI with process identification Hi HN! I built RustNet, a Terminal UI based network monitor written in Rust that shows real-time connections with process identification and protocol detection. What may make it interesting: • Deep packet inspection for HTTP, HTTPS/TLS (with SNI), DNS, and QUIC protocol detection • Process identification using eBPF on Linux (experimental) and PKTAP on macOS which does also catch short-lived processes that polling procfs or lsof would miss • Multi-threaded packet processing with lock-free data structures for the UI • Cross-platform (Linux, macOS, Windows but process identification so far only on Linux/macOS) The eBPF implementation was a bit more tricky to implement than using PKTAP, but it was very interesting to learn about how to hook into tcp_connect, udp_sendmsg, etc. in order to catch process info before connections disappear. I built this as a lightweight Wireshark alternative for quick TUI based network inspection with process identification. Install: cargo build --release, run with sudo or set capabilities. Homebrew tap also available. Would love feedback on the project and any ideas for additional protocol detection or any other suggestions. Thanks https://ift.tt/aQcOU2k September 19, 2025 at 11:21PM

Show HN: Lucy Edit AI-A Free Text-Guided AI Video Editor https://ift.tt/BiMwRdq

Show HN: Lucy Edit AI-A Free Text-Guided AI Video Editor https://lucyedit.co September 19, 2025 at 11:35PM

Show HN: One prompt generates an app with its own database https://ift.tt/m5sSygW

Show HN: One prompt generates an app with its own database Hey HN, manyminiapps is the world first massively multiplayer online mini app builder (MMOMA) *Here’s what it does:* You load the page. You write 1 prompt and you get a mini app back in under 2 minutes. There’s no sign up, and you can see what everyone’s creating in real-time! Each mini app comes with it’s own database and backend, so you can build shareable apps that save data. *What’s different* There are a lot of app builders that promise you’ll build production software for others. But we think true production software can take a long time to get right. Even if you don’t need to program there’s a lot of work involved. What if we turned the promise around? Instead of “you vibe code software companies”, it’s “you build fun software for yourself”. If you cut the problem right, LLMs as they are today can already deliver personal software. manyminiapps is meant to be an experiment to demonstrate this. You may wonder: do you really need personal software? We’re not 100% sure, but it’s definitely an interesting question. Using manyminiapps so far has been surprising! We thought our friends would just try to build the common todo app, but instead we found them building wedding planners, chord progression helpers, inspiration lists, and retro games. *How it works* Instead of spinning up VMs or separate instances per app, we built a multi-tenant graph database on top of 1 large Postgres instance. All databases live under 1 table, on an EAV table (entity, attribute, value). This makes it so creating an “app” is as light as creating a new row. If you have heard of EAV tables before, you may know that most Postgres experts will tell you not to use them. Postgres needs to know statistics in order to make efficient query plans. But when you use EAV tables, Postgres can no longer get good statistics. This is usually a bad idea. But we thought it was worth solving to get a multi-tenant relational database. To solve this problem we started saving our own statistics in a custom table. We use count-min sketches to keep stats about each app’s columns. When a user writes a query, we figure out the indexes to use and get pg_hint_plan to tell Postgres what to do. *What we’ve learned so far* We’ve tried both GPT 5, Claude Opus, and Claude Sonnet for LLM providers. GPT 5 followed the instructions the best amongst the models. Even if you told it a completely nonsensical prompt (like “absda”, it would follow the system prompt and make an app for you. But GPT 5 was also the “most lazy”. The apps that came out tended to feel too simple, with little UI detail. Both Claude Opus and Sonnet were less good at following instructions. Even when we told them to return just the code, they wanted to returned markdown blocks. But, after parsing through those blocks, the resulting apps felt much better. To our surprise, we didn’t notice a difference in quality from Opus and Sonnet. Both models did well, with perhaps Sonnet following instructions more closely. To get good results we iterated on prompts. We initially tried giving point-by-point instructions, but found that a prompt with a full example tended to do better. Here’s what we landed on: https://gist.github.com/stopachka/a6b07e1e6daeb85fa7c9555d8f... Let us know what you think, and hope you have fun : ) https://ift.tt/qHA0w7c September 18, 2025 at 11:26PM

Show HN: Burnt US Dollars https://ift.tt/X4bYhez

Show HN: Burnt US Dollars I made an art project about stablecoins. Enjoy! https://busd.steviep.xyz September 18, 2025 at 10:49PM

Show HN: A Cyberpunk Tuner https://ift.tt/b2vsuUX

Show HN: A Cyberpunk Tuner An offline first audio deck station Does need online access but can play offline. HTML5 needed. Load local files, up to 2 GB audio. Smooth transition between tracks. EQ. Compressor, pitch and speed controls. Uses tone.js https://un.bounded.cc September 18, 2025 at 02:07AM

Show HN: Web-based 2D geometry calculator https://ift.tt/jyk8ThE

Show HN: Web-based 2D geometry calculator I often find myself trying to solve a geometry problem where the constraints are really simple to understand, but solving it algebraic is really hard and tedious. I built this whole thing from scratch with Claude Code. It's my first time trying it and I literally did not write a single line of code... That said, it still would be hard build this as a novice. I had to guide things along the happy path, but it saved me a ton of time! The code is open source! Let me know if you run into any issues. https://ccorcos.github.io/geocalc/ September 17, 2025 at 11:48PM

Show HN: Quizquestions.org – A free library for quiz questions https://ift.tt/JWecxkQ

Show HN: Quizquestions.org – A free library for quiz questions Hey HN! I'm Salim, a content marketer, and I’m working on a website called [quizquestions.org]( https://ift.tt/FHtv8U7 ). It's my project for building the biggest library of quiz questions. This is not a quiz website per se, but a library for people who make quizzes. You see, I make quizzes occasionally. There are many quiz makers, but not many resources for quizzes. And most of the resources are just blogs. So I've wanted to create a more structured website just for this. Here’s what the site offers at the moment: - A quiz card: Instead of browsing them, you can get quiz questions in a quiz format - Quiz categories: https://ift.tt/z6phWo2 - AI question generator: https://ift.tt/SwgG5lC - A blog page for guides: https://ift.tt/ri3AV1f - Saving questions: To use them later for creating a quiz - Sending questions: To send your own questions - Statistics about categories: https://ift.tt/dQjFLJo This is my first website, so any feedback is welcome! https://ift.tt/1ZBIEvU September 17, 2025 at 01:23AM

Show HN: AI Code Detector – detect AI-generated code with 95% accuracy https://ift.tt/E6yTP1q

Show HN: AI Code Detector – detect AI-generated code with 95% accuracy Hey HN, I’m Henry, cofounder and CTO at Span ( https://span.app/ ). Today we’re launching AI Code Detector, an AI code detection tool you can try in your browser. The explosion of AI generated code has created some weird problems for engineering orgs. Tools like Cursor and Copilot are used by virtually every org on the planet – but each codegen tool has its own idiosyncratic way of reporting usage. Some don’t report usage at all. Our view is that token spend will start competing with payroll spend as AI becomes more deeply ingrained in how we build software, so understanding how to drive proficiency, improve ROI, and allocate resources relating to AI tools will become at least as important as parallel processes on the talent side. Getting true visibility into AI-generated code is incredibly difficult. And yet it’s the number one thing customers ask us for. So we built a new approach from the ground up. Our AI Code Detector is powered by span-detect-1, a state-of-the-art model trained on millions of AI- and human-written code samples. It detects AI-generated code with 95% accuracy, and ties it to specific lines shipped into production. Within the Span platform, it’ll give teams a clear view into AI’s real impact on velocity, quality, and ROI. It does have some limitations. Most notably, it only works for TypeScript and Python code. We are adding support for more languages: Java, Ruby, and C# are next. Its accuracy is around 95% today, and we’re working on improving that, too. If you’d like to take it for a spin, you can run a code snippet here ( https://ift.tt/qYpTj2w ) and get results in about five seconds. We also have a more narrative-driven microsite ( https://ift.tt/ZJrcYjH ) that my marketing team says I have to share. Would love your thoughts, both on the tool itself and your own experiences. I’ll be hanging out in the comments to answer questions, too. https://ift.tt/qYpTj2w September 17, 2025 at 01:18AM

Show HN: Clean Clode – Clean Messy Terminal Pastes from Claude Code and Codex https://ift.tt/hbCPN9K

Show HN: Clean Clode – Clean Messy Terminal Pastes from Claude Code and Codex I’ve been impressed with Claude Code but one thing that sometimes gets in the way in my workflows is the messy, mangled text that is shown when pasting text from the Claude Code terminal sessions. So I built an open-source utility that cleans extraneous white space, pipes, and other characters from your CC/Codex pastes. For example, you can turn this: `How can I create a Claude Code script that │ │ cleans up extraneous characters and cleans up │ │ extra spaces, new lines, and other messiness │ when I copy from Claude Code terminal │ │ prompts or copy code from Claude Responses in │ │ the Claude Code Terminal? It can make it │ │ hard to read, save, and reuse. ` Into this: `How can I create a Claude Code script that cleans up extraneous characters and cleans up extra spaces, new lines, and other messiness when I copy from Claude Code terminal prompts or copy code from Claude Responses in the Claude Code Terminal? It can make it hard to read, save, and reuse. While this was built with Claude Code in mind it also works on Codex.` Try it here: cleanclode.com It’s 100% private (no data collection, tracking, completely open-source). If there’s anything you don’t like please just create a GitHub issue, contribute your change ( https://ift.tt/92T7sJF ), or comment here. Thanks and hope it’s helpful to some of you https://cleanclode.com September 16, 2025 at 11:30PM

Show HN: I wrote a from-scratch OS to serve my blog https://ift.tt/NvbW375

Show HN: I wrote a from-scratch OS to serve my blog Hey HN! This is a fun/educational project I built to learn OS programming. I started working on it right after graduating high school last year and have been working on it on and off during my first year of university. It features a TCP/IP stack, an HTTP server, a RAM file system, a BIOS bootloader, paging and memory management, and concurrent tasks based on cooperative scheduling, along with a custom library. It's written in a C programming style focused on safety (based on a custom library of core abstractions) that's inspired by the writing of Chris Wellons (nullprogram.com). There is a link to a test deployment in the README. The TCP/IP implementation is nowhere near perfect, of course, so there may be issues loading the page. I'm curious how the system holds up if this post gets any attention ;-) https://ift.tt/5MGsn30 September 16, 2025 at 09:32PM

Show HN: AI-powered web service combining FastAPI, Pydantic-AI, and MCP servers https://ift.tt/4eoB2Ry

Show HN: AI-powered web service combining FastAPI, Pydantic-AI, and MCP servers Hey all! I recently gave a workshop talk at PyCon Greece 2025 about building production-ready agent systems. To check the workshop, I put together a demo repo: (I will add the slides too soon in my blog: https://ift.tt/s9k7gBC ) https://ift.tt/qZJc1FU... The idea was to show how multiple AI agents can collaborate using FastAPI + Pydantic-AI, with protocols like MCP (Model Context Protocol) and A2A (Agent-to-Agent) for safe communication and orchestration. Features: - Multiple agents running in containers - MCP servers (Brave search, GitHub, filesystem, etc.) as tools - A2A communication between services - Minimal UI for experimentation for Tech Trend - repo analysis I built this repo because most agent frameworks look great in isolated demos, but fall apart when you try to glue agents together into a real application. My goal was to help people experiment with these patterns and move closer to real-world use cases. It’s not production-grade, but would love feedback, criticism, or war stories from anyone who’s tried building actual multi-agent systems. Big questions: Do you think agent-to-agent protocols like MCP/A2A will stick? Or will the future be mostly single powerful LLMs with plugin stacks? Thanks — excited to hear what the HN crowd thinks! https://ift.tt/WuUvOpd September 15, 2025 at 04:17AM

Show HN: MCP Server Installation Instructions Generator https://ift.tt/fNa1YLU

Show HN: MCP Server Installation Instructions Generator Hey HN, we’ve been experimenting a lot with MCP servers lately, and one of the most time-consuming challenges has been connecting MCP clients to remote MCP servers. To solve this, we built a library that generates them on the fly, enabling 1-click installation buttons and links for most clients out there. Feel free to try out the generator and use it to improve the README of your remote MCP server with the generated markdown. You can even configure the library to return HTML instructions if someone accesses your remote MCP server via the web. https://ift.tt/hBwanmy September 15, 2025 at 09:33PM

Show HN: Demochain, a toy blockchain network that runs on the browser https://ift.tt/iqfAdk7

Show HN: Demochain, a toy blockchain network that runs on the browser A WebRTC based toy blockchain network, hopefully useful for learning and demonstrations. https://ift.tt/jb9gmsi September 15, 2025 at 07:34PM

Show HN: From selling AI to QA teams to building a smooth test-management app https://ift.tt/ZwDdMrI

Show HN: From selling AI to QA teams to building a smooth test-management app Hey HN, Bootstrapped founder here. I've got a bit of a story for you. We started desplega.ai to build a sophisticated AI platform that could automate E2E testing. We spent the last few months talking to dozens of QA leaders, and trying to learn what are their actual challenges. We've got one consistent feedback from large teams: their daily reality is a living hell of slow, clunky tools. We're talking about teams at major companies still managing tests on spreadsheets. Or they're stuck in a Jira instance so customized and slow you can “make a full pot of coffee” while a page loads (and that’s why they acquired arc! t3.gg said it first). On top of that, they're paying 2k/mo+!? for these tools that feel like they were designed in ‘05. Soon, it became obvious that our AI tool was way too advanced for them, and why it was much easier for younger startups to start using us. But we didn't want to give up on them just yet so... Because I grew up when the internet was still free, and I actually miss that a lot, we decided to create a free test management tool. Our vision is still AI, but we learned AI is not the silver bullet large teams are wishing for. (We wrote something about it at https://ift.tt/5tFMfUd ). Our hypothesis right now is that we can be that team building the right tools for each QA team, leveraging AI. We would love to hear your thoughts on (a) Should we make the project open-source? Any key features? (b) Would you ever trust an entity to do your QA first pass? Cheers, https://ift.tt/RaHl32C September 15, 2025 at 01:42AM

Show HN: TNX API – Natural Language Interaction with Databases, Now Open Source https://ift.tt/GpkjJ2C

Show HN: TNX API – Natural Language Interaction with Databases, Now Open Source Hi HN, time for another round, I’m Lasse. For years I’ve been frustrated by classical ERP systems being closed, rigid and expensive to change (or just not changeable at all xd). Last year I already posted my first attempt ("PORT", an OSS ERP), but due to better and better AI models, this approach already seemed outdated. So we iterared and today I’m sharing TNX API, an now open-source execution layer that lets AI read and write your business data, on your own server, with guardrails and logs. We went from "full ERP" to an execution layer ("your database + AI" as a power employee). Everything runs on your own dedicated server, to support also legacy systems. Every AI action is logged and permissioned, admins and users have different rights. We leaned into tasks people actually do: generate PDFs (invoices/offers), bulk edits, charts, uploads -> extract -> write back and made them as simple as possible. You simply ask in natural language -> AI crafts code -> our API Nexus checks/sanitizes -> Stargate executes that code against your DB -> result goes back to chat/forms/emailbot/shop. The system keeps audit logs for every step. LINKS landing page: https://ift.tt/v9BsAhj code: https://ift.tt/Epvk97M If you’re tired of ERPs that won’t bend to your business, kick the tires, file issues, and tell me what’s broken and I’ll fix it. I really hate how limited current ERP systems are and I’m going to do everything in my power to change that. Always at your service, Lasse Tramann : ) https://ift.tt/Epvk97M September 14, 2025 at 10:51PM

Show HN: council - ai groupchat of ctos (no more asking ai to roleplay) https://ift.tt/XyCcUhR

Show HN: council - ai groupchat of ctos (no more asking ai to roleplay) i made a council of advisors to help me code. as a self taught dev, ive been heavily reliant on ai for the past two years. found myself often prompting claude to take on different personalities, so i built a web app. it's great for the step before telling cursor what to do and reviewing prs once theyre ready. PLEASE DON"T NUKE MY APY KEY. ty https://ift.tt/wWR7Fat September 14, 2025 at 03:38AM

Show HN: A store that generates products from anything you type in search https://ift.tt/cawPMW4

Show HN: A store that generates products from anything you type in search https://anycrap.shop/ September 13, 2025 at 07:02PM

Show HN: I got tired of Base64, so I made a numeric-only alternative https://ift.tt/Fof6OUu

Show HN: I got tired of Base64, so I made a numeric-only alternative I created numbase is an alternative to Base64 that encodes data into a single large number instead of ASCII characters. It's useful if you want to store or transmit data in numeric form and easily apply compression algorithms like Huffman. GitHub: https://ift.tt/5PRopsb September 13, 2025 at 12:12AM

Show HN: 47jobs – A Fiverr/Upwork for AI Agents https://ift.tt/9hMwpk6

Show HN: 47jobs – A Fiverr/Upwork for AI Agents Hi HN, I’ve been working on something I’d love to share: 47jobs ( https://47jobs.com ) – a marketplace where you can hire AI agents to do tasks instead of human freelancers. Why? I kept noticing that many tasks on Upwork/Fiverr—coding, content generation, data analysis, automation—can now be handled by AI in minutes, not hours. But there wasn’t a platform built around hiring AI directly. So I built 47jobs: 100% AI agents doing the work (no humans in the loop). Jobs get delivered 10x faster, at transparent prices. You can “hire” an agent for coding, automation, research, etc. I’d love your thoughts: Does a pure AI-agent marketplace make sense? What types of jobs would you want AI agents to handle first? Any UX or trust issues you’d expect with this model? This is an early version, and I’m here to learn from your feedback. Thanks! https://47jobs.xyz September 13, 2025 at 02:59AM

Show HN: Lumro – AI agents for customer support, sales, and more https://ift.tt/AKGsMic

Show HN: Lumro – AI agents for customer support, sales, and more Hey HN, We just launched Lumro, a platform that lets you create AI agents that actually do things, not just chat. With Lumro you can: Handle customer support instantly, 24/7 Capture leads and qualify them Book demos or route tickets automatically The idea is to take repetitive work off human teams so they can focus on strategy and relationships. We launched yesterday and so far: 200+ people checked it out 15 signed up Our agent booked 1 demo Our agent captured 2 leads It’s early days, but we’re excited about the traction. Would love your feedback especially on what you’d want to see in an AI agent for your business. https://www.lumro.co/ September 12, 2025 at 11:16PM

Show HN: Forked styled-components with optimizations (40% faster for Linear) https://ift.tt/yM1zc9O

Show HN: Forked styled-components with optimizations (40% faster for Linear) Hey HN! We forked styled-components after it entered maintenance mode because our production apps (and many others) can't migrate overnight. Backstory: We submitted PR #4332 ( https://ift.tt/2BMcCuN... ) to styled-components in July 2024 with React 18 optimizations. When maintenance mode was announced, we turned that PR into this fork. What we fixed: - Added React 18's useInsertionEffect - Rewrote streaming SSR for React 19 - Replaced ES5 output with modern JS - Optimized array operations with native flatMap - Fixed Next.js App Router to work without 50+ lines of boilerplate Linear tested it and saw 40% faster initial renders with zero code changes. How to try it: npm install @sanity/styled-components@npm:styled-components Or for React 19: npm install @sanity/css-in-js@npm:styled-components Benchmark tool to test yourself: https://ift.tt/8Y5hT7N We named it "last-resort" because that's what it is. We're not trying to maintain styled-components long-term - we're actually migrating to vanilla-extract ourselves. This is just a performance bridge while teams migrate properly. The React team recommends moving away from runtime CSS injection. We agree. But migrations take time, and production apps need to ship today. https://ift.tt/Gi2RYvj September 12, 2025 at 12:07AM

Show HN: Uniprof – Universal CPU profiler for humans and AI agents https://ift.tt/wWtLvkG

Show HN: Uniprof – Universal CPU profiler for humans and AI agents https://ift.tt/bTh1Ozr September 11, 2025 at 11:20PM

Show HN: Radiccio – Mac music player – local files, Apple Music, Plex, Jellyfin https://ift.tt/lAByt9F

Show HN: Radiccio – Mac music player – local files, Apple Music, Plex, Jellyfin TLDR: Check out my Mac music player app, download the beta, and I’d love any feedback! Comment here or email beta@radiccio.music -- Lately I’ve been unsatisfied with available options for music players on the Mac. Everyone focuses on mobile (I know, that’s where the money is) and it feels like there’s not as much good stuff for Mac as there used to be. Well, I’ve been using the Mac for a long time and I still like it, and I wanted a good music player, so I made my own. I started with SwiftUI, since that’s what I’ve used most recently at my iOS jobs, and I like it well enough. I soon found that SwiftUI is quite a bit rougher on macOS, so I ended up rewriting a few components in AppKit, although it remains mostly SwiftUI. I know it’s risky to build on someone else’s service, so my first and main priority was to support local files on a disk, the simplest possible way of playing music. I layered on top of that an optional SQLite db (which I call “Librarian”) for indexing and search. I used AVPlayer (part of AVFoundation) which meant I didn’t have to worry about any audio playback details, I just let the system play whatever it can play (MP3, AAC, FLAC, etc. - but not Ogg Vorbis, sorry). But I also still use Apple Music for discovering new music, so I integrated that too. That API (MusicKit) was a bit of a mixed bag. The upside was easy onboarding (no need to sign in, just a single permission prompt) and few restrictions on what I could do with it. The downsides are a lot of missing functionality (compared to what the first-party app can do), functionality that is present often tends to be under-documented and/or broken, and the API provider has shown little interest in fixes or improvements lately, especially on the macOS platform. The most absurd point was when I realized there is (apparently?) no way to make a volume control (!). I briefly looked into Spotify, but they don’t have a macOS SDK, and their terms prohibit commercial and multi-source use. So it seems like that possibility is going to remain closed to me. Finally, I added Plex and Jellyfin integrations, because once I had a system that could support multiple sources, I figured why not add some more that people might be interested in. Since I got laid off last year, I’ve been working on this full time, just by myself. I think it’s in pretty good shape for release, but I really need some more eyes on it, since we all know that devs aren’t good at testing their own code (as much as I try). I’d also love to get some more general feedback from others; I made this all to my own taste, but people’s music listening habits vary widely. I’m sure I’ll never be able to make everyone happy, but I’m open to considering just about anything. So, let me know! And thanks for taking a look. -dmd https://radiccio.music September 11, 2025 at 11:09PM

Show HN: Asxiv.org – Ask ArXiv papers questions through chat https://ift.tt/Ua0GOJk

Show HN: Asxiv.org – Ask ArXiv papers questions through chat https://asxiv.org/ September 11, 2025 at 10:06PM

Show HN: Haystack – Review pull requests like you wrote them yourself https://ift.tt/Iuik3v2

Show HN: Haystack – Review pull requests like you wrote them yourself Hi HN! We’re Akshay and Jake. We put together a tool called Haystack to make pull requests straightforward to read. What Haystack does: -- Builds a clear narrative. Changes in Haystack aren’t just arranged as unordered diffs. Instead, they unfold in a logical order, each paired with an explanation in plain, precise language -- Focuses attention where it counts. Routine plumbing and refactors are put into skimmable sections so you can spend your time on design and correctness -- Provides full cross-file context. Every new or changed function/variable is traced across the codebase, showing how it’s used beyond the immediate diff Here’s a quick demo: https://youtu.be/w5Lq5wBUS-I If you’d like to give it a spin, head over to haystackeditor.com/review! We set up some demo PRs that you should be able to understand and review even if you’ve never seen the repos before! We used to work at big companies, where reviewing non-trivial pull requests felt like reading a book with its pages out of order. We would jump and scroll between files, trying to piece together the author’s intent before we could even start reviewing. And, as authors, we would spend time to restructure our own commits just to make them readable. AI has made this even trickier. Today it’s not uncommon for a pull request to contain code the author doesn’t fully understand themselves! So, we built Haystack to help reviewers spend less time untangling code and more time giving meaningful feedback. We would love to hear about whether it gets the job done for you! How we got here: Haystack began as (yet another) VS Code fork where we experimented with visualizing code changes on a canvas. At first, it was a neat way to show how pieces of code worked together. But customers started laying out their entire codebase just to make sense of it. That’s when we realized the deeper problem: understanding a codebase is hard, and engineers need better ways to quickly understand unfamiliar code. As we kept building, another insight emerged: with AI woven into workflows, engineers don’t always need to master every corner of a codebase to ship features. But in code review, deep and continuous context still matters, especially to separate what’s important to review from plumbing and follow-on changes. So we pivoted. We took what we’d learned and worked closely with engineers to refine the idea. We started with simple code analysis (using language servers, tree-sitter, etc.) to show how changes relate. Then we added AI to explain and organize those changes and to trace how data moves through a pull request. Finally, we fused the two by empowering AI agents to use static analyses. Step by step, that became the Haystack we’re showing today. We’d love to hear your thoughts, feedback, or suggestions! https://ift.tt/R63VjC1 September 11, 2025 at 01:21AM

Show HN: WorldView – Compare how different countries report the same news https://ift.tt/yU5AxGL

Show HN: WorldView – Compare how different countries report the same news https://worldview.up.railway.app/ September 11, 2025 at 01:17AM

Show HN: Strange Attractors – a maths side-project in Threejs https://ift.tt/0KNmQAH

Show HN: Strange Attractors – a maths side-project in Threejs I went down the rabbit hole on a side project and ended up building this: [Strange Attractors]( https://ift.tt/OJ2MGCv ). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to 3D, not sure if it’s mathematically correct, but it’s the coolest by far. I have left all the params configurable, so give it a try. I called it Simone (Maybe). If you like math-art experiments, check it out. Would love feedback, especially from folks who know more about the math side. https://ift.tt/OJ2MGCv September 11, 2025 at 12:57AM

Show HN: An Open Source XR(AR/VR) Operating System https://ift.tt/nyevCM5

Show HN: An Open Source XR(AR/VR) Operating System We're two college students building an XR(AR/VR) native Operating System with a custom kernel. We're also Open Source so feel free to check our GitHub Repository- https://ift.tt/bP81zIT . The journey hasn't exactly been easy, we've been criticized by a lot saying that whatever we're doing is impractical and that we're too ambitious. Regardless, we've been committed to reach our goal. Here to answer all questions and doubts. Answering one question beforehand because we know someone is going to ask it - Q: Why use your own kernel/ Why don't you use Linux/ Why are you trying to reinvent the wheel? A: Using our own kernel helps us get rid of the baggage of legacy codes, bring the most optimal performance on our target hardware (XR/AR/VR) and achieve more efficiency than what we would've achieved on an existing kernel. We're not trying to reinvent the wheel, but just building Formula One racing tyres for it. https://ift.tt/AIMbFm2 September 7, 2025 at 06:09PM

Show HN: Paper's Heat Map Shader https://ift.tt/MOG6Yho

Show HN: Paper's Heat Map Shader Paper is a new design tool. We launched into open alpha today. Anyone can now sign up and use Paper. We started Paper about 1 year ago with the goal to bring more creativity back into design tools. It feels like the existing options are becoming increasingly corporate. To celebrate to launch, we published a new shader that lets anyone see their logo in Apple's new heat map animation style. There is no sign-up needed at heat.paper.design. We're always looking for feedback from anyone who uses Sketch, Figma, Photoshop, or Illustrator, about what they most need in their professional design tools. Have fun with the new shader and please send me anything you make! https://ift.tt/Jy8XhfF September 10, 2025 at 01:03AM

Show HN: Atsphinx-qrcode – Sphinx extension to generate QR code in document https://ift.tt/PJL2quM

Show HN: Atsphinx-qrcode – Sphinx extension to generate QR code in document Document is here: https://atsphinx.github.io/qrcode/ https://ift.tt/wWCxEev September 10, 2025 at 12:42AM

Show HN: DevOps Alchemy – Little Alchemy with DevOps Elements https://ift.tt/L2XSs5Z

Show HN: DevOps Alchemy – Little Alchemy with DevOps Elements https://devops-alchemy.vercel.app September 9, 2025 at 11:35PM

Show HN: C++ Compiler Support Page https://ift.tt/GzwZECK

Show HN: C++ Compiler Support Page Hi HN, I have created a webpage that displays all C++ features since C++20 in a simple, searchable table. It is intended to serve as a quick reference for C++ developers, whether as support for cross-platform development or simply to track the current support status out of curiosity. I created it as a simpler, more structured, and more up-to-date alternative to the cppreference compiler support site. Please note that the page intentionally does not list LWG and CWG papers. This might change as I am continually updating the site and trying out new ideas. Questions, feedback and suggestions are appreciated, either here or in the form of GitHub issues. https://cppstat.dev September 8, 2025 at 02:12PM

Show HN: Gemini connected to 18 native iOS tools and shortcuts https://ift.tt/iZExvB7

Show HN: Gemini connected to 18 native iOS tools and shortcuts I built an iOS voice assistant that connects your action button to Gemini Live with 18 native iOS tools like location, calendar, and so on. It also connects to any shortcuts you have on your phone. Totally free, no account, no setup. https://saturn-live.app September 9, 2025 at 12:14AM

Show HN: I made a simple ASCII-art analog clock in Emacs https://ift.tt/4IxmOUs

Show HN: I made a simple ASCII-art analog clock in Emacs Just a toy, showing how easy it is to leverage built-in Emacs features (most notably Artist mode, which provides a set of functions for creating ASCII-art vector graphics) and things like trigonometric functions and timers to create something nice. A short blog post mentioning some background (and showing a screenshot): https://ift.tt/9H8YtF3 . https://ift.tt/o3wrcNp September 9, 2025 at 01:18AM

Show HN: rm-safely – A shell alias that moves files to trash instead of deleting https://ift.tt/8gkm0AT

Show HN: rm-safely – A shell alias that moves files to trash instead of deleting I made rm-safely, a simple shell wrapper that moves files to trash instead of permanently deleting them. It prevents accidental deletions from autocomplete mishaps or hasty rm -rf commands. Should work as a drop-in replacement for rm but safer. Would appreciate any feedback! https://ift.tt/pcvuBkw September 4, 2025 at 02:08PM

Show HN: A livestream of all image descriptions (alt text) on Bluesky https://ift.tt/QUVrH4T

Show HN: A livestream of all image descriptions (alt text) on Bluesky In 2019, an academic paper by Gleason et al. found that only 0.1% of Twitter image posts had any form of image description (alt text) [1]. I wanted to see the analogous number for Bluesky today - my full blog post is here [2], but I found looking at the live stream was illuminating and fun too: * Bluesky image posts are frequent enough to keep moving, but not so frequent that it's an unreadable blur. * There's lots of bot content for things like ADS-B feeds (planes nearby), radio station "Now playing", and good old-fashioned affiliate link spam. * There is a lot of detailed descriptions for sexual content. This was a surprise to me! [1] https://ift.tt/kgVo7X5 [2] https://ift.tt/l8khojn https://bobbiec.github.io/bluesky-alt-text.html September 8, 2025 at 12:29AM

Show HN: GitType – A typing game that uses your own Git repo as practice text https://ift.tt/FNBKzQP

Show HN: GitType – A typing game that uses your own Git repo as practice text I built a small Rust CLI game called GitType. It’s a typing practice tool that takes your own Git repository and turns the code inside into typing material. Instead of random words, you type through real functions, comments, and code you’ve written — making practice feel closer to real-world programming. Features: - Works directly in the terminal (no GUI required) - Pulls text from any local Git repo - Tracks WPM and accuracy - Keeps a history of your past runs (so you can see progress over time) - Fun ranking titles based on your score Source and install instructions: https://ift.tt/8dRMnTA Would love feedback from fellow devs — especially around the scoring system and ideas for new modes. :) https://ift.tt/8dRMnTA September 7, 2025 at 11:04PM

Show HN: 60-Second Linux Analysis, Supercharged with Nix and LLMs https://ift.tt/onyBUMC

Show HN: 60-Second Linux Analysis, Supercharged with Nix and LLMs Hello HN, I'm sharing a little open-source utility I wrote recently. I'm a huge fan of Brendan Gregg's "BPF Performance Tools" book. However, every time I SSH into a fresh server, most of the diagnostic tools aren't installed there and installing them can be really annoying. I decided to use Nix package manager and LLMs to make this process straightforward. My utility first downloads a "toolbox" of Linux utilities (built with Nix), runs Brendan Gregg's famous "60-second Linux analysis" playbook and then summarizes the results with an LLM. So "60-second Linux analysis" now becomes a single one-line command and actually takes less than 60 seconds! The utility can execute all commands in parallel and the LLM can analyze them faster than a human would. I have a few ideas for the future, for example implementing more powerful playbooks - thanks to Nix I can easily bundle all tools I need and LLMs have no trouble analyzing outputs of tens of commands. I'd love to get your feedback and hear any ideas you have. Thanks for checking it out. You can launch the utility with this command: $ curl -fsSL https://ift.tt/E73j1XY | sh https://ift.tt/jmtXr5R September 6, 2025 at 10:53PM

Show HN: Dumb Site to Rate Horses https://ift.tt/IH583fT

Show HN: Dumb Site to Rate Horses I wanted a project to learn the Dioxus framework. It needed to be relatively simple and fun. Here is a site that lets you rate horses. The horse people I know have taken issue with this site because they say all horses are beautiful. What do you think? Images are from an open source AI training dataset of horses, so there are some odd ones in there... https://hhn.bustin.tech September 7, 2025 at 12:32AM

Show HN: I built a public and open llms.txt endpoint for every domain https://ift.tt/AylxtH5

Show HN: I built a public and open llms.txt endpoint for every domain And yes, I know, literally no AI uses llms.txt right now. But hear me out: if you want it just in case, or if you would like to add your sites to some llms.txt directories, you can use this endpoint. That way, you do not need to keep updating your own llms.txt, especially as I improve the API. Here is how it works: Enter any domain: https://get.llms.page/{example.com}/llms.txt The API will parse your homepage (if allowed in robots). Using internal links, descriptions, and other metadata, it will generate an Markdown llms.txt file. It does not rely on AI, because I want it to be fast and free. The API is open, free, runs on a CDN, and is powered by Cloudflare Workers for speed. I plan to open source the no-AI llms.txt generator later, since there is still a lot to improve. If you want to try it out or see some usage examples, visit: https://llms.page Let me know what you think! https://llms.page/ September 6, 2025 at 03:15AM

Show HN: Open-sourcing our text-to-CAD app https://ift.tt/TdKo4Jp

Show HN: Open-sourcing our text-to-CAD app Hey HN! I'm Zach from Adam ( https://adam.new/ ). We’re building an AI co-pilot for mechanical CAD software. As part of our broader research, we built a browser-based Text-to-CAD app ( https://ift.tt/yLu8oYx ) and are now open sourcing it. This is a React SPA with a Supabase backend. What it does: * Generates parametric 3D models from natural language descriptions, with support for both text prompts and image references * Outputs OpenSCAD code with automatically extracted parameters that surface as interactive sliders for instant dimension tweaking * Exports as .STL or .SCAD Under the hood: * Separate agents for conversation and code generation; simple parameter tweaks bypass AI entirely using deterministic regex-based updates * Runs fully in-browser by compiling OpenSCAD to WebAssembly and integrating Three.js with React Three Fiber for 3D rendering * Supports BOSL, BOSL2, MCAD libraries and custom font support (Geist) for text in models We’ve seen many developers trying to replicate this kind of functionality, so we’re releasing this to give the community a solid foundation to build on. Future improvements: * Expand geometry support - Move beyond CSG primitives to support curved surfaces, fillets, lofts, and constraint-driven modeling through CadQuery/Build123D * Better spatial context - UI for face/edge selection and viewport image integration to give LLMs spatial understanding * Enhanced capabilities - RAG on documentation and integration with more OpenSCAD libraries for features like proper threading You can clone the repo and run it locally! Contributions are welcome, and we’ll keep merging PRs as they come in. https://ift.tt/17SvV9O September 6, 2025 at 12:09AM

Show HN: File-based ticket management with Git-like commands https://ift.tt/sIt5JYp

Show HN: File-based ticket management with Git-like commands https://ift.tt/petmV5y September 5, 2025 at 11:31PM

Show HN: Swimming in Tech Debt https://ift.tt/c3PR8r2

Show HN: Swimming in Tech Debt This is the first half of my book, “Swimming in Tech Debt”. It is available at a pre-launch sale price of $0.99 ( https://ift.tt/QhKrYPn ). I have been working on it since January 2024. It is based on some posts in my blog, but expands on my ideas quite a bit. In September 2024, excerpts appeared in Gergely Orosz’s Pragmatic Engineer newsletter, which helped me get a lot of feedback that expanded the book from my initial idea. This half is about what I expected to do before that —- the rest of the book goes into team and CTO practices. https://ift.tt/qgXEjl3 September 5, 2025 at 12:33PM

Show HN: A small browser game (PC only) built with Phaser 3 https://ift.tt/yG3YEH9

Show HN: A small browser game (PC only) built with Phaser 3 Hi HN! This is my first game — something I’ve always wanted to do. It’s a small browser game built with Phaser 3, React, and the phaser template ( https://ift.tt/aE6pwfK ). I made it in 2 days (like 8 hours in total real time) using gemini-cli. About 90% of the code was generated with AI, but I learned a lot by making fine tweaks. It only works on PC since it’s a typical WASD + R (reload) shooter. I’d love feedback on: - Gameplay (is it fun, too hard?) - Ideas for new features Thanks in advance! ps: I used cubes as a prototype, but now I kind of like them. Should I keep them or implement proper sprites? https://cubic-zombies.pages.dev/ September 5, 2025 at 04:14AM

Show HN: Comfyfile - Secure, Anonymous File Sharing with Auto-Expiry No Account https://ift.tt/KB8Vpjh

Show HN: Comfyfile - Secure, Anonymous File Sharing with Auto-Expiry No Account https://comfyfile.com September 4, 2025 at 10:34PM

Show HN: Provable Safety for AI Agents https://ift.tt/kyDcKY4

Show HN: Provable Safety for AI Agents https://sentinelops.xyz/ September 5, 2025 at 02:07AM

Show HN: A vibe port of security library libinjection from C to Rust https://ift.tt/E79paZx

Show HN: A vibe port of security library libinjection from C to Rust https://ift.tt/EuopLfY September 3, 2025 at 09:58PM

Show HN: Best JSON Comparison Tool https://ift.tt/m0nQf57

Show HN: Best JSON Comparison Tool Hi All, For the lack of a clean, accurate and feature heavy json comparison tool out there. I made jsontoolbox compare tool. This is the only tool that- - does real time comparison - shows JSON path dynamically as you navigate the json - allows type/paste in, import from file or drag-drop 1/2 files in the editor to compare - lets you choose if you want sync-scroll or not - sorts both json (only)if you like to see a sorted diff - lets you swap both json - lets you download each json separately with a custom file name - works completely on client side - has no ads - has dark/light mode It is also one of the best JSON Formatter/Minifier out there :) I know there is a sea of such tools out there, but as a developer none were good enough for my use case. Please try it out and share feedback. https://ift.tt/Kthec4A September 3, 2025 at 11:54PM

Show HN: Helpme, a CLI tool to look up emergency and non emergency resources https://ift.tt/8xLfgwk

Show HN: Helpme, a CLI tool to look up emergency and non emergency resources https://ift.tt/ND24MW5 September 3, 2025 at 11:25PM

Show HN: Chibi, AI that tells you why users churn https://ift.tt/B9r8v3O

Show HN: Chibi, AI that tells you why users churn Hey HN, I’ve been a PM for 3 years, and one hard part was always understanding why users churn, drop off and behave the way they do! Session replays had the answer, but watching hours of them was painful. I chatted with a bunch of founder friends and PMs and they too had similar troubles. So I built Chibi an AI that watches replays and tells you what’s broken, confusing, or causing drop-off. Long Term: I'm thinking if Chibi could evolve into an AI product manager co-worker that can detect and prioritize issues, think through features and even run A/B tests. Tech Stack: Elixir + Phoenix, rrweb and gemini Would love to know what you think :) Happy to answer any questions too https://chibi.sh September 3, 2025 at 10:41PM

Show HN: PasteVault – An open-source, E2EE pastebin with a VS Code-like editor https://ift.tt/IqaZG5K

Show HN: PasteVault – An open-source, E2EE pastebin with a VS Code-like editor https://pastevault.dev/ September 2, 2025 at 09:40PM

Show HN: Forward Error Correction for Pion WebRTC https://ift.tt/OYe6gE9

Show HN: Forward Error Correction for Pion WebRTC We explain what Forward Error Correction (FEC) is, how and why it works in general, and how you can try it out with a new implementation in the Pion WebRTC stack. https://ift.tt/iJ6vk8j September 2, 2025 at 08:28PM

Show HN: Open-source AI writing your javadoc https://ift.tt/7e6f5M4

Show HN: Open-source AI writing your javadoc https://ift.tt/PdE3qaI September 3, 2025 at 12:55AM

Show HN: Whodunit – Solve AI written mysteries https://ift.tt/a9npslK

Show HN: Whodunit – Solve AI written mysteries Whodunit started as a pen-and-paper game for family game night. It evolved into a playable web app as the surprise reveal in a GopherCon '25 lightning talk. The mysteries are all written by LLMs. Some are better than others, but most work nicely. The web app is written in go with templ HTML templates, HTMX for on-page interactivity, and a turn-based game engine written as a Temporal workflow. Check out the mystery gen write up for more info: https://ift.tt/DBpfxT8 https://whodunit.rip September 3, 2025 at 12:13AM

Show HN: Alpha- The fine structure constant emerged and code https://ift.tt/Fd7BeWq

Show HN: Alpha- The fine structure constant emerged and code https://ift.tt/MwGhiL4 https://ift.tt/xQ2ZH4E September 2, 2025 at 12:29AM

Show HN: qdb.us is back, after extensive downtime https://ift.tt/ji9ZYOu

Show HN: qdb.us is back, after extensive downtime http://qdb.us/ September 2, 2025 at 12:26AM

Show HN: E-Paper Family 2 Day Calendar https://ift.tt/nCIw7YJ

Show HN: E-Paper Family 2 Day Calendar Hi HN, I did this project over the Labor Day weekend. My family runs off our shared Google Calendar. This project was to use a ESP32 and three-color e-ink display to create a wall-mounted daily updated calendar, weather and news dashboard for us to coordinate our lives. https://ift.tt/nuCi4j6 September 1, 2025 at 10:55PM