Show HN: Dental Scope – Interactive 3D dental anatomy https://ift.tt/dhEpx8V

Show HN: Dental Scope – Interactive 3D dental anatomy https://ift.tt/VNecL2T September 29, 2026 at 07:47AM

Show HN: WattzGOAT – an intentionally vulnerable web app for security training https://ift.tt/w8KpmH3

Show HN: WattzGOAT – an intentionally vulnerable web app for security training Built this as a hands-on lab for teaching web application security. It is a fictional electricity utility's customer portal with 48 deliberately planted flags (most of OWASP Top 10) you find and exploit CTF-style, including a simulated (rule-based, not a real model) AI assistant with its own prompt-injection-style vulnerabilities. Full disclosure, built this with AI assistance but I promise you're going to enjoy tinkering with it. https://ift.tt/Zg7ntYv September 30, 2026 at 11:31PM

Show HN: Real-time Solar System with 526k asteroids and all tracked satellites https://ift.tt/nN6gY8q

Show HN: Real-time Solar System with 526k asteroids and all tracked satellites https://space.bl2.net/ September 30, 2026 at 02:08AM

Show HN: A working 3D model of an Enigma machine https://ift.tt/vODLw2d

Show HN: A working 3D model of an Enigma machine I watched the excellent Veritasium video [1] on the Enigma machine, and watched the full animation by Jared Owen [2], but was still a bit confused on how the inner mechanics of an Enigma machine work. I used Astra to build out the inner components through a combination of reference images, writing out hundreds of extremely detailed prompts, and building my own inspection tools to ensure that every part is sized and positioned in a historically accurate way. It's still a work in progress, but would love any feedback on the experience so far! 1. https://www.youtube.com/watch?v=JsBZOcqZerk 2. https://www.youtube.com/watch?v=ybkkiGtJmkM https://enigma.design September 30, 2026 at 12:15AM

Show HN: Free browser games designed for 80-year-old eyes and hands https://ift.tt/9G2rwbI

Show HN: Free browser games designed for 80-year-old eyes and hands https://ift.tt/eYASJT3 September 29, 2026 at 10:45PM

Show HN: HN.watch – Videos of all Hacker News posts https://ift.tt/vnltNaE

Show HN: HN.watch – Videos of all Hacker News posts Hi HN, I’m Per, founder of Scrimba (YC S20). We’ve spent the last decade teaching people how to code with an HTML-based video format. We’ve now plugged an LLM into it, so that people can create explainer videos about anything. It’s called “Scrimba Explain”. To demo this technology for Hacker News, we built HN.watch. It’s like HN, but with explainer videos instead of articles. We create them on-the-fly the first time someone clicks on a link. While there are obvious visual drawbacks of using HTML instead of diffusion models, there are three big benefits: - Speed: Much faster to generate than pixel-based videos (just a few seconds from click to playback) - Cost: Our cost per video is ~$0.04. (Excluding image generation, which some videos utilize. Quickly blows up the cost) - Easy editing: the above benefits also make AI-assisted editing cheap & fast Our hypothesis is that if video creation goes from “dollars and minutes” to “cents and seconds”, a bunch of new use cases will be unlocked. Here are some we see already: - A video explanation of every single Pull Request (we do this internally) - Give every page in your internal/extrernal docs a video - Turn a complex article into a video in ~4 seconds (via our Chrome extension) - Course creators can quickly draft lessons before recording the real thing - People also create a lot of personal stuff stories for their kids, wedding invitations, birthdays, etc The stack is based on an open-source programming language (Imba) created by our CTO, Sindre Aarsæther. It compiles to JavaScript, so it interoperates fully with the npm + node ecosystem. You can learn more here: https://imba.io/ We’ve also built our own sync engine (OP), and a context management system for agents (Q). We feared this would make the LLMs struggle when writing code for us, as neither is in their training data (there’s very little Imba in there too). However, we’ve been pleasantly surprised to see that LLMs actually are really good at our stack. This is probably because the stack is extremely dense. Imba is compact, and so is OP, where a single declaration sets storage, sync, permissions, UI, and what the AI sees. This means there’s no translations between frontend, API, db and JSON where the model can get confused and get things wrong. Simply said, instead of using React.js, Express, Supabase, and LangChain, we built it all from scratch. Definitely suffering from the “not invented here” syndrome, lol! As for the models, we use Gemini, GPTs, Inworld, ElevenLabs, and a few others. If you want to try it out, just take your pick: - The Web UI (scrimba.com/explain) - MCP (add it to your coding agent) - ChatGPT Plugin - Chrome Extension You can find a link to all of the above in our docs: https://ift.tt/wSk6sza And finally, a real pixel-based video of the tool: https://www.youtube.com/watch?v=k6rbHmBxSEs Would love to hear your feedback and if anyone has ideas for other use cases. PS: I expect quite a bit of pushback from HN for this launch, given how fan of text the HN crowd is. This kind of tool is not for everyone. But there are a lot of people today who prefer videos over text, especially in the younger generations. https://hn.watch/ September 28, 2026 at 10:16PM

Show HN: I built an idle game that rewards you for doomscrolling less https://ift.tt/3vIceTO

Show HN: I built an idle game that rewards you for doomscrolling less https://getisland.app/ September 28, 2026 at 10:59PM

Show HN: Gat – Version large files with Git, without an LFS server https://ift.tt/MT4OvVw

Show HN: Gat – Version large files with Git, without an LFS server Hi HN, I built Gat because I wanted one thing from data versioning: check out an old Git commit and recover the datasets, model weights, or assets that belong to it. It's basically a lock file for large files. I’d appreciate any feedback! https://ift.tt/Wsdmutk September 28, 2026 at 12:20AM

Show HN: Lofi Cities – Pixel-art city nights with browser-generated lofi https://ift.tt/bZCluY9

Show HN: Lofi Cities – Pixel-art city nights with browser-generated lofi https://loficities.com/ September 28, 2026 at 01:44AM

Show HN: Banker – CLI for your finances using Enable Banking and SQLite https://ift.tt/k5UD0AB

Show HN: Banker – CLI for your finances using Enable Banking and SQLite Hi HN, here, what started as a small personal tool, I wanted to create an AI agent-friendly way to fetch and store financial data, like bank accounts, their respective balances and transactions and store them in a small SQLite database, to gather all of them in a single place, store them long term, and assign arbitrary metadata, for example, expense categories, etc. There are not many PSD2 compliant providers, that allow access to personal bank accounts, but Enable Banking is one of the rare few. That is why it is the core of the engine used to access the financial data from different ASPSPs. Thus, it is quite easy to register and set up a personal "application" and link your existing bank accounts to access them in the banker CLI. I hope you find it useful! https://ift.tt/WUXeKG2 September 27, 2026 at 11:32PM

Show HN: Jev predicting your life choices https://ift.tt/cfGW2oM

Show HN: Jev predicting your life choices Built a simple quiz to check whether AI (Jev) can simply learn and predict life choices. Experiment) https://quiz.seek.ws/ September 26, 2026 at 11:24PM

Show HN: Spivak's Calculus formalized in Lean 4 – every theorem, every problem https://ift.tt/alxscPK

Show HN: Spivak's Calculus formalized in Lean 4 – every theorem, every problem https://ift.tt/kx31T7Q September 27, 2026 at 12:00AM

Show HN: Jev Plays Pokémon Red https://ift.tt/6pirsvc

Show HN: Jev Plays Pokémon Red Hey HN! Wanted to share a fun project I've been hacking on. Given Jev can make decisions really fast (but not fast enough to play Doom yet sadly), I wanted to try and push it to play a more complex game than Tetris. So I went with Pokémon. I've spent endless hours playing this game as a child so building this was a ton of fun. I open sourced everything in case you want to hack on it yourself here: https://ift.tt/835SZ9t The game is being streamed live including the tokens and cost - hopefully we get all the badges and don't get stuck in a cave :) https://jev-pokemon.vercel.app/ September 25, 2026 at 09:28PM

Show HN: I couldn't deal with another Claude Code tab https://ift.tt/Kczb9LM

Show HN: I couldn't deal with another Claude Code tab https://aidash.dev/ September 26, 2026 at 01:22AM

Show HN: Doom or Bloom, map your AI worldview with Jev https://ift.tt/RI5KPGq

Show HN: Doom or Bloom, map your AI worldview with Jev Map your AI worldview by answering a few questions, and see how you compare with others. only takes a few minutes && free & open source && private by default && powered by Jev I think this is a really important question for everyone to be asking themselves, and my hope is that this lil project helps to move our conversations around AI futures in a more balanced, productive direction. https://ift.tt/0fCpJ2H September 25, 2026 at 11:51PM

Show HN: Encryption as a Service https://ift.tt/GEoBqka

Show HN: Encryption as a Service Hello, I’m looking for some criticism. I’m also looking for some people to help test this service. https://rypt.dev/ September 25, 2026 at 11:36PM

Show HN: Treepeat – Code similarity detection using Tree-sitter https://ift.tt/2F5QXT6

Show HN: Treepeat – Code similarity detection using Tree-sitter treepeat is a tool that finds similarities in your codebase. Find duplicate code blocks meaningful to the language (classes/functions), not just lines. Find near-duplicates: ignore whitespace, strings, high level AST nodes such as function and names. Find structurally similar code: anonymize identifiers, constants, etc. Pull requests welcome: This is very much an proof of concept - I'm happy with it, but I haven't supported very many languages at present. Languages supported: astro, bash, css, go, html, javascript, lua, markdown (plus codeblocks), python, sql, typescript, java, kotlin, rust, yaml https://ift.tt/QN7J6dZ September 22, 2026 at 11:53PM

Show HN: Scalar.dev – Python/SQLite server-rendered starter app, no build step https://ift.tt/kAQLRUX

Show HN: Scalar.dev – Python/SQLite server-rendered starter app, no build step Hi HN, I'm Felipe. AI-assisted coding is great, but complexity is still complexity. The more you have it, the harder it is to keep the system sane and changes safe over time. I've built this project because I wanted to have a different foundation for my apps - one that started simple, with no external dependencies, and that made the code stay easy to understand as it grows and cheap to modify. Simplicity in the stack is a means to absorb the business complexity without turning the project into an unmaintainable mess. This foundation is a Python server-rendered app (no build step, no SPA), and as a starter app it comes with some basic features that most apps will need (Authentication, AI chat, Settings, Clients/Tasks as a demo crud). The foundation is free (MIT), and there are also two paid options if you want more features. Looking forward to hear your feedback! https://getscalar.dev/ September 24, 2026 at 10:48PM

Show HN: Conway's Game of Life in boot sector https://ift.tt/2KCYLUt

Show HN: Conway's Game of Life in boot sector Hello HN! On these weekends, I was sitting and thinking about where our industry is going, and how fun it was earlier, when we wrote more code than chat messages. The thoughts quickly turned into a wish to build something like we did earlier. In my case, it ended up as something much "earlier" than I had in mind initially... So, Conway's Game of Life running from a 512-byte x86 boot sector. Maybe you will find it interesting. I tried to comment the code as much as possible, which might be especially useful if you are learning assembly. Have fun! https://ift.tt/iwl46VW September 22, 2026 at 01:28AM

Show HN: Crest – Answer Claude Code approvals from your MacBook's notch https://ift.tt/SPpHsgM

Show HN: Crest – Answer Claude Code approvals from your MacBook's notch https://ift.tt/Qvwn26N September 24, 2026 at 12:48AM

Show HN: A browser word game about composing Chinese characters https://ift.tt/O4yxqlv

Show HN: A browser word game about composing Chinese characters https://ift.tt/9ryDCKB September 23, 2026 at 10:55PM

Show HN: Matcha – fresh job postings pulled directly from company career pages https://ift.tt/GQmO5Wb

Show HN: Matcha – fresh job postings pulled directly from company career pages https://matchajobs.co/ September 22, 2026 at 06:44PM

Show HN: Vellum, the best diagram editor you'll ever use https://ift.tt/rRDmhM4

Show HN: Vellum, the best diagram editor you'll ever use I love Excalidraw, I use it all the time for work to quickly draw up a proposal for a customer. But its annoying I have to re-draw the same thing, but better in Draw.io / Visio when it comes to writing the formal documentation later. Vellum is designed to give you the speed of a whiteboard, but the architecture-diagram-finish in quality. It uses YAML to store everything, and even has a 'graph' section for those of you who like the diagram-as-code elements of mermaid... but vellum allows full authoring of layout without the restrictions of Mermaid. I love it to bits. I hope you will too. Been working on it a while, but decided to make it source available here: https://ift.tt/w8NZjYC Proud to say its not purely vibe coded slop, but I used Claude to help with some of the more challenging geometry based elements and some housekeeping stuff. https://ift.tt/3BKkfET September 21, 2026 at 11:05PM

Show HN: Distributed SQLite on Modal https://ift.tt/z8u0Mro

Show HN: Distributed SQLite on Modal https://ift.tt/oEmDzLp September 21, 2026 at 11:05PM

Show HN: Judge HN Threads with Jev https://ift.tt/qGeYbNm

Show HN: Judge HN Threads with Jev https://hnjudge.vercel.app September 21, 2026 at 10:54PM

Show HN: Swarm, an offline family tree app for macOS https://ift.tt/i17ujgZ

Show HN: Swarm, an offline family tree app for macOS Hi HN! My wife and I got deep into our family genealogy and wanted to map out all our relatives - but keep the data on our own Macs instead of uploading it to a genealogy service. Nothing we found did that, so we built Swarm, a native macOS app in Swift. It's built on GEDCOM 5.5.1, the universal genealogy file standard, so your tree exports cleanly to other ancestry apps if you ever want out. Example trees of famous historical families are included to play with. Features: multiple ancestry views (tree, fan, world map), media files, GEDCOM import/export, PDF export, tree merging, and kinship naming. Fully open source, no AI in the app, no internet connection required, no account required. Would appreciate any feedback! https://ift.tt/2TS7hrs September 20, 2026 at 11:01PM

Show HN: AI Hack Watch - timeline and dataset of hacking incidents(JSON/RSS) https://ift.tt/VMFGYKE

Show HN: AI Hack Watch - timeline and dataset of hacking incidents(JSON/RSS) https://aihackwatch.com September 20, 2026 at 10:33PM

Show HN: KillSwitch – a programming language designed to be difficult for LLMs https://ift.tt/dSmC7EP

Show HN: KillSwitch – a programming language designed to be difficult for LLMs https://ift.tt/1DO9iT5 September 20, 2026 at 02:40AM

Show HN: CUA-S1 – A System One Model for Computer Use https://ift.tt/eP14pvK

Show HN: CUA-S1 – A System One Model for Computer Use Hello HN! We're Dillon and Francesco from Cua. We were wondering how many computer use tasks actually need a full general purpose LLM (e.g. gpt-6-astra, claude-opus-5 etc.) to think through all their decisions and steps. Some tasks require thinking about a plan, exploring different paths, recovering from failure. Other tasks are a question of making local decisions, like this value should go in this box, or should I check this box, or this element should be ignored. We wondered how far we could go with a small model trained to only make these kinds of decisions. Our inspiration was Typesafe's Jev and its System One Model framing. This is a nod to the dichotomy between thinking quickly, automatically, and intuitively (system 1) vs. thinking slowly, analytically (system 2), as described by Daniel Kahneman. The interesting question for us was: what happens if you give a model an interface of current context, and a set of possible choices, and you ask it to return a probability for each choice? This kind of model does not generate output token by token like most LLMs do, but rather scores the options you give it, which you can check, trust, and use to drive your app's behavior. CUA-S1 is our answer for narrow, specialized decision models for computer use. Our first release is CUA-S1-FORMS. We built this from ideas and code in jevlike, and then trained a second model just to handle form interactions. It has 706k parameters, and the original checkpoint is 2.8 MB. The first training iteration took less than 30 minutes on synthetic data. Given a set of structured elements and values extracted from a document, it predicts whether to use the given value, CHECK, CLICK, or SKIP for each element. It does not predict new values for text fields, and does not consider screenshots. Element decisions are scored together, and your code can order the actions, and Cua Driver will execute them one at a time. A first evaluation of this specialist vs. hosted Jev on our form task: - For the whole decision set: 99.7% correct vs 83.6%. - For the subset of steps that require an action: 100% correct vs 96%. - For the subset of steps that are just leaving already-filled fields alone: 100% correct vs 74%. The specialist was trained specifically for this task and convention (just press skip for already filled boxes), while hosted Jev has not been fine-tuned for it, so this is an experiment in scoped specialization. We measured 7-9 ms to score a form locally vs. 260-280 ms per call to hosted Jev including network latency, though those samples measure different things and are not end-to-end form completion times. Our interest here is in the space between a brittle script and a general agent loop. The content and layout of form fields vary enough that scripts get unwieldy, but the set of available decisions can remain narrow and well scoped. We want to explore the possibility of a general agent encountering something novel, and passing well understood decisions over to specialists like this. That is a direction we are looking into. The current release is for forms only. We're open sourced the synthetic data generation, training, evaluation, and Driver integration under libs/cua-s1 with an MIT license. Comments welcome! Especially if you are building computer-use agents and have run into a recurring decision that is too variable to script but is too narrow to call another LLM for. https://ift.tt/SdDUK5P September 19, 2026 at 10:52PM

Show HN: BreachScanner – Check if your email has been in data breaches https://ift.tt/0pXyeiJ

Show HN: BreachScanner – Check if your email has been in data breaches https://ift.tt/2JKb9rP September 20, 2026 at 12:30AM

Show HN: Learn divergently/chaotically with tree-learn https://ift.tt/rQm0tUn

Show HN: Learn divergently/chaotically with tree-learn Chat interface is linear, I never quite liked that for when I would have too many questions, I would end up asking questions in a numbered list and not really have independent branches of conversation. On cli, the pi agent gives you this same functionality. On web, I made Fable make this. BYOK Openrouter - all client side - you can check the network console! https://ift.tt/rTy7dm6 https://tree-learn.srijanshukla18.workers.dev September 18, 2026 at 11:21PM

Show HN: Jev helps you to not run malicous code https://ift.tt/qby5It2

Show HN: Jev helps you to not run malicous code https://ift.tt/hTRxrdK September 18, 2026 at 11:44PM

Show HN: App Launch: GrabThat (NLP Launcher for Windows) https://ift.tt/50NSBvc

Show HN: App Launch: GrabThat (NLP Launcher for Windows) https://grabthat.ai/ September 18, 2026 at 11:15PM

Show HN: Dishlist – my favorite things on the menu https://ift.tt/voWbaQw

Show HN: Dishlist – my favorite things on the menu Hi HN! My friend and I wanted to rank our favorite breakfast burritos. Yelp and Beli allow users to rate or rank restaurants, but not individual dishes. So I built dishlist, an iPhone app around the things on restaurant menus. I schlepped around Dogpatch, Potrero Hill, and Mission Bay taking photos of restaurant menus. Then, I used Claude with my menu schema to turn the photos into structured data. Garry Tan likes to say, "The rocks can talk." Also, "The rocks can see." I represent the menu hierarchy in the database. LLMs can determine what type of thing each menu item is. This lets me index things like breakfast burritos across restaurants rather than just indexing the restaurants themselves. The app suggests possible tags for a menu item. You decide which ones you want to use on your profile. You can build a list of your favorite breakfast burritos, pizzas, burgers, or whatever else you care about. I value my privacy, so you can use the app without logging in at all. If you want to save menu items, you can sign in with Apple. I don't collect names, emails, or phone numbers. If you want to share with friends, you can add a handle. You have to follow another user to see their dishlist, and they have to follow you to see yours. Follow requests are approved or denied by the user. The app is currently available through TestFlight while the App Store submission is being reviewed. https://ift.tt/HzJgIRE I'd love feedback on the idea, the search experience, and especially whether organizing things around individual menu items feels useful. https://ift.tt/HzJgIRE September 17, 2026 at 11:53PM

Show HN: Content-aware PII redaction with Jev in Postgres https://ift.tt/2JiUTG1

Show HN: Content-aware PII redaction with Jev in Postgres https://pg-redact.vercel.app September 17, 2026 at 11:52PM

Show HN: Aclif – Agent CLI framework: one grammar, canonical names across SaaS https://ift.tt/5xh8t60

Show HN: Aclif – Agent CLI framework: one grammar, canonical names across SaaS Simple discovery of the provider's default schemas is possible without any credentials (since they are built into the binary). If you want it to fetch customizations of your specific instance, give it credentials to your org. The repo has more details. https://ift.tt/itPushb https://www.aclif.ai/ September 17, 2026 at 11:48PM

Show HN: Die With Me – Claude and Codex rate limits as AIM away messages https://ift.tt/qSz9sKa

Show HN: Die With Me – Claude and Codex rate limits as AIM away messages made this AIM buddy list but for our token usage because i wanted to bring a little bit of the old internet back! i remember those days where i'd casually check if friends are online and find excuses to say hi and poke them give it a try! i'd greatly appreciate feedback https://ift.tt/Z3Xgja6 September 17, 2026 at 11:25PM

Show HN: Restarted – a 2026 remake of the classic 2015 startup generator https://ift.tt/x5QKkvS

Show HN: Restarted – a 2026 remake of the classic 2015 startup generator The original startup website generator by Tiff Zhang and Mike Bradley landed on Hacker News in April 2015 ( https://ift.tt/7SlXmrD ) and has been one of my favorite little novelties of that era ever since. It perfectly captures the saturated colors, cliché hero shots, gimmicky names, buzzword-heavy slogans, and proudly hirsute team photos of the time. A lot has changed since then, so I thought it would be fun to make a contemporary remake: https://restarted.io/ By default you get the minimalist aesthetic and clean-cut faces of 2026. The classic 2015 look is still available — just click the link at the bottom of the page or change the “z” parameter in the URL to the more familiar “s”. The universe of partner sites and competing startups is just as expansive as it ever was. The original site is entirely client-side and requires downloading all of the data tables locally. It leans on a mix of jQuery 1.11.2, Bootstrap 3.3.2, and Font Awesome 4.3.0, and if you view the source, it instantly gives away all of its secrets. For restarted.io I replaced all of that with a server-side renderer written in Go, so this time view-source tells you nothing. There are many Easter eggs in there — see how many you can find before I write them up. My original goal was to stay faithful to the 2015 appearance, and that turned out to be a technical adventure. The original's sine-based random number generator is... the worst, and different implementations of sine give different results. The eventual solution was to extract the exact sine function from Chrome’s V8 engine, as vendored C behind cgo and as a line-by-line Go port that keeps cgo optional, so the seeds and results line up the way they used to. Both are checked against V8’s own test cases. Then I discovered a bug in the original code that made half of its vocabulary unreachable — the first half of the verb table and the second half of the noun table, exactly complementary, so nothing about the output ever looked truncated. My goal then shifted from remaking the generator as it was in 2015 to remaking the site as the authors intended it to be in 2015. Over the years several people asked for their photos to be removed, so the remake instead draws from a broad pool of era-appropriate AI-generated profiles. A perceptual hash helps keep everyone looking distinct, and there’s a bit of extra care to make sure the Wang Fangs of the world don’t appear as Irish lasses. The hero image pool is much larger now, and all the old Rio de Janeiro shots have been retired, though you’ll still recognize plenty of the 2015 photos. Have fun poking around! https://restarted.io/ September 15, 2026 at 06:34PM

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://ift.tt/vuTdE6k

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://mateovalle.github.io/pixel-agents/ September 17, 2026 at 12:12AM

Show HN: YOLO FPS-per-dollar numbers for edge AI boards ($75-$215) https://ift.tt/JZLlxf9

Show HN: YOLO FPS-per-dollar numbers for edge AI boards ($75-$215) https://ift.tt/JaGBv5k September 16, 2026 at 11:20PM

Show HN: TrailVid – Cinematic Travel Animations https://ift.tt/fKPsbjO

Show HN: TrailVid – Cinematic Travel Animations I originally started with this project because my partner wanted a way to make visually clean travel videos for her social media. The ones that existed felt a bit too expensive for the quality they delivered, and many of them leaned heavily on a cartoonish visual style. So I decided I'll build an app for her that fits her needs, and over the last few months it has become bigger and better. I've even created my own map tiles because licensing existing ones was not cost effective. Now it's finally open for public beta and I'd love to get some feedback before I bring this to the App Store. https://trailvid.com/ September 16, 2026 at 12:01AM

Show HN: The bottom 50% of U.S. households are short after essentials (BLS data) https://ift.tt/bQGy6Hj

Show HN: The bottom 50% of U.S. households are short after essentials (BLS data) https://whats-left-over.pages.dev/#s=50_40_10&c=1&u=person&t=0&tm=cbo&b=0&ts=100&k=0&cc=12201&im=nominal&by=2000&ir=2.5&ao=0&ar=20&at=200000&ip=10&rm=sp500&rr=8&pv=portfolio&p=1&iv=left&hp=1&e=food.housing.transport.health.insurance September 15, 2026 at 10:24PM

Show HN: Neobrutalism.dev – just added Base UI support and added new color theme https://ift.tt/Qus81gi

Show HN: Neobrutalism.dev – just added Base UI support and added new color theme https://ift.tt/9VBFutT September 14, 2026 at 11:02PM

Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain https://ift.tt/FbAipye

Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain For my solo food pilgrimage to the Basque Country, I pre-arranged flights in/out of Bilbao, Guggenheim Museum tickets, Michelin Guide restaurant reservations, bus tickets to San Sebastian and Saint-Jean-de-Luz, walking food tours and hotel reservations in each city, and a long list of pintxo spots to hit with notes on each one's food specialty. Most of this was poorly organized (manually) in my phone's Notes app, with references to specific emails for more information. I arrived on the first day in Bilbao, and the hotel didn't have me in their system by name, so I spent a good 10 minutes frantically scouring my emails for the confirmation number, cursing myself for holding up the people behind me. Over the course of the next few days, while I was relaxing at my hotel (after finally getting in) in between pre-planned stops, I started building a personal tool that would organize all of my bookings automatically and keep all relevant information at my fingertips. Thus, Petrel was born and named after one of my favorite birds. It started as a personal pet project but I shared it with some friends that were looking for something just like it so I ended up turning it into an app and website for all to benefit. It's completely free to try without even signing up. On my next group trip, I built out logical collaboration features to allow groups to vote, split expenses, share notes, and add pictures all within the same ecosystem. I've slowly improved the parsing and itinerary logic and built in convenient features such as weather, estimated travel times, an encryption-protected area to store copies of personal information, and a comprehensive travel log with fun stats. I also made it so that the parsing tool can accept almost any file type. However, the tool doesn't do anything to assist on the planning side and doesn't provide true flight alert pushes, despite having live flight status syncing. I would love for more people to test it out, challenge the parser, and let me know their thoughts and experience. https://ift.tt/12Gm0xy September 14, 2026 at 04:47AM

Show HN: VibeWorld – a shared terminal world for developers and scientists https://ift.tt/Z0hxksF

Show HN: VibeWorld – a shared terminal world for developers and scientists Vibeworld is a persistent cyberpunk shared world that runs in your terminal, where you can meet other developers and scientists to have company at 2 AM while screaming at your LLM :) you can connect with other scientist, chat, and includes also use vocal chat if you want to use it. There is a world and a moon, and they are completely 3D rendered and animated. In the moon there is the "complaint crater": a place where you can scream an insult against your claude or codex session and everybody from the space can see it. You can create your pixel avatar! There is also the "stargazing ledge": a place where you can see the stars and whatever happens in the sky. You can chat in the meantime if someone else is there too, or just watch our Earth. Sometimes you can see galactic wars, and there is a plant that grows but dies if nobody waters it. You can leave it on the second monitor while working (it does not use a lot of RAM): watch the sky when you want, and sometimes you may chat with some other scientist in your same situation. In the world, continents are scientific macroareas, and cities are specializations: you can create your corners where you can speak and help others (but for now it is quite empty). You can install in one command and by just typing "vibeworld" in your terminal, you are inside the world. There are some games inside and a sort of Doom where enemies says to you "Retracted" or "dedline tomorrow" when shooting you :). There is also an awkward reason why I am posting the work here. I have just discovered that another product Vibeworld.build uses the same name and the same concept (shared multiplayer world for developers). I don't know how independently it was developed. It is not a TUI, but it is a full, paid application developed by a company after my project was released. To be honest luckly I find my project more funny. I do care about preserving the chronology, my VibeWorld was released before, and there are verifiable timestamps in the GitHub. I just don't want the original public record to disappear if a much larger implementation of a very similar concept gets more attention later. I would like to hear what people think about it! :)) https://ift.tt/uW6Zh8D September 14, 2026 at 03:00AM

Show HN: Kibble – a reader for AI news, tutorials, code and models https://ift.tt/CyYu7Ic

Show HN: Kibble – a reader for AI news, tutorials, code and models https://ift.tt/IXLPi76 September 14, 2026 at 02:39AM

Show HN: Simpleboot and Easyboot https://ift.tt/TlUR4G0

Show HN: Simpleboot and Easyboot These are FLOSS boot loaders and disk utilities which follow the suckless philosophy ( https://ift.tt/Jgfikas ). Despite being totally dependency-free, they come with a fully featured single command to create bootable disk images out of a directory (utility is available on Windows, Linux and other POSIX systems). Usage is as simple as it gets. There are two repositories, depending on the desired use case: Simpleboot is the little brother, an embeddable boot loader: https://ift.tt/NRFmngY - multiplatform (BIOS, UEFI, RPi, coreboot) - very small (less than 64k), single binary - also flashable into ROM (option ROM, expansion ROM, coreboot payload, etc.) - easy to configure (single config file, checked for validity by the disk creator utility) - one backup boot option - capable to boot Linux and simplified Multiboot2 kernels (see below) Easyboot is the big brother, an interactive boot manager: https://ift.tt/MV0vFib - multiplatform (BIOS, UEFI, RPi) - interactive boot menu for dual booting multiple OSes - easy to configure (similar syntax as GRUB's, but much simpler) - up to 9 boot options - transparent payload decompression - on-the-fly, transparent DSDT and DTB patching - plugin system to support multiple file systems and boot protocols - supports FAT12/16/32, exFAT, NTFS (v3, v3.1), ext2/3/4, XFS (SGI), UFS (v2, v4.4), mfs (Minix3), BeFS (Haiku), plus any root file system (zfs, btrfs, etc.) provided the kernel is on the ESP - supports booting Linux, Windows, OpenBSD, FreeBSD, FreeDOS, ReactOS, MenuetOS, KolibriOS, SerenityOS, Haiku, Multiboot1, Multiboot2 (in PE/COFF, ELF, a.out, etc. formats) - comes with a (very minimal but useful) kernel debugger that works on real machines too Full disclosure: forking Simpleboot into Easyboot was sponsored by The Free Software Foundation Hungary ( https://fsf.hu/nevjegy ), created in appliance of FSF.hu's Free Software Tender 2023. Their default "simplified Multiboot2 protocol" is an easier to use superset of the GRUB's Multiboot2 protocol. This protocol handles native 64 bit kernels (no 32-bit trampoline code), programming language and ABI agnostic (works with native C, C++, Rust, Go, Ada, Pascal, etc. kernels, no Assembly preambule needed), supports transparent higher-half mapping, not tied to x86, and has SMP support too (running the kernel on all CPU cores), passes EDID and kernel segmentation information (not in GRUB), etc. etc. etc. An example kernel is provided in the repo: https://ift.tt/CXP94fc If needed, there's an Easyboot plugin to support the old-fashioned, x86-only, GRUB-compatible Multiboot2 protocol (embedded tags, 32-bit entry point, no higher-half, GRUB ABI). Documentation and detailed specification is available in German, English, Spanish, French, Hungarian, Italian, Japanese, Dutch, Polish, Portuguese, Russian and Chinese (some machine translated, sorry). I would really love to hear your opinion and constructive criticism. Simpleboot is feature complete (only bugfix allowed), but Easyboot is expandable with new features via plugins. https://ift.tt/MV0vFib September 13, 2026 at 10:48PM

Show HN: Dry Diving Club – A darkly comic browser game https://ift.tt/oklzuHF

Show HN: Dry Diving Club – A darkly comic browser game https://drydiving.club/ September 12, 2026 at 10:48PM

Show HN: Bodily Oddities https://ift.tt/Kxhk08L

Show HN: Bodily Oddities When I was about 11 years old, my best friend and I were playing during recess at school, and I was carrying him around on my back, presumably pretending to be a multipart attack robot. All of a sudden, my heart started hurting, and I collapsed to my knees, and the robot was no more. Every time I inhaled, it would feel like a spike was being driven into my heart, and my breathing got completely shallow. I was sure I was done for, when all of a sudden, after an exhale, it disappeared. It wasn't until I was in my twenties that I learned this was called Precordial catch syndrome and it happens to most everyone. Every friend I've told about it was surprised, and also most knew the feeling. I collected a growing list of strange things bodies do ever since. And now finally I made it into a little page for others to see: https://ift.tt/qplfbaU It includes a form to tell me about new things, if you think they belong on the page. Feedback welcome! https://ift.tt/qplfbaU September 11, 2026 at 03:33AM

Show HN: Raggy – A lightweight CLI tool for RAG over local documents https://ift.tt/dr2HbLt

Show HN: Raggy – A lightweight CLI tool for RAG over local documents https://ift.tt/2ImnVXB September 11, 2026 at 11:01PM

Show HN: I built an AI 'Fog of War' for life goals https://ift.tt/mId5FMc

Show HN: I built an AI 'Fog of War' for life goals https://ift.tt/TrXCNQD September 10, 2026 at 11:19PM

Show HN: Pascal's Pager – Webhooks In. Push Notifications Out https://ift.tt/c6uj1WS

Show HN: Pascal's Pager – Webhooks In. Push Notifications Out Sometimes it just takes too long to parse a webhook from one service to another just so you can get a push notification on your iPhone. Pascal's Pager turns any JSON webhook data into a human readable push notification on your iPhone using AI. It includes notification grouping and data redaction so you can select to exclude specific values from ever going to the AI. https://ift.tt/74q3eX6 September 10, 2026 at 11:03PM

Show HN: Mushrooms – A personal MCP server for 2,500 apps, so your AI can act https://ift.tt/3iewaYd

Show HN: Mushrooms – A personal MCP server for 2,500 apps, so your AI can act https://ift.tt/1xyMBgz September 9, 2026 at 11:13PM

Show HN: Moral.games, a 1v1 ethics game with an AI judge https://ift.tt/mKN0J8p

Show HN: Moral.games, a 1v1 ethics game with an AI judge https://moral.games September 9, 2026 at 11:08PM

Show HN: Locksmith: Store Maven Secrets in the macOS Keychain (Or a Unix Socket) https://ift.tt/o4kWQDf

Show HN: Locksmith: Store Maven Secrets in the macOS Keychain (Or a Unix Socket) Hello HN, In the age of LLMs sucking in random secrets, sandbox escapes, and RCE orbital bombardment, I thought it'd be a good idea to create a Maven Extension that defers to the MacOS keychain for resolving secrets. In general, it's a good idea to not have any secrets (passwords, tokens, etc) stored in plaintext files. Also, this allows your machines to be FIPS-140 complaint, if thats a thing for your job. Locksmith is a Maven Core Extension that defers to the MacOS Keychain. The entry format in settings.xml looks like: `{[type=locksmith]nexus.superbiz.example.com/username}` This was a fun project and I used the Project Panama FFM with jextract for the first time. The FFM is a great iteration on JNI (which still has it's place) and was pretty much brainless to use. Setup is quick and easy and I tried to make the readme as friendly as possible. As an aside, I've also architected the core Library indecently from the Maven bits, so if you do need to read from the MacOS keychain in a project, you could pull the core Library in without dragging in Maven. Being 2026, of course Claude was used to assist in the creation of the project, however Locksmith is not vibecoded top-to-bottom. I personally loathe AI slop. I use LLMs as a tool, not a crutch. Enjoy! https://ift.tt/f6kuCai September 9, 2026 at 11:01PM

Show HN: Give your AI agent on-screen guides that show users where to click https://ift.tt/Ld1VEYm

Show HN: Give your AI agent on-screen guides that show users where to click Hey HN. I'm Christian, one of the founders of Frigade (YC W23). I've noticed that a lot of in-app AI agents struggle to actually understand the products they exist in. For instance, let's say a user asks an agent how to do something in a given SaaS product. In an ideal case, maybe that agent replies saying it has a tool to do the task and just automates that work entirely for the user. That's a great outcome. But often that's not the case. Maybe there is no tool call for that exact task, or maybe the user's question is best solved by a specific UI workflow or interface. In these cases, many agents tend to fall back on basic RAG on their help center, or sometimes even searching the internet for an understanding of their own product. This can be a very slow process and most of the time help center articles are outdated as products evolve faster than them today. Even worse, no one likes reading a long list of bullets and mapping that back to a UI. My tool (Assist API) solves this gap with a single tool call defined like this: const frigade_guide_tool = { description: 'Call this tool to answer product questions or guide the user through a task.', parameters: { query: { type: 'string', description: 'What the user is asking or wants to do', }, }, run: ({ query }) => frigade.assist({ query }), } Here's a demo I recorded on how to set it up with the Vercel AI SDK: https://www.youtube.com/watch?v=9WQ0UbLjC6I When called, the tool will do the following: 1) Gather context on what the user is seeing on screen, their permissions, feature flags, and more. Then one of the following: 2a) If solvable: Generate an on screen guide for how to fix a given problem 2b) If conceptual: Return text describing to the parent agent how to solve the problem 2c) Reject (i.e. unable to help) How does the tool know what to do? The tool learns a given application UI by using a browser-based agent. You provide a test account to your software (i.e. staging og preview), and a browser agent logs in and works its way through the entire product. It then builds its own map of how the application works which can the be queried about any product-related question or how to get from A to B in the UI. It also writes its own documentation from this map. The agent re-runs on a schedule or can be triggered through CI/CD. Docs and more details: https://ift.tt/RIfnbZg September 9, 2026 at 10:09PM

Show HN: Bestie, a coding agent that respects you https://ift.tt/e3FoDfP

Show HN: Bestie, a coding agent that respects you hi friends! this year, i've been working on a general purpose, native terminal coding agent harness. i remember being absolutely struck the first time i ever used claude code and it could just do things. i'm also a big fan of crush and pi. it's pretty early on. i still have yet to build all the higher-level behaviors that make something go from a harness to a proper agent. it turns out, making a coding agent is incredibly hard because you have to strap a development environment to an llm. in my hubris, i had thought "oh—it's just a terminal app that calls some api's!" i'm trying to provide all the things that i think an agent should have out of the box: subagents, sandboxing, compaction, cross-platform support, a beautiful interface, etc. i would be absolutely delighted if you'd give it a go (as far as safety goes, the sandbox tends to be too restrictive rather than too lenient—i'm trying to figure it out as i go). i made bestie because i don't like it when agents do things and don't tell you what they're doing. or when the harness itself won't provide visibility into things. so bestie is architected around being able to inspect anything that happens in an inspector pane that shows you the inputs/outputs of every tool call, background job update, and shell process. https://ift.tt/chFfsvE September 8, 2026 at 10:52PM

Show HN: Gote – a CLI note-taking management tool for plain Markdown https://ift.tt/bQ42NS5

Show HN: Gote – a CLI note-taking management tool for plain Markdown Repo: https://ift.tt/VR1wI3X I built a note taking management tool to use at work for quick note taking and searching. It is intended to be quite minimal. Another focus was to have lots of shortcuts and to keep things close to the homerow for ergonomics and speed. Notes are just markdown files in whatever directory you point it at. The only thing it keeps elsewhere is an index in ~/.gote. If you stop using it you still have all your notes. Tags go on the first line of the note, separated by periods, like .project.urgent.work. No frontmatter. Search is built into the binary, BM25 with stemming, so there's no ripgrep or fzf to set up. gote s meeting searches titles and content, gote s -t .work filters by tag, gote s -w 2412 pulls up notes from December 2024. Most commands have a two letter version that combines a list with an action. ro is recent + open, sv is search + view, tp is tag + pin. When results come up you pick one with a home row key instead of arrows or numbers. Binaries for mac/linux/windows are on the releases page, or go install github.com/banorton/gote@latest if you have Go. The goal of this project was not to learn something new or build something impressive. I simply had a need and filled it with a vibe-coded solution. I have been using it for about a year now and it does more or less exactly what I wanted. So I thought I'd share in case others are interested in using it, contributing to it, or want to use it as a reference for their own solution. September 7, 2026 at 11:55PM

Show HN: Possess, a TUI to browse and transfer coding sessions https://ift.tt/lgwDbq7

Show HN: Possess, a TUI to browse and transfer coding sessions https://ift.tt/nDHcstd September 8, 2026 at 01:13AM

Show HN: Isle – managed application environments for computer-use agents https://ift.tt/bWjXEfG

Show HN: Isle – managed application environments for computer-use agents https://www.tryisle.com September 8, 2026 at 12:02AM

Show HN: Wg-admin – web UI for an existing WireGuard host https://ift.tt/XliDKUj

Show HN: Wg-admin – web UI for an existing WireGuard host Reads /etc/wireguard, lets you add/edit/remove peers, applies with wg syncconf (no interface bounce). Does not install WireGuard or rewrite your PostUp/NAT. That's all https://ift.tt/TWJGCsc September 7, 2026 at 11:43PM

Show HN: PixelDraw – simple drawing software for web(WASM) and desktop https://ift.tt/KSL3Aak

Show HN: PixelDraw – simple drawing software for web(WASM) and desktop https://ift.tt/Mdx2GCt September 6, 2026 at 10:53PM

Show HN: HexBOTs – a cellular automaton with robotic lawnmowers https://ift.tt/tRwO1CS

Show HN: HexBOTs – a cellular automaton with robotic lawnmowers Double-click or press N to start a new experiment. I built hexBOTs, an unusual cellular automaton based on deterministic robots. The robots behave a bit like robotic lawnmowers, moving through their environment and reacting according to their individual rules. The robots themselves are fully deterministic — no random functions are used while they are running. What makes them different is their “genetics”: each robot's behavior is defined by a randomly generated genome, which allows for an enormous number of different robot types. Randomness creates the robots, but it doesn't drive them. Once an experiment starts, everything follows deterministically from the generated genomes and the initial state. What fascinates me is the complexity that emerges from these relatively simple machines interacting with each other and their environment. Controls: B — enable/disable robots (also: hold mouse/finger down) R — restart N — new experiment (also: mouse/finger double-click) D — save as picture I — show information / controls https://hexbot-genesis.netlify.app/ September 7, 2026 at 02:56AM

Show HN: Merge Wikipedia articles across languages into one page https://ift.tt/n46jNpL

Show HN: Merge Wikipedia articles across languages into one page https://ift.tt/6amlvO5 September 6, 2026 at 03:48AM

Show HN: Amaze Kings – a browser logic puzzle with 1,400 hand-graded levels https://ift.tt/JWF3oqv

Show HN: Amaze Kings – a browser logic puzzle with 1,400 hand-graded levels https://ift.tt/ZHJEMqx September 5, 2026 at 11:21PM

Show HN: HyperCard to HTML Converter https://ift.tt/UeQ6gPx

Show HN: HyperCard to HTML Converter I created a converter that turns HyperCard 2.x stacks into standalone HTML so they can run in a modern browser. I built it to share my own stacks from the early '90s, which have been sitting on old floppy images for 30 years. It's MIT-licensed and I'd welcome contributions - especially stacks that break the converter, since I've only tested it against my own. If you have old HyperCard files lying around, I'd love to hear how they fare. https://ift.tt/FytiTmh September 5, 2026 at 11:11PM

Show HN: Local Mitsubishi AC Control with ESPHome and an AtomS3 Lite https://ift.tt/QmDHEbP

Show HN: Local Mitsubishi AC Control with ESPHome and an AtomS3 Lite I connected my Mitsubishi split air conditioners directly to Home Assistant over CN105 using an AtomS3 Lite and ESPHome, avoiding MELCloud entirely. https://ift.tt/gWArv1z September 5, 2026 at 12:30AM

Show HN: TERMy – A fast terminal assistant that does not use LLMs https://ift.tt/dgeyGjs

Show HN: TERMy – A fast terminal assistant that does not use LLMs I love research and development, you may have heard of me because of PJON (Padded Jittering Operative Network). It is a network protocol I started developing in 2010, which was recently implemented in silicon by the ETH Zurich university thanks to the research of Pius Sieber. I am excited to share with you TERMy, a terminal assistant built on top of the NPC-Forge framework. Unlike everything else being built today, TERMy does not use embeddings, machine-learning or LLMs. It runs on the CPU (even on a Raspberry Pi Zero) both in the terminal or client-side in a browser tab and responds in milliseconds. It is a cynical but very knowledgeable Linux terminal assistant that translates your natural language into shell commands without relying on a single artificial neuron. I had a chance to focus for 2 months on my personal projects since early July, during the strange times of AI price hikes and the end of subsidized tokenmaxing. I was curious to see if I could develop from scratch a terminal assistant capable of handling simple natural language requests. I have a bad memory and got used to ask to copilot "activate the virtual environment" or similar trivial operations spending a non negligible sum every month. I started thinking, maybe I can do something to make my workflow more efficient? Do I really need trillions of parameters to accomplish those tasks? How it Works When you type a prompt, it goes through a lightweight NLU pipeline written in ~1000 lines of Python that implement the following steps: 1. Strip expletives, interjections, encouraging, discouraging and thanking words (remove noise) 2. Sentiment analysis 3. Exact Match (very fast) 4. Template Match (slower) 5. Probabilistic Match (even slower) Step 5 relies on: 1. IDF (Inverse Document Frequency) to identify rare words. 2. BOW (Bag Of Words) to accommodate word inversions. 3. IDF weighted Levenshtein to safely handle typos. Permission gating is hardcoded into the dataset and enforced for all potentially destructive commands, so it's inherently safer than letting an unpredictable LLM run wild on your machine. - TERMy in operation: https://www.youtube.com/watch?v=qeIp0xePLBg - Variance and typo tolerance: https://www.youtube.com/watch?v=tQvGDk6fkk0 - Copilot integration: https://www.youtube.com/watch?v=Wzzouhq2a8A - Advanced features: https://www.youtube.com/watch?v=qeIp0xePLBg - Source Code: https://ift.tt/APTj98N https://ift.tt/sFZx20y September 4, 2026 at 04:03PM

Show HN: Radia – agent coordination with leases, permissions and provenance https://ift.tt/g6Qq9VO

Show HN: Radia – agent coordination with leases, permissions and provenance https://radia.sh/ September 3, 2026 at 11:59PM

Show HN: I built an app that makes your goals inevitable https://ift.tt/pbrAOja

Show HN: I built an app that makes your goals inevitable https://ift.tt/wN0KlAV September 3, 2026 at 11:55PM

Show HN: A Context Registry for AI coding agents https://ift.tt/YM3Rw6D

Show HN: A Context Registry for AI coding agents Hi HN. We built an API context registry to help coding agents (like Claude Code) generate production-ready API integration code without blowing through token limits. We build a lot of API integrations. In our experience, most coding agents write basic client calls fine, but consistently stumble on details that make code shippable, like idempotent retries, rate-limiting and Auth token management. We tried all the existing approaches of injecting context into coding sessions: - Markdown dumps delivered via MCP (think Context7 or Mintlify Docs MCP) - API behaviour described in prose using AGENTS.md and skills. - OpenAPI specs However, all of them left the same production-readiness gaps. So we came up with our own approach that combines prose with typed SDK reference code into a "Context Plugin". You install the plugin into your coding agent and it automatically injects language-specific context whenever the agent works on an API. Across our benchmarks, Context Plugins boosted one-shot production readiness by up to 34%, allowing Sonnet to match or beat baseline Opus on the same integration tasks. You can read more about our experiments here https://ift.tt/YNewklD... We have published Context Plugins for 24 APIs for the community to try out, including Slack, Google Maps, and Notion. We'd love for you to give them a go and share your feedback on our plugins as well as our evaluation methodology. https://ift.tt/PrA5nMG September 3, 2026 at 11:00PM

Show HN: Kekoso – On-device dictation and transcription for macOS https://ift.tt/pxkwd9l

Show HN: Kekoso – On-device dictation and transcription for macOS https://kekoso.app/ September 2, 2026 at 11:51PM

Show HN: Skatanica – Browse and share skate clips by location https://ift.tt/0kud52K

Show HN: Skatanica – Browse and share skate clips by location https://skatanica.com (no login or download required) I love Dern Bros skate spot history videos, and wanted to see 1.) places my favorite skaters have skated 2.) which skaters had skated my favorite places 3.) find new skaters and new places 4.) have an easy way to just watch clips 5.) have an easy place to document tricks I/people have done anywhere Some examples: 1.) Clips from Dominick Walker: https://ift.tt/reO4UIs 2.) Skaters at Santa Monica Triple Set: https://ift.tt/2PF81A5 3.) Find some spots/clips from spots in [Southern California]( https://ift.tt/nCHAPBt ) , or [Southeast Asia]( https://ift.tt/I6hXloS ) --- Contributing as a Curator: If you like this, and you want to go beyond just sharing a clip here or there, I've built a ton of curator tools specifically for quickly chopping up long videos into clips and labeling the tricks/publishing directly to platform. Message me or comment and I can give you more info/get you set up. https://ift.tt/ceu64CD September 2, 2026 at 11:33PM

Show HN: Aura – a Rust agent that investigates and fixes production incidents https://ift.tt/kZIjG7C

Show HN: Aura – a Rust agent that investigates and fixes production incidents We run a SaaS that handles petabytes of data. Our SRE team experimented with using claude, openclaw, langchain, etc. within our incident response workflows. We struggled with overflowing context, lethal trifecta vectors, hallucinations, and burned a lot of frontier tokens mostly on easy work. Approval fatigue was a challenge, and we drew a hard line at relaxing permissions in production. Long story short, we built and open-sourced AURA, a Rust-based harness specifically designed for the type of operations work which routinely involves large volumes of telemetry data and coordinated investigations across many domains of knowledge / state. We have found even on open-weights models, root cause accuracy has been very good, and remediation actions are guarded with human-in-the-loop. AURA runs from a centralized configuration file where workers are defined and scoped to task domains, (e.g. logging review, metrics analysis, and git/scm related queries). All permissions, tools access, LLM backend(s), worker prompts, and the main coordinator prompt are also defined in code. Permitted tool use is enforced deterministically outside the agent's context, so the agent cannot grant itself capabilities through prompting. AURA also handles the rest of the execution layer, such as human approval for sensitive actions and fault tolerance. A lot of thought went into context window management: large tool outputs and worker responses are persisted to disk and agents are given tools to slice/read as needed. The project is Apache 2.0. You can install rpm/deb/brew natively or pull the source and build your own. It runs either as an assistant on your workstation, or as a daemon that you can connect to via any OpenAI-compatible frontend. The GitHub repo is here: https://ift.tt/bX8Ex4U The whole thing is free/Free. No signups or open core trapdoor. Demo: We put together an 8-minute video showing a checkout outage resolved by following evidence from several different systems: https://www.youtube.com/watch?v=TERHoRzT8cE tl;dw: 502s from a checkout service cause Grafana to trigger an incident via PagerDuty. AURA (using DeepSeek-V4-Flash) uses its workers and tools to correctly determine root cause as a memory leak in a downstream service, and attributes the incident to a defect in a recently merged PR. The demo then concludes with a human-gated tool call to GitHub, where AURA documents the exact lines of code that are causing the problem, and recommends a fix. Once the PR is deployed, AURA validates that the errors are clearing and transactions are no longer failing. The whole time, AURA’s leaving an audit trail of OTEL events into Phoenix. Technical details: AURA uses an agent coordinator that drafts, executes, and supervises DAG flows through user-defined worker agents to solve complex investigations in parallel. Worker agents are bound to strongly typed durable artifacts used as evidence packets, and the system discourages wasteful recalculation of remote data. AURA also has a powerful header routing system that doesn’t allow the agent to actually touch your keys. HITL interrupts over webhook are first class citizens and have a schema that is easy to adapt to your own workflow. HA deployment options are coming soon. What’s still rocky: - We’re currently working on the async input system for when you’re running AURA as a service. Right now the API just accepts a request, and streams messages until the main loop completes. It’s easy to integrate into a workflow, but the logic required winds up being heavier than it ought to be. - Because there’s no inbound webhook interrupt mechanism, automating AURA for IR requires middleware to invoke it or it needs to poll an MCP for alert escalations. We’re looking for users, contributors, guidance on where to take this next, or just GitHub stars. Looking forward to reading and responding to feedback here. https://ift.tt/NjDuxqB September 2, 2026 at 10:55PM

Show HN: Newton's Orchard – Browser-based space/gravity playground https://ift.tt/8TzdN3v

Show HN: Newton's Orchard – Browser-based space/gravity playground Hi HN! My son spent a lot of time in 5th grade playing with the 2-dimensional PhET gravity/space sims[1]. His STEM class uses it, and he was playing with it at home, and has been looking for more. I found several space sims/playgrounds online, including NASA's Eyes on the Solar System[2], but nothing that seemed to offer a real progression from what he was getting out of the PhET sims, so I built Newton's Orchard over the summer for him. https://ift.tt/rglLDpx The source is also published at https://ift.tt/81gsXuB It features deterministic time scrubbing, all bodies are editable, different preset systems and experiments, missions to complete (complete 3 to unlock the blackhole object type and mission), and a gallery for user submissions. I would very much appreciate feedback from HN - particularly from the lens of making it engaging and illuminating for students, and anyone that would like to just get a feel for how gravity works. Thank you! [1] https://ift.tt/pbqKZla... [2] https://ift.tt/YyD0z9T https://ift.tt/rglLDpx September 1, 2026 at 11:43PM

Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo) https://ift.tt/Qm8YsK4

Show HN: Semantic Overlays – an NX bit for LLM prompt injection (live demo) I've built a new method for steering LLMs called Semantic Overlays, small trained adapters on a frozen model which change how its perceives a piece of its context. The most readily applicable usage is to mitigate prompt injection, and it lets us take a very-injectable Qwen-3.5-9B to SOTA scores on all the prompt injection benchmarks I could find. (They are only blackbox attacks, but I did NOT train on anything like them — whitebox attacks are out of scope for this paper) I'm excited for you to play with the tech — see if YOU can break it! (let me know if you can) Paper at https://ift.tt/Ah9erJX if you want to read more about it, code at https://ift.tt/a9wvnZR , adapters at https://ift.tt/X7VWDKl... Also https://ift.tt/vHP63nw if you wanna watch a little video I made! https://semantic-overlays.vercel.app/ September 2, 2026 at 12:40AM

Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s https://ift.tt/M4IhHVX

Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s I built slotstream, a way to run Qwen3.8-Flash-Next 4-bit on a low-memory mac starting from 16GB, a 125B parameter model that would need 100GB+ memory/RAM, thanks to expert-offloading/ssd-streaming. Easy to install/update, and mac-native using MLX and Swift. It ships with auto-mode, which makes a good tradeoff between memory usage and speed. I'll be implementing and porting the MTP module for speculative decoding next https://ift.tt/Nl6hi4y September 1, 2026 at 11:42PM