news.ycombinator.com
Show HN: I replaced a $120k bowling center system with $1,600 in ESP32shttps://news.ycombinator.com/item?id=48968606I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think.My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert.It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but it fades into the background beyond that. Turns out these things are really cool, but absurdly expensive.Ours was installed in 2008 and cost six figures. It's calculating ball speed and trajectory, camera-based pin detection (object detection and trig, on ICs!), runs the fouling, the animations, the pinsetting machine and ball return. Very cool stuff for its age.From the business perspective, my faciliJul 19, 2026 2:41 PM
pokayoke.codes
Show HN: Pokayoke – turn code conventions into checks for agentshttps://pokayoke.codesHey HN,Something I've been tinkering with in the background is a system to manage the "messy-middle" of TypeScript toolchains. Quite often, when I'm using Biome or any of the other linter / formatters, there will be repo conventions that I want to enforce (especially with AI agents), but which aren't supported by them, such as:- Enforcing lines-of-code limits in modules - Never using custom TailWind colors - Only using lowercase underscores in filenamesLike, this is quite "random" but also bread-and-butter stuff that it's easy to think or talk about when you're working by yourself or with a few other human teammates, but I've found that agents consistently miss these conventions if I put them in an AGENTS.md file for example.I wanted to make my esoteric repo conventions less stochastic, and more deterministic. I realised that agents are adept at writing the kind of code needed to run arbitrary checks on the TypeScript AST or workspace environment -- the kind of code that is cumbersome Jul 16, 2026 9:40 AM
github.com
Show HN: GLP-RAM – Chrome extension reducing the browser memory appetitehttps://github.com/chebykinn/glp-ramHi!I've been struggling to use Chrome on my M1 Mac, because of how much RAM it eats, and memory saver wasn't enough.I've made this extension based on combination of features on multiple separate extensions: 1. When you click on the new tab, only the first tab loads in background, the rest will have a placeholder until you click. 2. Only 3 active tabs per window are allowed to be loaded, the rest will be killed. 3. The extension watches if you have unsaved input, paused or active media, or if the page is configured to send notifications and it keeps these tabs alive.I've been using it for a couple of weeks and it allows me to open way too many tabs to handle :)The extension is published in Chrome Web Store, let me know if you have any questions!Jul 14, 2026 4:14 PM
mojavepaint.app
Show HN: Mojave Paint for macOS, edit images like it's 1999https://mojavepaint.app/We all need a swiss army knife for images. A tool for really getting in there and dealing with the pixels precisely. You might be combining images into a sprite sheet, you might be matting images to squares, cutting out solid backgrounds, re-tinting graphical elements. For a website, a video game, for an app.There's a million photo editors, there's a million design tools, and Mojave Paint can do those things in varying degrees but "graphical asset production" is its first and primary mission.It's cheap! $9.99 (one-time, sad I even have to say that) for the "Pro" version. It's Mac-only, and Apple Silicon Mac at that. Does it look a little like Photoshop 5.5 from the year 1999? Maybe a little but also it's got plenty of its own original ideas. (Blog post on that is forthcoming…)I've always been passionate about image editing tools for the technically-minded so I'm throwing my hat in the ring in that space. And sure GIMP is for the technically-minded but boy is it ugly on the Mac!Jul 10, 2026 12:29 PM
sipp.sh
Show HN: Sipp – Run small local LLMs in browser 3x fasterhttps://www.sipp.shHi HN! Sipp is an open-source AI inference library for running local models in browsers with up to 3x faster decode speeds than alternative libraries.My background is in HCI (human-computer interaction) and graphics programming. Me along with my co-founder have been experimenting and thinking a lot about what the next user experience will look like when tokens are commodified to the point of being essentially “free.” A motivation for us was to try to move beyond the chat app and information retrieval use cases that are dominant now, and figure out how AI could instead act as a continuous and silent hand that helps the user indirectly, subtly monitoring their intent and dynamically generating or shifting the UI to meet their needs.In our explorations, we ran into two pain points: 1) when running AI in the browser, performance wasn’t good enough for real-time applications, and model loading and caching were issues; 2) when trying to run locally on desktop, there weren’t any good solutionJun 24, 2026 2:52 PM
bing.com
What Is Middle Class Income? Thresholds, Is It Shrinking?http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8acb99989d41de9061bfceb0a130e8&url=https%3A%2F%2Fwww.investopedia.com%2Ffinancial-edge%2F0912%2Fwhich-income-class-are-you.aspx&c=18016217309465528112&mkt=en-usHow to tell which one you belong to among the various classes Investopedia contributors come from a range of backgrounds, and over 25 years there have been thousands of expert writers and editors who ...Jun 19, 2026 9:19 PM
github.com
Show HN: Babysit – let coding agents operate a TUIhttps://github.com/yusukeshib/babysitI've been trying to automate my work recently, but I ofeten encounter the situation where agents needs human intervention to complete the task. So I made a simple command that wraps a TUI called babysit that has a terminal emulator inside using pty. Agents can start commands in background, and they can ask human by attaching the TUI on a new tmux pane when human intervention is needed, or they can operate the TUI with screenshot/send/expect/wait commands. So far, I really like using it, and I wanted to share it here.https://github.com/yusukeshib/babysitJun 16, 2026 12:53 PM
github.com
Show HN: Bullstudio v2 – open-source BullMQ dashboardhttps://github.com/emirce/bullstudioI'm happy to announce version 2 of Bullstudio, a modern and performant dashboard for Bull and BullMQ job queues.Between v1 and v2, a lot of new improvements and features have been implemented. You can now choose whether you want to run the dashboard as a standalone application or embed it directly in your app. We've also implemented fast per-queue views for your background jobs: Paginated jobs table with server-side search, scheduler and worker management as well as flow vizualization.Feel free to check it out and give me some feedback!Jun 11, 2026 7:03 PM
news.ycombinator.com
Can you help reconcile my first/second-hand LLM Experience with HN's Experience?https://news.ycombinator.com/item?id=48102861I've made an account as a long-time lurker because I am hoping y'all could help reconcile my experience in my company/team with what seems to be the wise HN consensus around LLMs.My Background (Software Engineer II):I've been writing software professionally for >10 years and grew up coding games/websites for fun; did my undergraduate in C.S./C.E., and did some time in ML research and such. Right now I'm on the back-end/DevOps team - my teammates are all Senior Staff/Principal Engineer (one is almost double my age lol!) and we have a pretty standard tech stack (NodeJS, AWS, C++, etc) with 95% brownfield development at a large but not FAANG-like company. I've had my current job for >6 years and out of ~20 in our department I'm the third newest!I'd say I'm a pretty stereotypical engineer AKA "a total nerd" with private side projects mostly around implementing computational geometry or procedural simulation papers in Rust, sometimes working on a lil website tool we use daily. But I mostly May 12, 2026 12:57 AM
github.com
Show HN: Mobile-ink, an open-source mobile infinite drawing canvashttps://github.com/mathnotes-app/mobile-inkHello everyone, I have been working on this for a year and it is such a difficult problem. mobile-ink is an open-source mobile infinite drawing canvas. There is not a strong open-source drawing engine beyond toy demos. Thus, mobile-ink aims to solve this problem and provide a state-of-the-art mobile note-taking canvas package.mobile-ink uses native Skia/Metal to address issues with native rendering, pencil latency, eraser behavior, page virtualization, preview caching, memory stability, page interactivity, etc. It has many advanced features such as shape-snapping, primitives to integrate figures, custom backgrounds, pdf import, stroke selection, smooth zoom/scroll, and more.The package is iOS + React Native as of now.May 8, 2026 5:01 PM
github.com
Show HN: An Agent First Slack CLIhttps://github.com/tilework-tech/nori-slack-cliHey folks,My team and I have been building a background agents as a service product. One of the things we needed pretty early on was for some way for the agents to be able to drive slack.Right now, I don't think there are many good agent-first ways of doing this. I don't love MCP -- it's just too many tokens in the context window, and agents seem to do better with CLIs because they can embed them in code and so on. But other CLIs that exist are either a) subsets of the web api that only focus on human needs and b) have polished terminal UIs with spinners and colors and interactive things that make it hard for LLMs to actually use them.nori-slack-cli is a very thin dynamic wrapper over @slack/web-api (i.e. bolt). Whatever the SDK can call, the CLI can call. When slack adds a new method it should just work without a new release on our end. (Inspired by the GWS cli: https://github.com/googleworkspace/cli).So you(r agent) can do things like:`nori-slack chat.postMessage --channel C123 --texMay 1, 2026 7:05 PM
news.ycombinator.com
Ask HN: Would you use revocable digital signatures to verify AI/Other content?https://news.ycombinator.com/item?id=47848539I’ve been exploring a potential product direction and wanted to sanity check it with people who actually build and ship things.Background: I’ve been working on a system using our core tech that can generate and verify digital signatures, but with a slightly different property than traditional approaches. The signatures are natively revocable. If the underlying model/system shouldn’t be trusted anymore, the signatures can be revoked either through a hard (delete the signing model) or soft (revoke the lease for the signing model) mechanism. I believe this feature is very beneficial on its own, but there are several other interesting properties (no key management, distributed verification, embedded metadata, etc.)Originally this came out of some deeper R&D work we’re doing, but I’ve been thinking this might actually be the most practical “wedge” into the market while we continue that research (and fund the research).One area that’s been interesting is applying this to AI systems. SpecificApr 21, 2026 1:28 PM
github.com
Show HN: Mulder – Containerized MCP server for digital forensics investigationshttps://github.com/calebevans/mulderI built Mulder for the SANS "FIND EVIL!" hackathon. My background is not in forensics, but I was interested in building the agent. I've been seeing some really cool results and thought this community might like it!Mulder is an MCP server that exposes forensic tools like Volatility, Sleuthkit, Plaso, and more as typed tool calls. Every invocation is recorded in an append-only audit log. When an agent finds something, it submits a "finding" to the case database. Each finding must have evidence citations that are validated before being admitted. If the agent cites evidence or a tool execution that doesn't exist, the finding is dropped.The biggest problem I needed to solve was context window pressure. These investigations often contain a lot of data, and processing it produces a lot of noise that will fill a context window quickly. To avoid this, all tool output is stored in a per-case SQLite database with full-text search. The agent can then search the database and request segments of tooApr 21, 2026 1:06 PM
understudy-ai.github.io
Show HN: I made an AI that reviews iPhone apps – 1h of autonomous GUI workhttps://understudy-ai.github.io/understudy/I've been building Understudy, an open-source GUI agent for macOS. Wanted to push the GUI stuff beyond the usual short demos, so I tried turning it into an iPhone app reviewer.You give it one prompt. It browses the real App Store in Chrome, installs the app on a real iPhone through macOS iPhone Mirroring (not a simulator), opens the app and explores it — never seen Snapseed before — records clips and screenshots, composites a narrated review video with FFmpeg locally, uploads it to YouTube, then deletes the app. About an hour, didn't touch the keyboard.The exploration part is what I'm happiest with. The agent reads the App Store description, goes "they say background removal works, let me try that," and then figures out an unfamiliar app on its own. It regrounds from the live screenshot every action, so unexpected dialogs or UI changes don't kill it.The reason it can sustain an hour of work: each of the 6 stages runs as a separate child session with its own context. You can't fit an hoMar 27, 2026 7:39 PM
news.ycombinator.com
New Open Source from Non-Traditional Builderhttps://news.ycombinator.com/item?id=47477073Let me begin by saying that I am not a traditional builder with a traditional background. From the onset of this endeavor until today it has just been me, my laptop, and my ideas I learned how systems work through trial and error, and I built these platforms because after an exhaustive search I discovered a need. I am fully aware that a 54 year old fantasy novelist with no formal training creating one experimental platform, let alone three, in his kitchen, on a commercial grade Dell stretches credulity to the limits (or beyond). But I am hoping that my work speaks for itself. Although admittedly, it might speak to my insane bullheadedness and unwillingness to give up on an idea. So, if you are thinking I am delusional, I allow for that possibility. But I sure as hell hope not. With that said I have released three large software systems that I have been developing privately. These projects were built as a solo effort, outside institutional or commercial backing, and are now being made aMar 22, 2026 1:01 PM
news.ycombinator.com
Launch HN: Sitefire (YC W26) – Automating actions to improve AI visibilityhttps://news.ycombinator.com/item?id=47457472Hi HN! We're Vincent and Jochen from sitefire (https://sitefire.ai). Our platform makes it easy for brands to improve their visibility in AI search.We’ve been working together for years and have backgrounds in RL/optimization at Stanford and software engineering. We came to this idea after speaking with marketing teams who were seeing declining traffic due to Google’s AI Overviews and didn’t know what to do.This space can feel esoteric. Many case studies, few actual studies. Constant battle against myths (e.g. you need a llms.txt vs. you don't need a llms.txt) and "GEO hacks". We try to be more data-driven. And we try to be more bold and build a system that not only monitors, but actually improves traffic from AI search.While Google performs a single search, AI search engines expand the user prompt into 3-10 fan-out queries. The sourced pages are ranked using a classified algorithm similar to Reciprocal Rank Fusion (RFF). Finally, the LLMs skim the pages and decide what snippets to citMar 20, 2026 5:05 PM
lukan.ai
Show HN: Lukan – An open-source agentic workstation in a single Rust binaryhttps://lukan.aiHi HN, I've been building Lukan, an open-source (MIT) agentic workstation that runs entirely as a single Rust binary with zero runtime dependencies. I started this because I wanted a unified workstation optimized for my own productivity. My goal was to build an environment where I could securely remote into my machine from anywhere, seamlessly view and modify local files, and run AI agents or drop into a terminal side-by-side, all integrated with a rich set of built-in tools. Here is what makes it different: Multi-agent sessions: Run multiple agents in parallel, each with its own isolated context and history. You can switch between them using tabs, resume after disconnects, and even rewind to previous checkpoints. Embedded terminal: A full tmux-backed terminal lives inside the Web and Desktop UI. Sessions survive page reloads and network drops. You can run any CLI tool alongside your agent (including Claude Code, Codex CLI, Lukan Cli, etc.). Pipelines & Background workers: DAG-based muMar 18, 2026 3:14 PM
caelix.co.uk
Show HN: Caelix, a balanced-ternary lattice field laboratoryhttps://caelix.co.uk/Hi HN,I've been working on an open-source simulation lab called CAELIX and wanted to share it here. It's a discrete lattice field framework for testing whether continuum-like signatures can emerge and be routed using strictly local update rules on a balanced-ternary substrate {-1, 0, +1}.There are 11 real-time animations running directly off the simulation code on the website. (I locked these specific visualisations to 2D so they actually run smoothly in the browser on phones and modest hardware). The architecture enforces a strict separation. The discrete balanced-ternary microstates act as a topological boundary generator which couples via a deterministic load functional into continuous carrier dynamics. The numerics are often FDTD-like, using diffuse and telegraph surrogate equations, but the framework as a whole is much broader than a conventional solver.A bit of background: I'm not a physicist. My expertise is in computing systems, databases and audio engineering. I go all the wayMar 12, 2026 11:25 AM
bing.com
A Beginner's Guide to Real Estate Investing: Key Strategies & Tipshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a89c0fdf0104de1ac0992f86ecbdca1&url=https%3A%2F%2Fwww.investopedia.com%2Fmortgage%2Freal-estate-investing-guide%2F&c=15277306082630266374&mkt=en-usInvestopedia contributors come from a range of backgrounds, and over 25 years there have been thousands of expert writers and editors who have contributed. Lea Uradu, J.D., is a Maryland state ...Mar 9, 2026 3:48 PM
bing.com
Bankruptcy: Explaining Chapter 7 vs. Chapter 13http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8b85a12f7c42e68e66f2d3bfcf8e0a&url=https%3A%2F%2Fwww.investopedia.com%2Farticles%2Fpf%2F07%2Fbankruptcy.asp&c=10077129311764917857&mkt=en-usInvestopedia contributors come from a range of backgrounds, and over 25 years there have been thousands of expert writers and editors who have contributed. Thomas J Catalano is a CFP and Registered ...Mar 8, 2026 2:16 PM
