housecat.com
Show HN: Housecat.com – Gmail + durable workflows + sandbox VMhttps://housecat.com/Hey we are Housecat.I've spend the last 15 years building dev tools at Heroku, Convox (YC S15), and Segment. Dev tools have gotten insanely good over the decades, now we're working to level up productivity tools for everyday work.Housecat is an email inbox running on an single-tenant agent computer with a durable workflow engine and connections to common tools for day-to-day work.My primary workflow with the product is for customer support: get a support email, trigger a triage process, open a GitHub issue, spin up a coding agent to fix it, and update the customer along the way. All from the same UI and sandbox.We've experimented with lots of different approaches to new workspace tools, and learned that many people still need a great GUI. We've landed on the email inbox as a very familiar and permanent surface and are building tools and automations directly inside it.Under the hood every user gets their own single-tenant sandbox VM and persistent SSD on exe.dev.User connections to GoogJul 22, 2026 1:04 PM
spacenews.com
The strategic competition with China: winning the multi-domain racehttps://spacenews.com/the-strategic-competition-with-china-winning-the-multi-domain-race/History demonstrates military innovation continually rewrites the rules of combat, reshaping warfare and rendering strategies from past conflicts obsolete. The introduction of repeating rifles transformed infantry combat during the 19th […] The post The strategic competition with China: winning the multi-domain race appeared first on SpaceNews.Jul 22, 2026 1:00 PM
bing.com
I Found the Only Nipple Covers That Don't Slide Off—and They're 30% Off Right Nowhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d3bbce31c4c7fbf8c899bba203f09&url=https%3A%2F%2Fwww.cosmopolitan.com%2Fstyle-beauty%2Ffashion%2Fa64982905%2Fcakes-body-review%2F&c=8259411219568662735&mkt=en-usAs someone who spends a lot of time thinking about clothes, I inevitably spend lots of time figuring out the right undergarments to go underneath, too. Grappling with uncomfortable strapless bras and ...Jul 22, 2026 12:27 PM
bing.com
Nolan Wells' cause of death undetermined, family's autopsy showshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8cfe4ba8944d52a5d2fb04d4cc9909&url=https%3A%2F%2Fwww.msn.com%2Fen-us%2Fnews%2Fus%2Fnolan-wells-cause-of-death-undetermined-familys-autopsy-shows%2Far-AA28sDXK&c=10338148914353379820&mkt=en-usNolan Wells, 18, was found dead just off Horn Island in Mississippi after enjoying a day out with friends on July 4.Jul 22, 2026 10:38 AM
github.com
Show HN: add-reasoning-to-prs: a hook that adds unnoticed assumptions to PR deschttps://github.com/backthread/add-reasoning-to-prsI think when you want to truly understand how something works, you either reverse-engineer the thing, or you participate in its making, or at least, understand the reasoning behind the build.Reading the documentation is not enough – you need to see how the thing was made, why certain decisions were made, what trade-offs were accepted, and what assumptions were made.I don't really think it is possible to sustainably scale automated agentic end-to-end development without reviewing the code, or reading every line of agent reasoning.So I wrote a claude code hook that takes your session transcript and before creating a PR, extracts decisionsl, assumptions and trade-offs that were made during the session (and possibly missed by the human) and appends them to end of PR description. In my testing with another repo, it produced real insights that raised real risks, that would be otherwise lost.For now, it's only claude code, but I will add support for all other harnesses.I would appreciate if yJul 22, 2026 10:27 AM
imagerry.com
Show HN: Imagerry – client-side image customizer and converter (WASM / WebGPU)https://imagerry.com/Hi HN! I built Imagerry (https://imagerry.com), a freemium, 100% client-side image converter and utility suite.### What it does till today:- 100% Client-Side: Zero file uploads, all processing happens locally using HTML5 Canvas & WebAssembly, though gpu is heavy on desktop apps. - Format Conversions & Resizing: PNG, WebP, AVIF, JPEG, SVG with high-quality Lanczos scaling (`pica`). - Utility Tools: Code Snippet Beautifier, App Icon Studio, Social OG Card Generator, and Passport Photo Arranger. - Cross-platform: Available as a PWA and desktop app (Electron).### Some Suggestions and tradeoff's for adding ?? :)I’m considering adding *local AI models* (such as in-browser AI image upscalers or background removers using ONNX Runtime Web / WebGPU) - by desktop apps preferable only.Since Imagerry focuses on privacy and zero cloud uploads, running models locally in the browser feels like a natural fit, but it comes with a *20MB–50MB initial model or even more depending on local model's download Jul 22, 2026 9:33 AM
spacenews.com
Gravity-1 sea launch off Shanghai puts 9 satellites into orbithttps://spacenews.com/gravity-1-sea-launch-off-shanghai-puts-9-satellites-into-orbit/HELSINKI — Commercial launch firm Orienspace launched its third Gravity-1 solid rocket late Tuesday, sending nine satellites into orbit from waters off Shanghai. The 30-meter-long Gravity-1 solid rocket lifted off […] The post Gravity-1 sea launch off Shanghai puts 9 satellites into orbit appeared first on SpaceNews.Jul 22, 2026 9:32 AM
tailrmade.app
Show HN: Our data canvas where everything runs directly in the browserhttps://tailrmade.app/A friend and I (engineer + designer) have been working on this for more than 6 years trying to make a more visual and interactive data management/programming environment that runs and processes everything in end user browser, it's like a node based IDE without compilation with the ability to make dashboards.We are building this because we both want to work with data visually rather than just via text, and we feel that existing solutions are either black boxes or unwieldy.We just open sourced the canvas/editor under AGPL (considering MIT). You can self host it and use your own keys for APIs and LLMs.The hosted version at https://tailrmade.app allows logging in (but no sign in is needed) (uses Firebase, not open source yet).I'm using it myself for JIRA dashboards, automated testing, image handling/shader tinkering and building control panels for the enterprise software I work with for a living. Do these workflows also make sense for you? Is there anything you think is missing that you thJul 22, 2026 9:02 AM
bing.com
Stocks and the Economy Are Increasingly Relying on the A.I. Boomhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d390f5b844c2ebd4cf03bbe11790f&url=https%3A%2F%2Fwww.nytimes.com%2F2026%2F07%2F22%2Fbusiness%2Feconomy%2Fstocks-economy-ai.html&c=8252160208470939041&mkt=en-usInvestment in artificial intelligence and related companies is lifting the stock market and spending across the economy. Credit...Pete Ryan Supported by By Ben Casselman and Joe Rennison Ben Casselman ...Jul 22, 2026 7:15 AM
news.ycombinator.com
Help MitM atks denl of srvce. Reliable AIhttps://news.ycombinator.com/item?id=49002711HELP MitM+ Denial of service hacks. PRO state level. THE patent pending tech at the core of all the new "Too powerful" models. Independent Inventor, attached for months. Oppressed. I'd appropriated. Work stolen. Documentation exist, mapped the network. Now is everything wish they can't but they still got of my files locked up in an accessible didn't create a serious problem. Can't make this up!!! Please.Jul 22, 2026 6:46 AM
github.com
Show HN: Spring Boot Inspired Java Selenium Open Source Frameworkhttps://github.com/seleniumboot/selenium-bootI built it with Claude code. Over my 12 years of experience in Test Automation, I always wanted to have an open-source framework that can reduce the plumbing work and still give you full control over the WebDriver. Selenium Boot is for that; the same ideology is used as Spring Boot does for Java Developers.I have extended user of semantic locators, thread-safe for Parallel Run, IntelliJ Plugin and an MCP Server for Test Automation, which is well aware of Selenium Boot to boost the test automation experience.Your comments/queries/star/contribution on GitHub will inspire me.Jul 22, 2026 4:30 AM
bing.com
Adam Schiff pushes federal judicial reform. ‘Americans deserve nothing less’http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d2390b20140b5bd80b4cdeb425b0e&url=https%3A%2F%2Fwww.yahoo.com%2Fnews%2Fpolitics%2Farticles%2Fadam-schiff-pushes-federal-judicial-113000849.html&c=13445572122684701430&mkt=en-usThe package includes three bills intended to address ethics concerns for federal judges and Supreme Court justices.Jul 22, 2026 4:30 AM
bing.com
Adam Schiff pushes federal judicial reform. ‘Americans deserve nothing less’http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8cf339bf454549be12b44a2e29dd4f&url=https%3A%2F%2Fwww.yahoo.com%2Fnews%2Fpolitics%2Farticles%2Fadam-schiff-pushes-federal-judicial-113000849.html&c=13445572122684701430&mkt=en-usThe package includes three bills intended to address ethics concerns for federal judges and Supreme Court justices.Jul 22, 2026 4:30 AM
bing.com
Jose Mourinho, Perez & the many issues facing Real Madrid in 2026-27http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d927a02264605b0c2ad6ee75e5fe6&url=https%3A%2F%2Fwww.msn.com%2Fen-za%2Fsports%2Ffootball%2Fjose-mourinho-perez-the-many-issues-facing-real-madrid-in-2026-27%2Far-AA28r9vk&c=18139115387835043487&mkt=en-usSince club football season ended over a month ago, few, if any, clubs have made quite as many headlines as Real Madrid. It all started a week before the final game of the season, with president ...Jul 22, 2026 2:30 AM
getcomputable.com
Show HN: Computable – Buy, sell, and redeem GPU for the exact weeks you wanthttps://www.getcomputable.com/Hey we are Computable. We spent years building trading infrastructure at Jump Trading and Coinbase. From that point of view, compute looks like energy markets before 2000: everything trades through private bilateral leases, there’s no visible price, and nothing can be resold. The same H100 rents at a 2x spread depending on who’s asking, and once you sign a 24-month lease, it can never change hands.So we built a market for GPU nodes, sold by the calendar week. Here are three things you can do on it that you can’t do anywhere else:- Buy exactly the weeks you need. Three nodes for the last two weeks of October means you pay for those two weeks and walk away when the run is done. You don't have to commit to 6-24 months, and there's no flexibility premium.- Sell back what you don’t use. If your plans change, unused weeks turn back into cash: we keep a market quote posted on every position, so there’s always a price to hit.- Buy (or sell) the future. Lock January in July at a price you set, Jul 21, 2026 9:48 PM
machinations.tpk.gg
Show HN: Machinations – a multiplayer strategy game where LLM is the game masterhttps://machinations.tpk.gg/I started by thinking about the game mechanics I actually wanted to see. I come from a long background in diceless tabletop RPGs, and what I loved about them was the GM improvising, making rulings on the spot. When LLMs came along, I saw a chance to build a mechanic that worked like that.But LLMs on their own are bad at it. They regress toward the mean and they try too hard to please the player. Nobody ever really fails. So I built a system (I won't name it, I'm not here to self-promote) around a 3d10 bell curve of outcomes. The dice decide how well an attempt goes, across a whole spread of grades from disastrous to legendary, and the LLM has to narrate whatever the dice say. That forces it to produce results the player won't like, which is where the drama comes from.With that in hand, I could resolve any conflict narratively. Two characters chasing the same goal, one trying to kill or rob the other, whatever. The roll leans the story in one direction or the other. Then I realized I neJul 21, 2026 9:26 PM
llmtrail.com
Show HN: I built a chat client that uses embeddings to cluster messages by topichttps://llmtrail.com/demoHi HN, I found myself scrolling backwards a lot in my chats with LLMs to follow up on interesting things I had seen earlier in the conversation. So, I built a basic chat client and I added a sidebar that allowed me to jump directly to different messages. The sidebar started getting hard to navigate with a lot of items, so then I thought it'd be nice if the chat history was clustered by topic.In the end what I settled on was to have an LLM generate summaries of the query and responses, turn those summaries into vector embeddings, and then score the new message against the existing groups. A group's score is the cosine similarity of the new message and the last three messages in each group. The message is added to the best scoring group if it exceeds the threshold and is still similar enough to the first message in the group.This was a fun project because I've never built a complete website before, so I learned a lot and it was satisfying to get something up and running. I also enjoyed tJul 21, 2026 9:19 PM
news.ycombinator.com
Ask HN: What is your onboarding/discovery process for a new client or project?https://news.ycombinator.com/item?id=48998228I've typically worked on longer and bigger software development engagements, but recently have picked up several small (but profitable) automation jobs via referral. My existing onboarding process is too much for these types of projects.I’m curious what methodologies or tools (super curious about tooling) people use to help obtain the required context (asynchronously) to scope out a project successfully.I feel like this is something that I’m good at and, probably, the most important input to delivering great outcomes for my clients. My level of engagement in this beginning phase is my biggest bottleneck, there is so much friction and energy required at the start. For reference on my existing pattern:I tend to start with 1-1 conversations. This gives me a good starting point of context AND helps earn trust with stakeholders.Then I move into 1 to many conversations which start to expose nuances as people talk to each other while I observe. This is also typically when I start to tease solJul 21, 2026 8:59 PM
orate.to
Show HN: Orate – On-device neural text-to-speech queue for Machttps://orate.to/Hey friends! Brad here - long time HN user, founder, engineer (Coinbase, Soothe, Jeevz, Release, Hired, GrowthX, etc)...I have been struggling recently with too many tabs, emails, articles, etc sitting unread while I swap between Claude code sessions all day. So I decided to build Orate to help me work through the backlog by listening to it all like I would a podcast.Orate allows you to select any text on your screen and keyboard shortcut it to a listening queue where it gets processed using the latest + greatest TTS AI models, and then read back to you in a mostly-natural sounding voice. Orate works fully on-device and offline. Whatever you pass to it stays yours. It's native, lives in your menu bar, and supports things like tagging, system playback controls, speed adjustment, and more. There's also an optional HD-voice tier that uses Chatterbox instead of Kokoro which ships with it for more expressive TTS.I'm also burnt out on being chipped away at little by little with a subscriptioJul 21, 2026 8:38 PM
github.com
Show HN: Claude Bucks – a wallet for your AI agenthttps://github.com/zachrip/claude-bucksHey all, I thought of this idea today: it would be pretty fun if claude could accrue currency and then spend this currency at a cosmetics shop on its own. The twist: the amount of money it earns it based on your ratings of its work multiplied by the effort (currently just token count but might change this). Claude can decide to spend money on small things or save money for larger purchases like the pirate hat - one of the items that actually changes the way that claude talks to you (Aaargh!). At first I thought this was just a whimsical idea, but then when using it I genuinely gave claude a rating of 0 for a session and it was able to sum up what went wrong and how to improve next time. So I added the ability to incent claude to do better work with the idea that better work = more money = more purchasing power (I know the incentive is a little backwards right now with the token count metric). Right now it's entirely vibe coded for speed/time but if it gains traction I will probably rewJul 21, 2026 8:15 PM
