octopunk.io
Show HN: OctoPunk – a full-featured, AI-integrated GitHub clienthttps://www.octopunk.io/blog/introducing-octopunkHello folks.Like a lot of great software, we built OctoPunk out of frustration.We are a set of developers who, for one reason or another, have been using GitHub as our primary code forge for professional work for a very long time.We've seen GitHub grow, stagnate, ignore feature requests, and simply never produce a full-featured desktop client.Finally, we had enough, decided to build our own, and OctoPunk was born.OctoPunk is not a git GUI wrapper like GitKraken, not a half-implemented desktop client like GitHub's official client, which doesn't support code review, and not something that ignores complete workflows like per-commit reviews, looking at you, VS Code extension (https://github.com/microsoft/vscode-pull-request-github/issu...).OctoPunk is a full-featured GitHub client that surfaces 95% of GitHub's functionality as a desktop client, presented through a UI and UX that feels instantly familiar to modern editors and developer tools. We provide a customizable dashboard, quick searcJun 17, 2026 3:28 PM
github.com
Show HN: Write Your GitHub Actions in TypeScripthttps://github.com/dedalus-labs/hollywoodI spend a lot of my time writing GitHub Actions.Specifically, I need to script a ton of things. The current way of writing GitHub Actions with YAML is usually fine for small jobs. But for anything complicated, I often find myself in incredibly cursed "shell-in-YAML" situations.This was a major source of bugs for me. Since the "script" was written in YAML, there was actually not an easy way to modularize out the scripting logic to unit test them. Worse, there was zero type safety! For those who work with GitHub Actions frequently, you know how annoying this gets.My ideal GitHub Actions workflow would be to write actual programs, preferably in a language with strong types support.I also don't want an opinionated framework or a beefy runtime to "run" my GitHub Actions. I literally just want a way to write arbitrary programs that can call other services using native tooling from their respective ecosystems; for example, the AWS SDK to orchestrate my cloud.So this got me thinking about the Jun 16, 2026 7:36 PM
bing.com
USGA’s New AI Rules Official Could Change How Golfers Learn the Gamehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d49174e9e4aec848b37515a113ca9&url=https%3A%2F%2Fathlonsports.com%2Fgolf%2Fusga-rules-ai-ghin-golf-rules-tool&c=392469612892846192&mkt=en-usThe USGA’s new Rules AI tool promises instant answers to golf’s most confusing situations. Here’s how it works and why it could be one of the most significant golfer-facing technology launches in ...Jun 16, 2026 5:17 PM
bing.com
USGA’s New AI Rules Official Could Change How Golfers Learn the Gamehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d8922fbd744fe98958b8870c5d371&url=https%3A%2F%2Fathlonsports.com%2Fgolf%2Fusga-rules-ai-ghin-golf-rules-tool&c=392469612892846192&mkt=en-usThe USGA’s new Rules AI tool promises instant answers to golf’s most confusing situations. Here’s how it works and why it could be one of the most significant golfer-facing technology launches in ...Jun 16, 2026 5:17 PM
github.com
Show HN: git-lrc – Free, Micro AI Code Reviews That Run on Git Commithttps://github.com/HexmosTech/git-lrcHi HN, I'm the author of git-lrc, would appreciate some feedback from the communityLast year my team started using AI coding tools more heavily, and we found ourselves generating tons of code, but spending less time looking at the stuff that's been generated.We felt like we were losing a bit of grip/understanding of what we were building. Regressions occasionally slipped through. Sometimes changes made it all the way to production only to be reverted later.We tried several AI code review tools, but most operate at PR time. That felt too late. I wanted review to happen while the implementation was still fresh in the developer's mind at a team level (soft enforcement). I also wanted to emphasize responsibility for keeping prod stable with each individual engineer.So I built git-lrc.When you commit, git-lrc opens a review UI with your diff. It summarizes what changed, points out things that deserve a second look, and lets you quickly jump through the important parts of the change.Over timJun 16, 2026 2:04 PM
bing.com
Qualcomm reveals flagship XR processor and new framework for AI glasseshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8cdf647029499ab27af5fbaf40d520&url=https%3A%2F%2Fwww.digitaltrends.com%2Fcomputing%2Fqualcomm-reveals-flagship-xr-processor-and-new-framework-for-ai-glasses%2F&c=14836605946637958361&mkt=en-usQualcomm is laying the groundwork for the next generation of XR hardware with two announcements that target both the brains inside future headsets and the tools needed to build them. At Augmented ...Jun 16, 2026 12:51 PM
mydev.day
Show HN: I built a dev diary that writes itselfhttps://mydev.day/Hi HN, I'm Lucas. I mostly build XR things, but over the past month or so I've been developing a tool that became necessary for me: I'm usually working on many different things at once, and I needed a way to create reports and check what I worked on last year on a specific day.mydev.day is an automatic development diary that writes itself as you build. You connect your agent to it once per project (takes a couple of minutes), and from then on it automatically adds an entry per feature. After that you can query it via the API to ask anything about all your work across projects and accounts, or go to the app to print nice looking charts and reports.It started as an internal tool, but inspired by the indie hackers I follow, I decided to turn it into a product to see if it could be helpful for other builders and developers out there!Fun fact: it was really cool to dogfood it on itself as I built it!Jun 16, 2026 9:55 AM
bing.com
Microsoft Makes Copilot Cowork Generally Available Worldwidehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d760490c0470185f1bd6e316b2117&url=https%3A%2F%2Fredmondmag.com%2Farticles%2F2026%2F06%2F16%2Fmicrosoft-makes-copilot-cowork-generally-available-worldwide.aspx&c=13690346813206061140&mkt=en-usMicrosoft Copilot Cowork is generally available for enterprise agentic AI task execution. Cowork handles long-running, multi-tool workflows across Microsoft 365 apps, files and data. Admin controls, ...Jun 15, 2026 4:59 PM
news.ycombinator.com
Ask HN: What agentic directory structure do you use?https://news.ycombinator.com/item?id=48540840The more I use Claude Code to generate large swaths of systems, the more I feel like we are missing a lot of practices and tools.The first bit that really annoyed me was the lack of tracking prompts. There are lot's of little inputs that inform the what the system should do and it seems to be very ephemeral. I've since started tracking the prompts in the codebase.Another observation is that if you want to have good agentic output, you need to provide lot's of signal into the context window. It seems that being disciplined about what goes into the context window is key. Using AI to generate input files can be dangerous because it adds entropy/noise to the human signal.One practice I have started to do is organize my projects in a certain way:- /specs - Pure human signal such as product vision, requirements, designs, etc. - /prompts - Agentic recipes such as skills, jobs, AI patterns. - /references - References that can be used in the context window (brand assets, documents, figma exportJun 15, 2026 1:19 PM
bing.com
The 6 Best Head Shavers for Men in 2026, Tested by Grooming Expertshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d14a424144ec8a7d9014d138fe913&url=https%3A%2F%2Fwww.menshealth.com%2Fgrooming%2Fg43095736%2Fbest-head-shaver%2F&c=5483974662153241738&mkt=en-usWhen you do choose to shave your head, the tools you use to do it are paramount. That’s where the best head shavers come in. These high-tech gadgets are specifically designed to make shaving your head ...Jun 15, 2026 12:50 PM
bing.com
The 6 Best Head Shavers for Men in 2026, Tested by Grooming Expertshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d1ad4c1544d86ad2c065bcbce1f05&url=https%3A%2F%2Fwww.menshealth.com%2Fgrooming%2Fg43095736%2Fbest-head-shaver%2F&c=5483974662153241738&mkt=en-usWhen you do choose to shave your head, the tools you use to do it are paramount. That’s where the best head shavers come in. These high-tech gadgets are specifically designed to make shaving your head ...Jun 15, 2026 12:50 PM
news.ycombinator.com
Ask HN: How can we democratize agentic codinghttps://news.ycombinator.com/item?id=48536656One of the beauties of the tech industry is that anyone can learn how to program. Most languages are open source and a lot of the foundational software that make up the bedrock of the most powerful tools today are also free and open source. It’s telling that agents were primarily trained on effective unix.I think no one can deny that frontier models, especially playing around with Fable, that institutions will be separated by those that are willing to spend and those that can’t afford to. The dynamic feels dramatically different from the previous age where anyone learn how to Google effectively to be frontier productive. Will open source models eventually be good enough or will compute be cheap enough that this won’t be a concern? For some reason this is keeping me up at night. Fable feels like an end of an era for what was solidly a democratized profession.Jun 15, 2026 4:37 AM
news.ycombinator.com
Tlbic: A shared prompt for humanity and the future of ASIhttps://news.ycombinator.com/item?id=48534205Hello everyone,I’m sharing the 6th edition of the TLBIC (Time-Limited Local Basic Income Credit) proposal. In this version, I added a foundational “question”—a prompt addressed both to us as humans and to the AI systems that may eventually evolve toward ASI. If, in your own work or conversations with AI, you ever find a moment where such a question feels meaningful, I would be glad if it proves useful. My hope is simply that something in this document resonates with you or sparks reflection. As a reminder to myself, I intend to continue this project without rushing—remaining steady, sincere, and careful in each step. Thank you for taking the time to read this. (This text was translated and refined with the assistance of AI tools.)[Links]- TLBIC_Policy_Proposal_v6.0_EN:https://drive.google.com/file/d/1B4UszWGy5rQ_eCn6Zde7Td7LF9GBUrWk/view?usp=drive_link- TLBIC_Policy_Proposal_v5.1_EN (Timor-Leste):https://drive.google.com/file/d/1_IiJZsSHRVuIfeHiaz6W_xu7siiFDotE/view?usp=drive_link- TLBJun 14, 2026 11:28 PM
morningstack.app
Show HN: Morning Stack finds real job openings, tweaks resume and cover letterhttps://morningstack.app/demo/Job hunting sucks. That grind of digging through LinkedIn and Indeed, sifting through endless spammy emails from headhunters who try to get the biggest possible audience, clicking "Quick Apply" to silent response, and trying to figure out which of all of these jobs are even real. My wife hit all of this when she started job hunting a few months ago, so I built her a tool to take the worst part of it off her plate. It turned into this. Oh, and she got an offer letter from a major company in just shy of two and a half weeks. Now, she loves her job.Morning Stack runs overnight. While my users sleep it works through the big job boards (and some niche ones), and then it tries to disprove every listing before it trusts one.Is the job even real? - It opens the posting in a real browser (Playwright) and checks. There's no API scraping and we don't login to anything. Then, we resolve back to the company's own ATS page so you can apply directly to them. If it can't find it, the job is dropped.DoJun 14, 2026 11:01 PM
github.com
Show HN: Manim-Studio – Prompt to 3blue1brown videohttps://github.com/instavm/manim-studioHi,Created a tool that lets you type your idea and it can generate a 3blue1brown style video on this.The demo is free to use - https://crafty-resilient-grebe.instavm.site/Github open sourced as well - https://github.com/instavm/manim-studioIf you feel its cumbersome to set up manim locally, you can now just prompt this tool and it will create the video you need, be as descriptive as you like.Shoutout to the original Manim - https://github.com/ManimCommunity/manimHappy manim-ing!Jun 14, 2026 3:36 PM
news.ycombinator.com
I built a bookkeeping app for UK sole traders as a new developer using AIhttps://news.ycombinator.com/item?id=48527480About a month ago I started building QuarterPerfect — a bookkeeping tool aimed at UK sole traders and landlords, specifically designed around the MTD ITSA changes coming into effect this year (first quarterly deadline: 7 August).A bit of background on me firstly.I'm not a senior developer. My previous project was a small roster app that converted an XLSX shift rota into a calendar with annual leave support — mostly built for me and a few colleagues at work. Nothing with real users, nothing with payments or compliance requirements. QuarterPerfect is a significant step up from that.QuarterPerfect offers users bank statement import (CSV and PDF), transaction categorization with receipt matching, merchant rules for auto-categorizing recurring transactions, and a read-only accountant share link so clients can hand off clean records without chasing. It's web-first with a mobile app in testing.The technical side was challenging but learnable. The harder thing was building in a domain I have nJun 14, 2026 2:24 PM
news.ycombinator.com
Story of How Im Running an Unlimited $6/Month AI Provider on 4x RTX 3090shttps://news.ycombinator.com/item?id=48524387This submission is a tale about how I launched an unlimited LLM provider to about 60 hyped people on the waitlist, then immediately served them a fully dysfunctional death-loop model, and how most people, very reasonably, disappeared, but thanks to a few extremely nice people stuck around anyway, we kept the project alive and its still pretty chaotic but gaining traction.To back up a little bit-- I believe that the whole point of AI agents is that they should keep working. They should read files, retry, search, code, summarize, run tools, and loop until the job is done. When your employer is paying for it, who cares about cost, but when it comes to my personal money/hobbies, if every loop feels like a tiny financial event, you start babysitting the agent instead of using it, and its not fun.On the other hand, metered pricing makes me worry about using too much. Usage subscriptions make me feel like I need to use every last magical % or I'm are "wasting it". If only an unlimited provideJun 14, 2026 5:11 AM
news.ycombinator.com
Show HN: I am running 3 coding agents non-stop over the last 3 days. Here is howhttps://news.ycombinator.com/item?id=485207571. Headless modeHeadless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run.2. Ask humanThe traditional communication channel with the operator won't work in headless mode - we need to implement a dedicated tool. Here is an example of how this can be done https://github.com/sermakarevich/claude/tree/main/mcp/ask_hu...3. Tasks queueBeads is a lightweight distributed graph issue tracker for AI agents, powered by Dolt. You can create tasks, define dependencies between tasks, and have status, priorities, hierarchy. Beads helps prevent multiple tasks from being claimed by > 1 worker.4. Worker artifactsWe want to be able to monitor how a worker is doing, at what stage it is, and resume it after a restart. For every task we can create a dedicated folder using the beads task id and put into it what we need. I put there: - plan and status md - knowledge md - events.jsonl - sJun 13, 2026 7:48 PM
news.ycombinator.com
Ask HN: What happens when AI-voice becomes good enough?https://news.ycombinator.com/item?id=48507696I fell into the rabbit hole of TTS models lately. Tried all major paid tools (ElevenLabs/InWorld/etc.), and all the newest open-source models.I started asking myself: what happens when the voice is "solved"? E.g. it gets impossible to distinguish it from a human. Wanted to hear your opinions!Sketched some of my own thoughts, and I see two futures:Future 1: the nuanced versionAudiobooks: I think established authors will still prefer human narrators. If you can afford a $3k–$4k fixed cost for narration, a good human voice is usually worth it. TTS may even push human narration prices down, making that choice easier.But for new/self-published authors, especially in non-fiction, AI narration may become the default. The choice is often not “AI vs. human narrator,” but “AI audiobook vs. no audiobook.” There will be backlash, but I think people will partly get used to it.The more interesting threat may be AI readers. If I can buy an ebook for $8–$10 and have it narrated in a voice/style I likeJun 12, 2026 6:30 PM
bitboard.work
Launch HN: BitBoard (YC P25) – Analytics Workspace for Agentshttps://bitboard.work/We’re Connor and Ambar from BitBoard (https://bitboard.work). BitBoard is an agentic analytics workspace. We give you the infrastructure and visualization layer to analyze data with AI.Today, we’re launching dashboards that you and your agents can work on together. You can connect your coding agent or AI chat to BitBoard and build live reporting. Here’s a demo: https://www.youtube.com/watch?v=HPl0K565a7c.AI tools treat data analysis as ephemeral, making it hard to report or collaborate. Legacy BI tools weren’t intended for AI users, so they bolt on chatbots and can’t offer meaningful control to your agents. Software can now make far more of a business legible than BI ever could, but neither legacy BI nor chat bots are built to handle it.Our original product was AI agents for administrative tasks in healthcare (https://news.ycombinator.com/item?id=44237769), but customers kept pulling us toward their data analysis problems: queries scattered across disparate sources, spreadsheets floatiJun 12, 2026 4:58 PM
