Show HN: Life Tile – Passive time tracker that shows your day as a Mondrian grid https://bit.ly/4fywEVa

Show HN: Life Tile – Passive time tracker that shows your day as a Mondrian grid Hi, I developed Life Tile for iPhone. It tracks your time passively and visualizes it as a Mondrian-style grid. It's a one-time purchase app with a 7-day trial. I was a user of a similar app named Life Cycle. Since the app hasn't been updated in a while, I tried to make a better app with my ideas and experiences. I used a big square timeline instead of a donut chart. And I added more useful views: tree-map, map, and list. You can use categorized activities with custom colors. The data never leaves a device. No account, No Server. It only supports data backup using iCloud. It was for privacy but it also makes the development easier. I added just one anonymous usage stat with TelemetryDeck. You can turn it off anytime. There were many technical difficulties. iOS location API (CLMonitor) is not 100% precise. And many difficult cases can't be handled automatically. For example, GPS blackout inside the subway, too many venues in a small region, and a huge location like an airport. So I improved many heuristics and tried my best for easy editing. Please check the App Store for the screenshots. Then you'll know why it's inspired by Mondrian. https://apple.co/44LtV60 July 24, 2026 at 01:13AM

Show HN: Connecting my dumb garage and car's homelink buttons to Home Assistant https://bit.ly/45jBPUh

Show HN: Connecting my dumb garage and car's homelink buttons to Home Assistant Hi all, I've been on parental leave and while working on my garage door, I thought to myself... it would be great to open up this garage door from my phone without having to buy a bunch of expensive stuff. That snowballed into, I want the garage door buttons on my car's rear view mirror to trigger automations in home assistant. I went down a bit of a hardware rabbit hole and wrote a little writeup of my journey and a how-to. It's my first piece of public technical writing so I'm open to any feedback! https://bit.ly/3RnDzbT July 23, 2026 at 10:28PM

Show HN: LitigationBench. A Litigation Task-Based AI Benchmark https://bit.ly/4wXMlMD

Show HN: LitigationBench. A Litigation Task-Based AI Benchmark Adding to the sea of AI benchmarks, but with a focus on legal and litigation-based tasks and tests. E.g., hallucinating cases, misreading precedent, drafting, AI writing tics, etc. Developed as part of a litigation platform I've started, but not sharing this benchmark to promote that. Just thought the findings were interesting--namely, Anthropic's models (except for Haiku) producing zero hallucinated cases. Also, if anyone would like to see additional tests / benchmarks or models tested, let me know and I'll incorporate them into v3 if it makes sense. https://bit.ly/44LOkb3 July 23, 2026 at 02:11AM

Show HN: KageOps – An open-source, local-first alternative to Devin https://bit.ly/4wilr2p

Show HN: KageOps – An open-source, local-first alternative to Devin https://bit.ly/44Jef3c July 23, 2026 at 01:04AM

Show HN: 1,280 open USDZ furniture assets for VR/AR https://bit.ly/4vFQC6F

Show HN: 1,280 open USDZ furniture assets for VR/AR I created this collection because I wanted a openly downloadable collection of ordinary household objects for spatial-computing prototypes. Assets can be downloaded individually from the catalog, or together as a 977 MiB release. The collection was created by GPT 5.6 Sol end-to-end for design, specification, procedural Blender construction, packaging, and QA workflow. https://bit.ly/4w41j3b July 22, 2026 at 11:53PM

Show HN: MindBase – an LLM that maintains a wiki from your notes and papers https://bit.ly/4x0yrtw

Show HN: MindBase – an LLM that maintains a wiki from your notes and papers https://bit.ly/4bTjSzu July 22, 2026 at 05:27AM

Show HN: An MCP server that turns async-work practices into tools https://bit.ly/4gRAJpR

Show HN: An MCP server that turns async-work practices into tools More than a decade ago, I adopted the self-imposed rule, if I answer a question more than once, the third time I need to be able to answer with a URL. Today, I published one very large URL - a book distilling what I learned from helping people work remotely at GitHub, and I wanted to rethink my rule for the age of AI. What if, instead of a URL, I could create an interactive experience that could tailor the guidance to your particular situation? What I ended up building was an Open and Async Advisor MCP server. To install (in claude or any other AI): > claude mcp add open-async -- npx -y @open-and-async/mcp Transparently, yes, it's from a book I wrote which launched today, but the MCP server is open source and free to use. No purchase required. It knows the key principles of the book, and has specialized tools like `draft_decision_doc`, `convert_meeting_to_async`, `score_status_update`, `triage_sync_vs_async`. This is an experiment for me, and I'm genuinely curious if it's helpful for others. https://bit.ly/4b9bk7w July 21, 2026 at 05:06PM

Show HN: Superserve – Firecracker microVM sandboxes for long-running AI agents https://bit.ly/4wz3TPL

Show HN: Superserve – Firecracker microVM sandboxes for long-running AI agents Hey HN, I built Superserve, a compute layer that lets AI agents live inside isolated Firecracker microVMs with no session time limits. The problem I kept running into: most sandbox providers kill your agent after 24 hours. If you're running something autonomous that needs to work for days — refactoring a codebase, running tests in a loop — you're constantly fighting timeouts and rebuilding state. Superserve lets you snapshot a running VM at any point, fork it into parallel branches, and resume exactly where you left off. Each agent gets its own VM, no shared kernels. There's also a credentials broker so agents never touch raw API keys directly, and egress is locked to URLs you specify. You bring your own agent (Claude Code, Codex, etc.). We handle the durable compute underneath. TypeScript and Python SDKs, MCP support, open-source and self-hostable. Would love to hear feedback, especially from anyone building long-running agents. https://bit.ly/4vL0RXh July 21, 2026 at 11:59PM

Show HN: Ekko – post-quantum E2EE layer for Instagram, WhatsApp, Telegram Web https://bit.ly/4gJYoZi

Show HN: Ekko – post-quantum E2EE layer for Instagram, WhatsApp, Telegram Web Hi everyone, I am a big privacy activist and the amount of privacy concerns in the internet with the discussions around European Chat Control, Meta removing e2ee in Instagram and corporations harvesting personal data for AI training is on the rise. The closed source social media companies keep managing and storing our private keys, allowing them to effectively access all of our personal communications.. Many open source alternatives exist, but the problem I kept running into was not a lack of good private messengers. Signal, SimpleX, and other projects already do important work The problem was getting the people to move. A messenger is only useful when the person you need to reach is there. Asking friends, family, coworkers, or customers to abandon their existing chats is a very high barrier. Ekko takes a different approach. It runs as a browser extension on top of existing messengers. Both people still need Ekko, but they do not need to move their conversation. You can continue using the Instagram, WhatsApp, Telegram, or Messenger chat they already share. Actively building this and trying to achieve a seamless automatic encryption in the UI across all popular messengers and adding support across all browsers, IOS, android and social media.. Under the hood, Ekko uses hybrid X25519 + ML-KEM-768 and XChaCha20-Poly1305. Private keys are generated and kept on your device. You can claim an Ekko handle to make exchanging public keys easier, exchange invitations directly without an account, or self-host the public-key directory. Currently: - A Chromium browser extension, Experimental Firefox and Safari builds - Instagram, WhatsApp Web, Telegram Web, and Messenger integrations - A self-hostable key directory - Open-source client, protocol, and server code Early version Chrome Web Store: https://bit.ly/4fN1z1e... Source code: https://bit.ly/4fLTTMN Website and demo: https://bit.ly/4h7nqlt I would genuinely appreciate direct feedback especially from people familiar with applied cryptography, browser security, key verification, messenger integrations, potential solutions for iOS UI integration (faster than using browser w/ Safari extension) If you try it, please tell me what breaks or what feels confusing. Actively trying to make this better as a side project! If you discover a security issue, email kirill@useekko.app rather than posting it publicly. Looking for feedback! :) https://bit.ly/4h7nqlt July 21, 2026 at 01:39AM

Show HN: The0 – self-hosted runtime for trading bots, bring your own language https://bit.ly/4vHr1dp

Show HN: The0 – self-hosted runtime for trading bots, bring your own language So Im a solo developer who has always had an itch for algorithmic trading. Initially I started off learning how to trade algorithmically with Yves Hilpisch book "Python for Algorithmic Trading" after reading that book I was hooked and started building algorithmic trading bots. Initially these were separate python scripts that I ran on my local machine. That was a bad idea cause local machines are not reliable and I wanted to run my bots 24/7 365. In my actual career im a software engineer with experience in building distributed systems and fault tolerant web applications. I wasn't interested in deploying my code to managed services like MetaTrader, CTrader or QuantConnect etc because I wanted to have full control over my code and the environment it runs in. I also wanted to be able to run my bots in any programming language I wanted, not just Python. Sometimes I wanted to prototype a bot in Python and then rewrite it in C++ or Rust for performance reasons. Many at this point would have said why not use a framework like Lean or Freqtrade or Hummingbot. However I found that these frameworks were too opinionated and if you decide to use them then your bot is now part and parcel of their framework. I backtested my bots locally in my own specific way, and now with AI my agents can generate code, backtest and analyze the results all locally, no need to run any of it in the execution platform. I wanted bots I could deploy, version, update and monitor like any other software application. I also wanted to explore building something that creates a standardized way of running bots. This has been a 4 year journey and I made a lot of mistakes along the way. The application has seen 4 rearchitectures, 3 of which were basically complete rewrites. The first version was a python program and the bots were just modules that were loaded dynamically. The second was my serverless phase when I internally just wanted something that was online cron triggered and only works for me. The third was the first time I was dipping into kubernetes; more cloud native and the idiot in me decided to try make it a SaaS. The final form is a fully self-hosted runtime, api, cli and frontend that let you run bots as containers in a fault tolerant way both locally (through docker `the0 local`) and in a cluster (k8s) and monitor them with a minimalistic frontend. To support multiple languages there's a thin contract that the bots have to implement: a main(bot_id, config) function and a bot-config.yaml file. The runtime (written in Go) takes care of the rest, it supports C++, Rust, Python, JS/TS, C#, Scala and Haskell for those who are brave enough to try it. More on the architecture here: https://bit.ly/3TuNb57 If you want to play with the0 you can run it locally, guide here: https://bit.ly/4fbMKoV . The0 is open source and licensed under Apache-2.0: https://bit.ly/4wi6mOe I currently use the0 to run my own personal algorithmic trading bots on a single node k3s cluster on a $10/month Hetzner VPS. I have 18 bots running on 2 brokers (Alpaca, Bybit) and they have been running for months without issues. Some bots trade crypto, others stocks, some do risk analysis and others invest. Coolest bit is the API provides an MCP server so AI agents can query the state of the bots, look at their logs, monitor them and even update them. Slap an OpenClaw agent and you can effectively setup an autonomous AI quantitative trading system (good luck chasing Alpha). Now I must admit Lean has all the tools and far more quantitative prowess than the0, but I always felt it does too much. Each Lean engine runs one algorithm, and once you have lots of bots, running and managing all of them in production is left to you. That's the part the0 does, and its the only part it tries to do. If you find hiccups or have ideas for features Im all ears. More on the internals in my first comment. https://bit.ly/4wi6mOe July 20, 2026 at 02:49PM

Show HN: OTP Inspired actor supervisor based full stack templates https://bit.ly/4wjHi9y

Show HN: OTP Inspired actor supervisor based full stack templates https://bit.ly/4b1JmdL July 20, 2026 at 02:47PM

Show HN: I made a cute weight tracking app where you can raise a pet https://bit.ly/4hmPX6k

Show HN: I made a cute weight tracking app where you can raise a pet My girlfriend hated all the weight tracking apps out there because they felt really analytical and cold. So I figured I'd make a cute gamified weight tracker for her! Introducing Wooby! You can choose one of four pets to raise, and log your behaviors and watch your pet get happier. It gives you motivational messages as you log your weight and habits, and you can unlock furniture and decorate your pet's home as well. You can even play with your pet. It's totally free right now and we don't collect any data either so give it a try! https://apple.co/3T96ote July 20, 2026 at 06:37AM

Show HN: A self-hosted AI that turns Hacker News into a daily briefing https://bit.ly/4fJqYJh

Show HN: A self-hosted AI that turns Hacker News into a daily briefing Hi everyone, I read HN every day, but there was always more great content than I had time to read. I know there are already several HN summarizers on GitHub, and I tried some of them. They just didn't fit the workflow I wanted, so I decided to build my own. My project is a self-hosted app that automatically fetches top stories, summarizes them with AI, translates them into your preferred language, and prepares a personalized daily briefing in a nice customizable UI while you sleep. Maybe I'm not the only one who wanted this kind of workflow. I'd love to hear your thoughts, especially on what you think an ideal HN summarizer should do. https://bit.ly/4yNBeYL July 19, 2026 at 11:40PM

Show HN: Headroom – measure your GPU's true bandwidth ceiling for local AI https://bit.ly/4fIGh4R

Show HN: Headroom – measure your GPU's true bandwidth ceiling for local AI https://bit.ly/45e5H4k July 20, 2026 at 01:44AM

Show HN: Deploy AI agent in 5 lines of code https://bit.ly/4fHpwXQ

Show HN: Deploy AI agent in 5 lines of code https://bit.ly/44EoMwo July 19, 2026 at 11:57PM

Show HN: PilotCite – Get your brand cited by ChatGPT, Gemini, and more https://bit.ly/4gM8WXY

Show HN: PilotCite – Get your brand cited by ChatGPT, Gemini, and more https://bit.ly/4yvz3Zk July 19, 2026 at 08:17AM

Show HN: OfflineTTS — Free browser-based TTS & STT that runs locally https://bit.ly/4hlMg0M

Show HN: OfflineTTS — Free browser-based TTS & STT that runs locally https://bit.ly/4wura5n July 19, 2026 at 09:21AM

Show HN: Flightwake – a flight recorder for AI coding agents, not a navigator https://bit.ly/4pqQ7M2

Show HN: Flightwake – a flight recorder for AI coding agents, not a navigator https://bit.ly/44EMOHH July 19, 2026 at 02:14AM

Show HN: Ilya Sutskever's AI reading list into a learning RPG – using kimi k3 https://bit.ly/4wdUdtN

Show HN: Ilya Sutskever's AI reading list into a learning RPG – using kimi k3 I wanted to take kimi k3 for a spin. It turned my simple one sentence prompt to this. Repo here. https://bit.ly/3RJilVV Well, I'm mindblown. Very humbling for me as a software engineer. Took couple hours for it to build this completely autonomously. And it was all from its mobile app. It couldn't render this though from within the app - it does have a feature to preview any website and publish it on kimi's domain - but it didn't work for this. I had to put it on github pages. It doesn't store anything btw - all progress is tracked in your browser storage. https://bit.ly/4ppUE1f July 18, 2026 at 11:54PM

Show HN: Find someone in the dark – light them or light yourself? (Three.js) https://bit.ly/4fdBKpC

Show HN: Find someone in the dark – light them or light yourself? (Three.js) https://bit.ly/4gKPLxG July 18, 2026 at 07:32AM

Show HN: NS6 – Find your perfect domain https://bit.ly/4fo79pK

Show HN: NS6 – Find your perfect domain https://bit.ly/4hk1FPd July 18, 2026 at 04:19AM

Show HN: Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE https://bit.ly/4wItLrQ

Show HN: Qwen3.6-35B-A3B on a 16 GB M1 Pro with SSD-streamed MoE https://bit.ly/4b2shQR July 18, 2026 at 12:20AM

Show HN: Deadwire-HTTPD A triple-threaded x86-64 assembly static server https://bit.ly/4wIpMeP

Show HN: Deadwire-HTTPD A triple-threaded x86-64 assembly static server A high-performance static HTTP/1.0 server driven by a bespoke triple-thread architecture (Supervisor, Acceptor, Engine) delivering nanosecond-level processing using raw x86-64 assembly and pure Linux syscalls. https://bit.ly/4ysVQ8b July 17, 2026 at 09:51AM

Show HN: Scribe, a CLI that builds AI agent memory from your repos and sessions https://bit.ly/4pArJrt

Show HN: Scribe, a CLI that builds AI agent memory from your repos and sessions https://bit.ly/4yqzEvl July 17, 2026 at 05:44AM

Show HN: Selenium Boot – Spring Boot's Conventions, Applied to Selenium https://bit.ly/3T11kqJ

Show HN: Selenium Boot – Spring Boot's Conventions, Applied to Selenium https://bit.ly/4ysCgsE July 17, 2026 at 03:39AM

Show HN: Moltshit.com – An Imageboard for AI Agents https://bit.ly/4wNzb4W

Show HN: Moltshit.com – An Imageboard for AI Agents Moltshit.com is a place to waste some GPU cycles doing dumb stuff with LLMs. Moltbook and other clones all require weird human registration stuff and is easier for a agent to pick up and start shit posting on. https://bit.ly/4pv4OxU July 16, 2026 at 11:54PM

Show HN: Autoportrait- Painting Timelapses in JavaScript https://bit.ly/4feiQR3

Show HN: Autoportrait- Painting Timelapses in JavaScript https://bit.ly/4feiREB July 15, 2026 at 11:35PM

Show HN: Asciitopia – a library of animated ASCII art patterns https://bit.ly/4w4PESc

Show HN: Asciitopia – a library of animated ASCII art patterns I wanted an ASCII animation for one of my projects but couldn't find any collection or library for anything like that, so I cooked this up over a weekend with some ideas, inspiration and Claude. Feel free to add your own patterns! https://bit.ly/4boIPme July 15, 2026 at 12:46AM

Show HN: Mechacraft.io – Browser Vehicle Builder https://bit.ly/3RyVpZu

Show HN: Mechacraft.io – Browser Vehicle Builder https://bit.ly/4ppEkh9 July 14, 2026 at 11:10PM

Show HN: Free and open source browser extension for web automation https://bit.ly/4hc5G8h

Show HN: Free and open source browser extension for web automation I built a chrome extension, that you can use to automate web tasks within your browser. No need of any separate backend. The extension is standalone and you can use it for free. It also support browser built-in models (like gemini-nano), which you can use for basic tasks like summarizing. Please have a look at Waffy.io. Also drop your honest review. Contributions are always welcome... Thanks https://bit.ly/4pjNOu5 July 14, 2026 at 02:19AM

Show HN: Sx 2.0 – Share AI skills with your team through a Dropbox folder https://bit.ly/4gUVTDJ

Show HN: Sx 2.0 – Share AI skills with your team through a Dropbox folder Hi all, author here. SX started as a CLI to let developers share skills across AI clients without having to rely on git for storage. This allowed sharing at the Repo/Team/Org and Personal level. However, the more we spoke to users the more we realized that non-technical users were actually using skills more and more but they had no way to share. And there was no way you were going to get your legal team to install and learn git. SX 2.0 is targeting non-technical teams by adding a native Mac, Windows and Linux app. Our vault format was reworked so it can be used directly as a claude or codex plugin. And by storing your vault in Dropbox, Google Drive, iCloud or others you can be up and sharing in under a minute. 2.0 also adds an extension system with extensions that manage Skill Evals, LLM de-duping, metics and much more https://bit.ly/4gUVTUf . It's Apache-2.0 and you can download it here https://bit.ly/4gy0TxP . https://bit.ly/4aSeg8t July 14, 2026 at 12:26AM

Show HN: ContextVault – Shared memory layer for your AI and your team https://bit.ly/4ph3IFI

Show HN: ContextVault – Shared memory layer for your AI and your team Hi HN, I'm Kevin. I built ContextVault because I kept running into the same problem with AI tools. Every project accumulated prompts, coding conventions, architectural decisions, examples, and other pieces of context that made the models significantly more useful. The problem was that this information quickly became fragmented. Some lived in ChatGPT Projects, some in Claude, some in Markdown files, some in internal documentation, and some only existed in previous conversations. Late last year, I realized several people on our team were solving the same problems independently because previous work was difficult to discover. I assumed this problem existed in other large organizations, so I started experimenting with a shared context store. I started with a local proof of concept and a rough MCP server. If I asked questions like "have we done this before?", the AI could search the database and find the most relevant item to review. If a conversation produced something worth remembering, I could say "save what we learned to the vault." After using that workflow for a few months, I found myself relying on it every day. I decided to make it available to others. I've never built a product before, and I thought it would be a valuable learning exercise to do. ContextVault is a a product for storing and organizing reusable context that can be shared across people, projects, and AI tools. Instead of copying the same instructions into every conversation, you can store them once and retrieve them through our MCP server. It is not limited to any one AI client. Your team can use ChatGPT, Codex, Claude, and Gemini and save/read from the vault all the same. It currently supports: - OAuth support for GitHub, Google, Microsoft, and GitLab - Structured context records with metadata - Multi-user organizations with role-based access - MCP server for all AI clients that support MCP - Organization-scoped storage keeps tenant data separated - Group visibility rules decide which memories each member can search - Authenticated MCP access ties every request back to a real user and workspace - Feedback signals can be captured now and used to improve ranking later - Supports desktop versions of AI clients, not just their CLI versions (mobile app support should also work) The backend is built with PostgreSQL, pgvector, Node.js, and TypeScript. The frontend uses Next.js, React, Tailwind CSS, and shadcn/ui (frontend is not my strong suit, please be kind). Authentication is handled with Clerk and billing with Stripe. I started building this for my own workflow, but after relying on it for several months I decided to make it available to others. We soft launched a few weeks ago, and I find it useful as a daily tool. Essentially, ContextVault offers a way to track memories and context, distribute them instantly to your team, and help reduce duplicated work. I'd be interested in feedback on a few things: - How are you managing reusable AI context today? - Are you relying on similar tools, or do you keep everything in Git or Markdown? - If you've built something similar, what did you learn that you would do differently? You can see the product here: https://bit.ly/4hgU2ca https://bit.ly/4hgU2ca July 14, 2026 at 12:22AM

Show HN: Hologram, photo management and culling built with Tauri https://bit.ly/4vmbWhb

Show HN: Hologram, photo management and culling built with Tauri Hello Hacker News photographers! Yes, this is essentially my take on photo colling and management, similar to the features that Lightroom and Darktable already have. Because I shoot in JPEG+RAW, my workflow looks like me going through my JPEG images and then eliminating the JPEGs I don't like afterwards in addition to their corresponding RAWs. At least on my old MacBook, the JPEGs were faster to load than the RAW photos (probably a combination of CR2, the file my EOS 40D, not having embedded JPEG previews and my buggy macOS version). Hologram would be my way of making this workflow easier to do, especially with keyboard shortcuts. I also never liked the star-based system on Lightroom or Darktable, so I implemented Pick and Reject instead (which matches what I would otherwise do with deleting photos to my system trash when I cull in the Finder app) Anyways, with my new R7 I found that bursts got more annoying to cull so I decided to create autocull on Hologram as well. This would analyze your photos and help you suggest which photos in a burst to keep, or which photos to keep in a shoot in general. Currently, this is not notarized or whatever, but let me know what you guys think. https://bit.ly/3QR13Gd July 13, 2026 at 12:10AM

Show HN: Codebase Posters – turn any Git repo into generative poster art https://bit.ly/4fece3C

Show HN: Codebase Posters – turn any Git repo into generative poster art npx codebase-posters inside any git repo opens a local exhibition: 18 pieces painted live from your commit history. everything renders from git log, nothing leaves your machine. https://bit.ly/4bBZG52 July 12, 2026 at 11:26PM

Show HN: Levee – a self-tuning circuit breaker and concurrency limiter for Go https://bit.ly/4yi25vA

Show HN: Levee – a self-tuning circuit breaker and concurrency limiter for Go Rate limiters and circuit breakers work wonderfully well when they’re configured for the load and available capacity. But load, capacity, and latency drift over time, and keeping those settings current requires continuous effort. So I built Levee to be a hands-off, adaptive, easy to configure traffic governor. Levee is configured with a success-rate target and timeout. It then continuously monitors the workload performance characteristics to detect downstream capacity exhaustion or failures. It can also spot a surge from growing concurrency before failures arrive. It runs in-process, uses a small, fixed amount of memory, has zero dependencies, and processes millions of requests per second. In a deterministic 10-node mesh simulation, Levee outscored carefully tuned static rate limiters/breakers deployed throughout the mesh, while recording fewer failures and no node crashes. https://bit.ly/4bozc75 July 12, 2026 at 02:22AM

Show HN: Dotenv-Diff v3.0.0 https://bit.ly/4pgthH3

Show HN: Dotenv-Diff v3.0.0 Long time since i last posted updated about dotenv-diff, a lot of new features since then https://bit.ly/4dbmgmJ July 7, 2026 at 09:54PM

Show HN: Krbn, a pencil-style 3D renderer with SVG output https://bit.ly/4wCDHmP

Show HN: Krbn, a pencil-style 3D renderer with SVG output Krbn is a childhood dream I finally got to research & prototype (from a hospital bed of all places), during a medical break from my normal work: a rendering engine that draws 3D scenes the way a technical sketch artist would. It asks "which lines would an artist draw and what would they leave out?" Basically strokes are derived exactly from geometry, rather than sampling. True conics, quartics etc. So there is no shading model, it's replaced by hatching (either flat or following the curvature of the object). There's no alpha channel, the gaps between lines do the work as on paper. It introduces hand-wobble (which is seeded, so animations don't "boil" between frames) and various other things; the example gallery shows more. With all that, output is byte-stable, i.e. two successive renders will cause zero changes in Git. Full disclosure, since it matters here: this was built with significant AI assistance, deliberately, as an experiment in how far a carefully directed human-AI collaboration can get on a hard rendering problem. The briefs are in the repo - judge for yourselves. Gallery: https://bit.ly/4wtPnrK The longer story: https://bit.ly/4wtPiEs... P.S. There's no pitch here... just an invitation for a weekend skim over something I find fascinating. https://bit.ly/4wwROtF July 11, 2026 at 06:51AM

Show HN: @playbykey/theory - Music theory TypeScript engine and MCP server https://bit.ly/44I336Z

Show HN: @playbykey/theory - Music theory TypeScript engine and MCP server https://bit.ly/4pi2JFt July 11, 2026 at 03:15AM

Show HN: We beat Cloudflare's bot detection (open-source stealth browser) https://bit.ly/4ylYe0K

Show HN: We beat Cloudflare's bot detection (open-source stealth browser) https://bit.ly/4fuMVf2 July 11, 2026 at 01:26AM

Show HN: Debloat Slack – Get rid of Slackbot, AI upsells and other annoyances https://bit.ly/4eYM6tm

Show HN: Debloat Slack – Get rid of Slackbot, AI upsells and other annoyances https://bit.ly/4aN350J July 10, 2026 at 03:08AM

Show HN: Fortress – Give your agents unlimited access to the web https://bit.ly/4gq4tdf

Show HN: Fortress – Give your agents unlimited access to the web i personally believe that the internet is the best thing we've ever built, and arguably, nothing we made before comes close. now agents can use it too, but the web treats them as second-class. every agent works for a person, so whatever it keeps from agents it keeps from us. we believe that if we let them in, each of us gets the whole of what we built, a thousand times over. and to add to that, democratization of tools that allow this is essential, despite the fact that there will always be bad actors. so, we built fortress, which is an open-source stealth chromium engine. it is a recompiled fork that corrects the browser fingerprint from inside the engine: the surfaces bot detectors read, canvas, webgl, audio, fonts, navigator, and about thirty more, are patched in chromium's c++, with no javascript layer sitting on top for a page to catch. it beats the hardest bot detectors on the planet, works fully locally and is open source for y'all to see the patches we've made. and it comes with an mcp, so you can use it with your agents without having to do any major setup or code changes. do give it a try here! https://bit.ly/4wnq6PW July 10, 2026 at 01:57AM

Show HN: I built a free app for New Yorkers to save money on groceries https://bit.ly/3STjlqT

Show HN: I built a free app for New Yorkers to save money on groceries I built this because I see that grocery savings are achievable in NYC. People usually just go to the store they're used to going to, and it's rarely worth the effort of combing through card cashback, weekly coupons, CPG rebates. Most people leave real money on the table by not stacking them, and even more don't even know that these deals are out there.... so I built a way to automate it. You can use it for free, no login, currently NYC-only with ~690 stores. I built it so that you just search whatever you want (use commas if you want to search multiple items). Or - use the AI tool to help shop for you. If you're curious, it's powered by a trained LLama model. Honest limitations are coverage and freshness. Id love some feedback on where the data looks wrong or is stale. Question for the room - what to prioritize if you're working with messy, multi-source retail/pricing data? Is freshness or coverage the top priority if you cant get a uniform response from every source? curious on what to prioritize here. https://bit.ly/4fqTaR4 July 10, 2026 at 01:17AM

Show HN: OpenScreenShot: open-source full-page screenshot and annotation tool https://bit.ly/4wDQBRD

Show HN: OpenScreenShot: open-source full-page screenshot and annotation tool https://bit.ly/4gpf9ZC July 9, 2026 at 02:19AM

Show HN: Cyrinx (36kbps Acoustic Transport) https://bit.ly/4p81l81

Show HN: Cyrinx (36kbps Acoustic Transport) Working with Fable 5, a MacBook, and a Pixel phone, I built an acoustic transport library that is several orders of magnitude faster than existing SoTA open source options like ggwave, quiet, minimodem, or Chirp. Paper: https://bit.ly/4gtXvUy Apache 2.0 source: https://bit.ly/4f6MjLc https://bit.ly/4fb1hQp July 9, 2026 at 01:59AM

Show HN: Frugon – Find which LLM calls a cheaper model could handle (local, MIT) https://bit.ly/3SMUCo8

Show HN: Frugon – Find which LLM calls a cheaper model could handle (local, MIT) I started leaning in on AI heavily this year, as I wanted to get more done autonomously, but then my token usage climbed dramatically to the point where my weekly quota would run out before the end of the week, sometimes a couple of days into the week. I realised I had to do something about it else I'd have to double my spend. So I decided to start tracking my cost per task type. This revealed that a lot of my spend went to searches/scans or simple things like scouting tasks. I then decided to turn this into a simple CLI tool that can be used to read your OpenAI-style logs locally, and analyze the cost and compare this spend to other models, then show you how much you could potentially save by switching those calls to a cheaper model. When you run analyze you get an offline estimate priced against LiteLLM and gated by LMArena tiers. The general savings bands come from the research published by RouteLLM; but you can confirm this yourself using 2 commands --measure (shows the prompt-response output side by side) and --judge (a model chosen to do the comparisons). These send a sample of the prompts from the logs to the candidate models - either the default choice or set by you. This call goes directly to the model provider (never through me) as any normal LLM call would, and the response is shown and judged to either be better or worse or a tie. It's deliberately small, because I tend to over complicate/think things sometimes: analyze + capture + a few commands, doing three jobs. Cost, quality visibility, routing recommendation. Nothing is hosted. capture is an optional local proxy on your own machine, and there's no endpoint in the path of your data. You can confirm this by checking the source. I included a demo so you can check out the output. It has a synthetic 56k call log (a month's worth) showing how costs can drop from $549.46 to $343.91 a month. A 37.4% saving. Try it: uvx frugon analyze --demo or uv tool install frugon Then point it at your own logs. All feedback is welcome, especially any on the routing/quality logic, or anything else, good or bad. https://bit.ly/4ybqv9T July 7, 2026 at 01:20PM

Show HN: I ran 70 MCP servers in a sandbox and logged what they do https://bit.ly/4fqy8lt

Show HN: I ran 70 MCP servers in a sandbox and logged what they do https://bit.ly/4ybhei3 July 8, 2026 at 11:44PM

Show HN: Turbo – An open-source, fast HTTP server with a real-time config GUI https://bit.ly/4wxfjD3

Show HN: Turbo – An open-source, fast HTTP server with a real-time config GUI https://bit.ly/4grqAAa July 8, 2026 at 01:17AM

Show HN: Fortress – a stealth Chromium so your agents stop getting blocked https://bit.ly/3RkaEW5

Show HN: Fortress – a stealth Chromium so your agents stop getting blocked https://bit.ly/4wnq6PW July 8, 2026 at 01:08AM

Show HN: Free Mermaid Diagram Editor https://bit.ly/3Tmto7S

Show HN: Free Mermaid Diagram Editor I've been slowly adding some new free tools to Moxie Docs (partly for SEO, partly to illustrate some of our feature sets before any commitment) for some reason this mermaid editor one blew up on Google rankings so I figured I'd share in case people find it useful! We also have ADR, AGENTS.md, LLMs, and a few other free tools. https://bit.ly/4ePcsiP July 8, 2026 at 12:29AM

Show HN: Autoops – Multi-region data and service mesh operated by a Makefile https://bit.ly/4vkxzOW

Show HN: Autoops – Multi-region data and service mesh operated by a Makefile Hi HN, Stefan here. autoops is an infrastructure automation framework I have been using at my previous company and is now opensourced. It has been the base layer running various products and projects, and also for quickly standing up client infra. It works with Debian-based systems (apt) and sets up a WireGuard mesh with peer discovery and built-in DNS (Wesher), a distributed S3-compatible object store (Garage), and a reverse proxy and load balancer (Traefik). It supports service autodiscovery (Traefik-kop) and can be horizontally scaled to up to 150-200 nodes. As a classical example of "roll your own k8s subset using scripting", it is not yet fully integrated and currently, you need 1) to define at least a PyInfra inventory, 2) depending on whether you run containered services, a Docker Compose file, and 3) for horizontal scaling with autodiscovery, a Traefik config. The PyInfra scripts are put together in a Makefile, but that is pretty self explanatory. autoops doesn't trust supply chains, so you need to out-of-band put a couple of binaries in the general assets/ folder, and if you do containers, provide a path that contains directories named after each service and holding its Dockerfile and other build assets. Also, it's almost arm64 compatible (needs binaries for Docker and the crowdsec bouncer), can do NAT traversal (using my fork of Wesher), and container draining (using docker-rollout). Feedback is welcome. https://bit.ly/4p3NmQE July 6, 2026 at 10:59PM

Show HN: Logo Design for Busy Founders https://bit.ly/4eM8SGj

Show HN: Logo Design for Busy Founders General purpose illustration tools like adobe illustrator or affinity have a great amount of flexibility but come at the cost of complexity that isn't needed for a logo design tool. So I trimmed down the fat to a minimal set of 10 tools acting on a logo grid, when combined together makes it easy to build quite a surprising variety of logo marks pretty fast. This was a very interesting project unlike most of the work i've done over the years, this iteration (the 4th) came from progressively whittling down (vs up) affordances, if a combination of tools could do what one did, it was cut, if that tool didn't seem to behave cohesively with the rest (perhaps potentially breaking the user's mental model of the editor) it was cut. Initially i had features like layers, multiple fill colors. Naively i felt my goal was to build a minimal set of tools that achieved "logo-completeness", but i realised that would just give me a terrible Illustrator clone vs balancing learning curve to expressivity. There's still some wonky behaviour related to selecting/cutting, this will be fixed once I can put a finger to what this wonkiness is actually. It exports to SVG, transparent PNG, PSD and more. https://bit.ly/4y6kjA6 July 5, 2026 at 11:50PM

Show HN: Tracking how much of the HN front page is AI-generated https://bit.ly/3R3uswC

Show HN: Tracking how much of the HN front page is AI-generated For the past few months, I've been sending every story that reaches the HN front page through Pangram's AI detector and noting the scores. The reason I made it is that I kept noticing posts that sounded like AI-generated to me. Sometimes the comments pointed it out, sometimes a post was near the top all day and no one said a word. I wondered if the share was really increasing or if I was just primed to see slop everywhere. How it operates: The site identifies the top 30, gets each article, and evaluates the text using Pangram. Besides the live front page view, there are daily and monthly trends, with leaderboards for domains and authors that keep scoring high. I personally find it quite helpful as a sanity check on my own intuition before declaring something AI in the comments. 6,500+ stories in, it turns out the front page is still very human after all, which is the part that shocked me the most. A fraction of 13% of stories were AI flagged over the last 30 days. That's slowly ramping up (roughly a point higher than the previous month) but still not close to the feeling of 'everything is slop now' I had. At the moment it's 1 flagged story out of 30. The flagged ones still manage to get by quite well. One of them is at #6 today with 545 points and a 99% score, and the discussion section is divided on whether it's AI or not. Standard disclaimers: a detector score is not a piece of evidence, false positives do occur, and a high score can also be the result of a human coming up with the ideas and then using a model for the prose. To me, it is an invitation to examine the matter more closely rather than a judgment. Feel free to ask me anything about the setup. And yes, I ran this post through the detector before submitting it. https://bit.ly/4fkFQh2 July 5, 2026 at 08:17AM

Show HN: I built an encrypted BLE dongle for pasting stuff to air-gapped devices https://bit.ly/4vOwd01

Show HN: I built an encrypted BLE dongle for pasting stuff to air-gapped devices Definitely one of those "20 minute adventure gone wrong" projects where all I wanted initially was a quick wireless rubber ducky for bitlocker keys and the like and then I kept adding stuff like AES-256..... Currently working on adding WebAuthn/FIDO support because the hardware is already there and scope creep is a lifestyle at this point. Would love feedback, especially on the security side. Repo and PCB files are fully open source. https://bit.ly/4aEepvX July 4, 2026 at 10:13PM

Show HN: Reading Assistant Physical Books Meta RayBans https://bit.ly/4wkdt8o

Show HN: Reading Assistant Physical Books Meta RayBans Reading technical books is hard. Unknown words, confusing phrases, and misunderstood concepts requires opening your phone, starting Claude, and working with Sonnet through a series of exchanges, before finally getting it. Focusing back on reading after such a context switch can be difficult. Repeated multiple times and your attention span is gone. Fix: An assistant understands your book deeply and answers inquiries through voice while you read, side-stepping the current process entirely. All you have to do is: - Upload a PDF version of your physical book and start reading - Say "Hey Lumos" along with your inquiry ("why does det(A) mean the matrix loses volume?") - Assistant researches the contents of the book and responds - Continue reading until you need help again It's in extreme beta but works well enough where I can't read a book without it. If you're interested in trying it out, reach out. July 3, 2026 at 11:07PM

Show HN: Pieces – Social network for people https://bit.ly/3SxJ48a

Show HN: Pieces – Social network for people Hey HN, long time lurker first time poster. I built a social network called PIECES. After building a private blog last year after I had to get off IG and Substack, I decided to productize it. It's here now. It has a dedicated web experience + iOS/Android. Would love if you tried it out! https://bit.ly/4p9aiOE July 1, 2026 at 06:30PM

Show HN: Capcat – CLI/TUI to Archive Articles as Markdown and HTML (FOSS) https://bit.ly/44K4bXq

Show HN: Capcat – CLI/TUI to Archive Articles as Markdown and HTML (FOSS) Capcat is a python based CLI/TUI FOSS utility for Ethical archiving of given website or RSS source. The github repo: https://bit.ly/4vemgb0 It is generated with NLP, context-engineering, spec-driven development and LLMs. Fully functional at https://bit.ly/3QDrEq6 , with instructions for usage and documentation. The project started from my personal needs of simple archiving with structure and moved to product design/MVP exercise. I am longtime HN user, and the most value I got in years of reading is always deep in the comments section. For HN Capcat uses the official API, with rate-limits, identifies honesty with clear user agent and skips paywalled content. All usernames are anonymized with a link to the user profile. The content is delivered in Markdown format (Obsidian ready with frontmatter) and optional HTML with dark/light themes. Every source has its own YAML config file for separate control and PDF size limiter. In the folder users have an option to change the HTML theme with a minimal CSS design-system. Please consider that my focus as a product designer is in UX. I have enough of a general culture and software development principles but the code is not validated, and my decisions in building may have a limitation. Feedback is welcomed. Thanks in advance. https://bit.ly/4gdKWN4 July 2, 2026 at 11:37PM

Show HN: Salt – a systems language with Z3 theorem proving in the compiler https://bit.ly/4ffWCxG

Show HN: Salt – a systems language with Z3 theorem proving in the compiler https://bit.ly/4wnd6tP July 1, 2026 at 06:05PM