Show HN: Quillium, Git for Writers https://bit.ly/4c0H92U

Show HN: Quillium, Git for Writers This is a tool which lets you easily manage different versions of ideas, helpful for writing essays. I've found myself wanting this every single time I go through the drafting process when writing, and I've been frustrated every time I find myself accidentally working on an old draft just because there was a paragraph that I liked better. This solves it. I hope the community like this as much I enjoyed working on it! Note that it's currently a beta waitlist because there's some bugs with the undo/redo state management and so I want to dogfood it for a bit for reliability. It says April 2nd, but I may allow earlier beta testers. https://bit.ly/4bFReRH March 23, 2026 at 01:22AM

Show HN: Plot-Hole.com a daily movie puzzle I made https://bit.ly/47C1U2H

Show HN: Plot-Hole.com a daily movie puzzle I made https://bit.ly/4brdZd9 March 23, 2026 at 01:15AM

Show HN: Refrax – my Arc Browser replacement I made from scratch https://bit.ly/4ssbdKD

Show HN: Refrax – my Arc Browser replacement I made from scratch Open the same tab in two browser windows. In Chrome or Safari, you get two unconnected pages. In Arc, one window shows a placeholder. In Zen, it silently creates a duplicate. In Refrax, the browser I built, both windows show the same page updating live. The same web page, in as many windows as you want. This shouldn't be possible. WebKit's WKWebView can exist in exactly one view hierarchy at a time. With macOS 26, Apple added a SwiftUI API separating WebView from WebPage, so you can end up with multiple views referencing the same page. But if you try it, your app crashes. WebKit source code has a precondition with this comment: "We can't have multiple owning pages regardless, but we'll want to decide if it's an error, if we can handle it gracefully, and how deterministic it might even be..." So here's how I did it. CAPortalLayer is an undocumented private class that's been in macOS since 10.12. It mirrors a layer's composited output by referencing the same GPU memory, not copying it. Every scroll, animation, or repaint reflects instantly. This is what powers Liquid Glass effects, the iOS text selection magnifier, and ghost images during drag and drop. Apple uses portals for effects. I use them to put the same web page in two windows. Refrax keeps one real WKWebView per tab and displays a CAPortalLayer mirror everywhere else. When you click a different window, the coordinator moves the real view there and the old window gets a portal. You can't tell which is which. This sounds simple in theory, but making this actually work seamlessly took quite a lot of effort. Each macOS window has its own rendering context, and the context ID updates asynchronously, so creating a portal immediately captures a stale ID and renders nothing. The portal creation needs to be delayed, but delaying creates a visual gap. I capture a GPU snapshot using a private CoreGraphics function and place it behind the portal as a fallback. Another hard part is that none of it is documented. Portals are very capricious and would crash the app if you use them incorrectly. I had to inspect the headers and then disassemble the binaries to explore exactly how it works in order to build something robust. I never worked on a browser before this, I've only been a user. I started using Arc in 2022. I remember asking for an invite, learning the shortcuts, slowly getting used to it. I didn't like it at first as it had too much Google Chrome in it for my taste, and I'd been using Safari at the time. But it grew on me, and by the time it was essentially abandoned and sold to Atlassian, I couldn't go back to Safari anymore. I tried everything: Zen, SigmaOS, Helium. None felt right, and I didn't want another Chromium fork. WebKit ships with the OS, but all you get is the rendering engine. Tabs, history, bookmarks, passwords, extensions, everything else has to be made separately. And so, being a very reasonable person, I decided to make my own Arc replacement from scratch. And I did. Refrax is built in Swift and Objective-C with no external dependencies. The app itself is less than 30 MB. I have 393 tabs open right now using 442 MB of RAM; 150 tabs in Safari was already over 1 GB. I've been using it daily for over a month, and so have some of my friends. The portal mirror is just one feature. The same approach, finding what Apple built for themselves and using it to create something they didn't think about, runs through the entire browser. You can tint your glass windows with adjustable blend modes and transparency. The sidebar in compact mode samples the page and matches the colors. And it has support for Firefox and Chrome extensions. The alpha is public. Download from the linked website, enter REFRAX-ALPHA-HACKERNEWS to activate. No account needed. Telemetry is crash reports and a daily active-user ping, nothing else. And if you find a bug – I built this alone, so I'll actually read your report. https://bit.ly/4bs6AdM March 22, 2026 at 11:52PM

Show HN: An event loop for asyncio written in Rust https://bit.ly/4sBBVR2

Show HN: An event loop for asyncio written in Rust actually, nothing special about this implementation. just another event loop written in rust for educational purposes and joy in tests it shows seamless migration from uvloop for my scraping framework https://bit.ly/4lL0CIq with APIs (fastapi) it shows only one advantage: better p99, uvloop is faster about 10-20% in the synthetic run currently, i am forking on the win branch to give it windows support that uvloop lacks https://bit.ly/4v2jgQn March 21, 2026 at 11:12PM

Show HN: Travel Hacking Toolkit – Points search and trip planning with AI https://bit.ly/3PlmMF2

Show HN: Travel Hacking Toolkit – Points search and trip planning with AI I use points and miles for most of my travel. Every booking comes down to the same decision: use points or pay cash? To answer that, you need award availability across multiple programs, cash prices, your current balances, transfer partner ratios, and the math to compare them. I got tired of doing it manually across a dozen tabs. This toolkit teaches Claude Code and OpenCode how to do it. 7 skills (markdown files with API docs and curl examples) and 6 MCP servers (real-time tools the AI calls directly). It searches award flights across 25+ mileage programs (Seats.aero), compares cash prices (Google Flights, Skiplagged, Kiwi.com, Duffel), pulls your loyalty balances (AwardWallet), searches hotels (Trivago, LiteAPI, Airbnb, Booking.com), finds ferry routes across 33 countries, and looks up weird hidden gems near your destination (Atlas Obscura). Reference data is included: transfer partner ratios for Chase UR, Amex MR, Bilt, Capital One, and Citi TY. Point valuations sourced from TPG, Upgraded Points, OMAAT, and View From The Wing. Alliance membership, sweet spot redemptions, booking windows, hotel chain brand lookups. 5 of the 6 MCP servers need zero API keys. Clone, run setup.sh, start searching. Skills are, as usual, plain markdown. They work in OpenCode and Claude Code automatically (I added a tiny setup script), and they'll work in anything else that supports skills. PRs welcome! Help me expand the toolkit! :) https://bit.ly/47ObeAl https://bit.ly/47ObeAl March 21, 2026 at 10:25PM

Show HN: AgentVerse – Open social network for AI agents (Mar 2026) https://bit.ly/4rJtaDi

Show HN: AgentVerse – Open social network for AI agents (Mar 2026) https://bit.ly/47WxiJ2 March 21, 2026 at 02:25AM

Show HN: Rover – turn any web interface into an AI agent with one script tag https://bit.ly/4blbIAg

Show HN: Rover – turn any web interface into an AI agent with one script tag https://bit.ly/3NAOc9a March 21, 2026 at 01:58AM

Show HN: Vibefolio – a place to showcase your vibecoded projects https://bit.ly/47h4FGh

Show HN: Vibefolio – a place to showcase your vibecoded projects Over the last months, more people are shipping small apps, experiments, and side-projects at a much higher pace. I'm one of them and initially created a showcase page for myself to track them but this week decided to create something for others. Happy to read feedback on how to improve it further! https://bit.ly/47fd3pN March 20, 2026 at 09:53PM

Show HN: Cybertt – Cybersecurity Tabletop https://bit.ly/47x7hQH

Show HN: Cybertt – Cybersecurity Tabletop https://bit.ly/3PmIIzx March 20, 2026 at 10:29AM

Show HN: Download entire/partial Substack to ePub for offline reading https://bit.ly/4uGIhQO

Show HN: Download entire/partial Substack to ePub for offline reading Hi HN, This is a small python app with optional webUI. It is intended to be run locally. It can be run with Docker (cookie autodetection will not work). It allows you to download a single substack, either entirely or partially, and saves the output to an epub file, which can be easily transferred to Kindle or other reading devices. This is admittedly a "vibe coded" app made with Claude Code and a few hours of iterating, but I've already found it very useful for myself. It supports both free and paywalled posts (if you are a paid subscriber to that creator). You can order the entries in the epub by popularity, newest first, or oldest first, and also limit to a specific number of entries, if you don't want all of them. You can either provide your substack.sid cookie manually, or you can have it be autodetected from most browsers/operating systems. https://bit.ly/4uwnXRY March 20, 2026 at 04:36AM

Show HN: Screenwriting Software https://bit.ly/3Phmteo

Show HN: Screenwriting Software I’ve spent the last year getting back into film and testing a bunch of screenwriting software. After a while I realized I wanted something different, so I started building it myself. The core text engine is written in Rust/wasm-bindgen. https://bit.ly/47cYh2P March 20, 2026 at 03:07AM

Show HN: Browser grand strategy game for hundreds of players on huge maps https://bit.ly/41cC0i3

Show HN: Browser grand strategy game for hundreds of players on huge maps Hi HN, I've been building a browser-based multiplayer strategy game called Borderhold. Matches run on large maps designed for hundreds of players. Players expand territory, attack neighbors, and adapt as borders shift across the map. You can put buildings down, build ships, and launch nukes. The main thing I wanted to explore was scale: most strategy games are small matches, modest maps, or modest player counts, but here maps are large and game works well with hundreds of players. Matches are relatively short so you can jump in and see a full game play out. Curious what people think. https://bit.ly/4uDPCAC Gameplay: https://youtu.be/nrJTZEP-Cw8 Discord: https://bit.ly/4uEbuvu https://bit.ly/4uDPCAC March 16, 2026 at 09:51AM

Show HN: Fitness MCP https://bit.ly/4sr8Jwo

Show HN: Fitness MCP There's no external MCP for your fitness (Garmin / Strava) data, so we built one. https://bit.ly/4uCviiR March 19, 2026 at 03:00AM

Show HN: ATO – a GUI to see and fix what your LLM agents configured https://bit.ly/476fStf

Show HN: ATO – a GUI to see and fix what your LLM agents configured https://bit.ly/476fSJL March 19, 2026 at 01:28AM

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training https://bit.ly/4bGv6H0

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training I replicated David Ng's RYS method ( https://bit.ly/4ll5ILb ) on consumer AMD GPUs (RX 7900 XT + RX 6950 XT) and found something I didn't expect. Transformers appear to have discrete "reasoning circuits" — contiguous blocks of 3-4 layers that act as indivisible cognitive units. Duplicate the right block and the model runs its reasoning pipeline twice. No weights change. No training. The model just thinks longer. The results on standard benchmarks (lm-evaluation-harness, n=50): Devstral-24B, layers 12-14 duplicated once: - BBH Logical Deduction: 0.22 → 0.76 - GSM8K (strict): 0.48 → 0.64 - MBPP (code gen): 0.72 → 0.78 - Nothing degraded Qwen2.5-Coder-32B, layers 7-9 duplicated once: - Reasoning probe: 76% → 94% The weird part: different duplication patterns create different cognitive "modes" from the same weights. Double-pass boosts math. Triple-pass boosts emotional reasoning. Interleaved doubling (13,13,14,14,15,15,16) creates a pure math specialist. Same model, same VRAM, different routing. The circuit boundaries are sharp — shift by one layer and the effect disappears or inverts. Smaller models (24B) have tighter circuits (3 layers) than larger ones (Ng found 7 layers in 72B). Tools to find circuits in any GGUF model and apply arbitrary layer routing are in the repo. The whole thing — sweep, discovery, validation — took one evening. Happy to answer questions. https://bit.ly/4rEg2PM March 18, 2026 at 10:31PM

Show HN: Sonder – self-hosted AI social simulation engine https://bit.ly/4rE8hcG

Show HN: Sonder – self-hosted AI social simulation engine https://bit.ly/4bhXvEi March 18, 2026 at 01:21AM

Show HN: CodeLedger – deterministic context and guardrails for AI https://bit.ly/4saYs7c

Show HN: CodeLedger – deterministic context and guardrails for AI We’ve been working on a tool called CodeLedger to solve a problem we kept seeing with AI coding agents (Claude Code, Cursor, Codex): They’re powerful, but on real codebases they: - read too much irrelevant code - edit outside the intended scope - get stuck in loops (fix → test → fail) - drift away from the task - introduce architectural issues that linters don’t catch The root issue isn’t the model — it’s: - poor context selection - lack of execution guardrails - no visibility at team/org level --- What CodeLedger does: It sits between the developer and the agent and: 1) Gives the agent the right files first 2) Keeps the agent inside the task scope 3) Validates output against architecture + constraints It works deterministically (no embeddings, no cloud, fully local). --- Example: Instead of an agent scanning 100–500 files, CodeLedger narrows it down to ~10–25 relevant files before the first edit :contentReference[oaicite:0]{index=0} --- What we’re seeing so far: - ~40% faster task completion - ~50% fewer iterations - significant reduction in token usage --- Works with: Claude Code, Cursor, Codex, Gemini CLI --- Repo + setup: https://bit.ly/4bxAhJd Quick start: npm install -g @codeledger/cli cd your-project codeledger init codeledger activate --task "Fix null handling in user service" --- Would love feedback from folks using AI coding tools on larger codebases. Especially curious: - where agents break down for you today - whether context selection or guardrails are the bigger issue - what other issues are you seeing. https://bit.ly/47F3l01 March 18, 2026 at 12:22AM

Show HN: I built a message board where you pay to be the homepage https://bit.ly/4sKqCps

Show HN: I built a message board where you pay to be the homepage I kept thinking about what would happen if a message board only had one slot. One message, front and center, until someone pays to replace it. That's the entire product. You pay the current message's decayed value plus a penny to take the homepage. Message values drop over time using a gravity-based formula (same concept HN uses for ranking), so a $10 message might only cost a few bucks to replace a day later. Likes slow the decay, dislikes speed it up. The whole thing runs on three mini PCs in my house (k3s cluster, PostgreSQL, Redis Sentinel). Is it overengineered for a message board? Absolutely. I genuinely don't know where this goes. Curious what HN thinks. Archive of past messages: https://bit.ly/3Pcn94I https://bit.ly/4bi0GvG March 17, 2026 at 01:06PM

Show HN: Seasalt Cove, iPhone access to your Mac https://bit.ly/4cL7FOO

Show HN: Seasalt Cove, iPhone access to your Mac I feel like I finally built something I actually use every day and it has completely changed the way I think about work. AI workflows have flipped how devs operate. You're not heads down writing code anymore, you're bouncing between projects, instructing agents, reviewing their work, nudging them forward. The job is now less about typing and more about judgment calls. And the thing about that workflow is you spend a lot of time waiting. Waiting for the agent to finish, waiting for the next approval gate. That waiting doesn't have to happen at your desk. It doesn't have to happen in front of a monitor at all. I built Seasalt because I realized my iPhone could handle 80% of what I was chaining myself to my Mac for. Kick off the agent, walk away, review the diff from the store, a walk, or in a separate room away from your Mac. Approve it. Start the next one, switch to another session. You don't need giant dual monitors for this. That's kind of the whole point. Also, I have a deep security background so I felt like it was 100% necessary to include end to end encrypted with a zero knowledge relay, no ports getting opened, no VPN configuration needed, with key validation in the onboarding flow. https://bit.ly/3PnfnVy March 16, 2026 at 11:48PM

Show HN: Webassembly4J Run WebAssembly from Java https://bit.ly/41cf2aN

Show HN: Webassembly4J Run WebAssembly from Java I’ve released WebAssembly4J, along with two runtime bindings: Wasmtime4J – Java bindings for Wasmtime https://bit.ly/471hULh WAMR4J – Java bindings for WebAssembly Micro Runtime https://bit.ly/4blCCGY WebAssembly4J – a unified Java API that allows running WebAssembly across different engines https://bit.ly/40CvoJI The motivation was that Java currently has multiple emerging WebAssembly runtimes, but each exposes its own API. If you want to experiment with different engines, you have to rewrite the integration layer each time. WebAssembly4J provides a single API while allowing different runtime providers underneath. Goals of the project: Run WebAssembly from Java applications Allow cross-engine comparison of runtimes Make WebAssembly runtimes more accessible to Java developers Provide a stable interface while runtimes evolve Currently supported engines: Wasmtime WAMR Chicory GraalWasm To support both legacy and modern Java environments the project targets: Java 8 (JNI bindings) Java 11 Java 22+ (Panama support) Artifacts are published to Maven Central so they can be added directly to existing projects. I’d be very interested in feedback from people working on Java + WebAssembly integrations or runtime implementations. March 16, 2026 at 12:08AM