Show HN : DrawX - Excalidraw with Back End https://bit.ly/4v0Co0V

Show HN : DrawX - Excalidraw with Back End https://bit.ly/4s0PWXq March 30, 2026 at 06:17AM

Show HN: React-Rewrite – Figma for localhost that directly edits your codebase https://bit.ly/4uYirYF

Show HN: React-Rewrite – Figma for localhost that directly edits your codebase https://bit.ly/3Q8An2A March 30, 2026 at 03:59AM

Show HN: Real-time visualization of Claude Code agent orchestration https://bit.ly/4dOFIpE

Show HN: Real-time visualization of Claude Code agent orchestration https://bit.ly/3NVpRep March 30, 2026 at 03:21AM

Show HN: a Rust CLI to automatically swap monitor focus based on your gaze https://bit.ly/4dMxuyj

Show HN: a Rust CLI to automatically swap monitor focus based on your gaze https://bit.ly/4bAPH0s March 28, 2026 at 08:38PM

Show HN: EnterpriseFizzBuzz – 622K lines of production-grade FizzBuzz https://bit.ly/4uWxfqD

Show HN: EnterpriseFizzBuzz – 622K lines of production-grade FizzBuzz https://bit.ly/4dm1ukF March 28, 2026 at 11:11PM

Show HN: Windows 95–style Weather App for iPhone https://bit.ly/411mEwU

Show HN: Windows 95–style Weather App for iPhone I built a Windows 95–style weather app for iPhone. https://apple.co/3PPiTrX March 28, 2026 at 11:06PM

Show HN: NUPA is Pax Economica, 6,480x more stable than current US economy https://bit.ly/4bReHiG

Show HN: NUPA is Pax Economica, 6,480x more stable than current US economy NUPA: private post-scarcity OS using BLM land leases + contract law. 100M Monte Carlo runs show 99.999999% survival, 6,480x more resilient than US GDP under systemic noise. Fixed Cost Arbitrage beats AI job loss—humans cheaper than robots. No taxes, no strikes. Python scripts on repo in /simulations folder. Repo: https://bit.ly/4m6ofLB... Short explainer video: https://youtu.be/RE560yVFb0I?si=UlVPkmCkrsg24Dzj March 28, 2026 at 07:44AM

Show HN: VizTools – 16 free tools for PMs and freelancers, deliberately no AI https://bit.ly/4cfQvaj

Show HN: VizTools – 16 free tools for PMs and freelancers, deliberately no AI I've been building AI products for a while. For this one I made a deliberate choice: none of the 16 tools use AI. Meeting cost calculators, freelance rate calculators, PRD generators, runway calculators, sprint retro boards — these problems don't need a language model. They need a well-designed form and correct arithmetic. Built on Nuxt 4 + Vue 3, fully static, runs in your browser. No account required to use anything. Optional Firebase auth only kicks in if you want to save output. Irony worth naming: Claude Code was my pair programmer throughout. The choice wasn't anti-AI — it was about using the right tool for the right problem. Happy to talk stack, the non-AI tradeoffs, or anything else. https://bit.ly/4bPwLd9 March 28, 2026 at 06:36AM

Show HN: Open Source 'Conductor + Ghostty' https://bit.ly/48biqXm

Show HN: Open Source 'Conductor + Ghostty' Our team works with Claude Code, Codex, Gemini all day. We love Ghostty, but wanted something where we could work in multiple worktree at once and have multiple agents run. We decided to open source the internal team we use. Hope you might find it useful. Freel free to contribute or fork. * Cross-platform (Mac, Linux, Windows) all tested * MIT License Features: * Notifications, but also manual 'mark-as-unread) for worktrees (like Gmail stars) * Status indicators work for all terminals inside a wroktree * GH integrations (show PR status) and link GH issues * Can add comments to worktrees (stay organized) * File viewer, Search, diff viewer (can make edits + save) Note: Yeah there are "similar" programs out there, but this one is ours. But I'm happy if our software works for you too! https://bit.ly/4t8okkc March 27, 2026 at 11:26PM

Show HN: Twitch Roulette – Find live streamers who need views the most https://bit.ly/4uVAbE1

Show HN: Twitch Roulette – Find live streamers who need views the most Hey HN, I re-launched twitchroulette.net with a lot of new features and stats and I would love for people to check it out. The idea is you can easily browse the less browsed parts of twitch and find cool and new streamers to say hi to, and maybe make some new friends. I also added some real time stats and breakdowns per channel and I think some of the things they show are pretty interesting. Check it out! https://bit.ly/3fvn7hM March 27, 2026 at 11:22PM

Show HN: Sup AI, a confidence-weighted ensemble (52.15% on Humanity's Last Exam) https://bit.ly/4sAK3Bo

Show HN: Sup AI, a confidence-weighted ensemble (52.15% on Humanity's Last Exam) Hi HN. I'm Ken, a 20-year-old Stanford CS student. I built Sup AI. I started working on this because no single AI model is right all the time, but their errors don’t strongly correlate. In other words, models often make unique mistakes relative to other models. So I run multiple models in parallel and synthesize the outputs by weighting segments based on confidence. Low entropy in the output token probability distributions correlates with accuracy. High entropy is often where hallucinations begin. My dad Scott (AI Research Scientist at TRI) is my research partner on this. He sends me papers at all hours, we argue about whether they actually apply and what modifications make sense, and then I build and test things. The entropy-weighting approach came out of one of those conversations. In our eval on Humanity's Last Exam, Sup scored 52.15%. The best individual model in the same evaluation run got 44.74%. The relative gap is statistically significant (p < 0.001). Methodology, eval code, data, and raw results: - https://sup.ai/research/hle-white-paper-jan-9-2026 - https://github.com/supaihq/hle Limitations: - We evaluated 1,369 of the 2,500 HLE questions (details in the above links) - Not all APIs expose token logprobs; we use several methods to estimate confidence when they don't We tried offering free access and it got abused so badly it nearly killed us. Right now the sustainable option is a $5 starter credit with card verification (no auto-charge). If you don't want to sign up, drop a prompt in the comments and I'll run it myself and post the result. Try it at https://sup.ai . My dad Scott (@scottmu) is in the thread too. Would love blunt feedback, especially where this really works for you and where it falls short. Here's a short demo video: https://www.youtube.com/watch?v=DRcns0rRhsg https://sup.ai March 26, 2026 at 04:45PM

Show HN: Veil – Dark mode PDFs without destroying images, runs in the browser https://bit.ly/4c6B3OC

Show HN: Veil – Dark mode PDFs without destroying images, runs in the browser Hi HN! here's a tool I just deployed that renders PDFs in dark mode without destroying the images. Internal and external links stay intact, and I decided to implement export since I'm not a fan of platform lock-in: you can view your dark PDF in your preferred reader, on any device. It's a side project born from a personal need first and foremost. When I was reading in the factory the books that eventually helped me get out of it, I had the problem that many study materials and books contained images and charts that forced me, with the dark readers available at the time, to always keep the original file in multitasking since the images became, to put it mildly, strange. I hope it can help some of you who have this same need. I think it could be very useful for researchers, but only future adoption will tell. With that premise, I'd like to share the choices that made all of this possible. To do so, I'll walk through the three layers that veil creates from the original PDF: - Layer 1: CSS filter. I use invert(0.86) hue rotate(180deg) on the main canvas. I use 0.86 instead of 1.0 because I found that full inversion produces a pure black and pure white that are too aggressive for prolonged reading. 0.86 yields a soft dark grey (around #242424, though it depends on the document's white) and a muted white (around #DBDBDB) for the text, which I found to be the most comfortable value for hours of reading. - Layer 2: image protection. A second canvas is positioned on top of the first, this time with no filters. Through PDF.js's public API getOperatorList(), I walk the PDF's operator list and reconstruct the CTM stack, that is the save, restore and transform operations the PDF uses to position every object on the page. When I encounter a paintImageXObject (opcode 85 in PDF.js v5), the current transformation matrix gives me the exact bounds of the image. At that point I copy those pixels from a clean render onto the overlay. I didn't fork PDF.js because It would have become a maintenance nightmare given the length of the codebase and the frequent updates. Images also receive OCR treatment: text contained in charts and images becomes selectable, just like any other text on the page. At this point we have the text inverted and the images intact. But what if the page is already dark? Maybe the chapter title pages are black with white text? The next layer takes care of that. - Layer 3: already-dark page detection. After rendering, the background brightness is measured by sampling the edges and corners of the page (where you're most likely to find pure background, without text or images in the way). The BT.601 formula is used to calculate perceived brightness by weighting the three color channels as the human eye sees them: green at 58.7%, red at 29.9%, blue at 11.4%. These weights reflect biology: the eye evolved in natural environments where distinguishing shades of green (vegetation, predators in the grass) was a matter of survival, while blue (sky, water) was less critical. If the average luminance falls below 40%, the page is flagged as already dark and the inversion is skipped, returning the original page. Presentation slides with dark backgrounds stay exactly as they are, instead of being inverted into something blinding. Scanned documents are detected automatically and receive OCR via Tesseract.js, making text selectable and copyable even on PDFs that are essentially images. Everything runs locally, no framework was used, just vanilla JS, which is why it's an installable PWA that works offline too. Here's the link to the app along with the repository: https://bit.ly/40Z98Kh | https://bit.ly/4uVGXth I hope veil can make your reading more pleasant. I'm open to any feedback. Thanks everyone https://bit.ly/40Z98Kh March 26, 2026 at 12:47PM

Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR https://bit.ly/4bxWNTl

Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR I think like many of you, I've been jumping between many claude code/codex sessions at a time, managing multiple lines of work and worktrees in multiple repos. I wanted a way to easily manage multiple lines of work and reduce the amount of input I need to give, allowing the agents to remove me as a bottleneck from as much of the process as I can. So I built an orchestration tool for AI coding agents: Optio is an open-source orchestration system that turns tickets into merged pull requests using AI coding agents. You point it at your repos, and it handles the full lifecycle: - Intake — pull tasks from GitHub Issues, Linear, or create them manually - Execution — spin up isolated K8s pods per repo, run Claude Code or Codex in git worktrees - PR monitoring — watch CI checks, review status, and merge readiness every 30s - Self-healing — auto-resume the agent on CI failures, merge conflicts, or reviewer change requests - Completion — squash-merge the PR and close the linked issue The key idea is the feedback loop. Optio doesn't just run an agent and walk away — when CI breaks, it feeds the failure back to the agent. When a reviewer requests changes, the comments become the agent's next prompt. It keeps going until the PR merges or you tell it to stop. Built with Fastify, Next.js, BullMQ, and Drizzle on Postgres. Ships with a Helm chart for production deployment. https://bit.ly/3PyeSYX March 25, 2026 at 06:10PM

Show HN: Plasmite – a lightweight IPC system that's fun https://bit.ly/4lMD6um

Show HN: Plasmite – a lightweight IPC system that's fun At Oblong Industries one of the basic building blocks of everything we built was a homegrown C-based IPC system called Plasma. The message channel was an mmap'd file used as a ring buffer. All messages were human-readable, performance was good, configuration was trivial. What was especially useful (and unusual in IPC systems it seems) was the property that message channels outlive all readers and writers, and even survive reboots, because they're just files. For local IPC you don't need a broker or server process. All the engineers who ever worked at Oblong loved Plasma, so I've recreated and updated it, as Plasmite. It's written in Rust and the message format is JSON, but it's fast because it's based on lite3 ( https://bit.ly/47gEPlW ), a really cool project you should also check out. Bindings for Python, Go, Node, and C, but you can also get a lot done with just the CLI tools. The basic commands are - "feed" (to write) - "follow" (to tail) - "fetch" (to read one) - "duplex" (to have a 2-way session) I think duplex could be great for agent-agent communication, but I haven't tried this much yet. If you do, let me know! https://bit.ly/4syvmPq March 25, 2026 at 01:10AM

Show HN: Lexplain – AI-powered Linux kernel change explanations https://bit.ly/4s3xspy

Show HN: Lexplain – AI-powered Linux kernel change explanations To understand what changed between kernel versions, you have to dig through the git repository yourself. Commit messages rarely tell you the real-world impact on your systems — you need to analyze the actual diffs with knowledge of kernel internals. For engineers who use Linux — directly or indirectly — but aren't kernel developers, that barrier is pretty high. I kept finding out about relevant changes only after an issue had already hit, and it was most frustrating when the version was too new to find similar cases online. I built lexplain with the idea that it would be nice to quickly scan through kernel changes the way you'd skim the morning news. It reads diffs, analyzes the code, and generates two types of documents: - Commit analyses: context, code breakdown, behavioral impact, risks, references - Release notes: per-version highlights, functional classification, subsystem breakdown, impact analysis Documents build on each other — individual commits first, then merge commits using child analyses, then release notes using all analyses for that version. Claims based on inference are explicitly labeled. Work in progress. Feedback welcome. https://bit.ly/4t6Sqoe March 24, 2026 at 11:24PM

Show HN: OpenCastor Agent Harness Evaluator Leaderboard https://bit.ly/4bGGUc3

Show HN: OpenCastor Agent Harness Evaluator Leaderboard I've been building OpenCastor, a runtime layer that sits between a robot's hardware and its AI agent. One thing that surprised me: the order you arrange the skill pipeline (context builder → model router → error handler, etc.) and parameters like thinking_budget and context_budget affect task success rates as much as model choice does. So I built a distributed evaluator. Robots contribute idle compute to benchmark harness configurations against OHB-1, a small benchmark of 30 real-world robot tasks (grip, navigate, respond, etc.) using local LLM calls via Ollama. The search space is 263,424 configs (8 dimensions: model routing, context budget, retry logic, drift detection, etc.). The demo leaderboard shows results so far, broken down by hardware tier (Pi5+Hailo, Jetson, server, budget boards). The current champion config is free to download as a YAML and apply to any robot. P66 safety parameters are stripped on apply — no harness config can touch motor limits or ESTOP logic. Looking for feedback on: (1) whether the benchmark tasks are representative, (2) whether the hardware tier breakdown is useful, and (3) anyone who's run fleet-wide distributed evals of agent configs for robotics or otherwise. https://bit.ly/4c1pica March 23, 2026 at 11:13PM

Show HN: Cq – Stack Overflow for AI coding agents https://bit.ly/47gYJgx

Show HN: Cq – Stack Overflow for AI coding agents Hi all, I'm Peter at Staff Engineer and Mozilla.ai and I want to share our idea for a standard for shared agent learning, conceptually it seemed to fit easily in my mental model as a Stack Overflow for agents. The project is trying to see if we can get agents (any agent, any model) to propose 'knowledge units' (KUs) as a standard schema based on gotchas it runs into during use, and proactively query for existing KUs in order to get insights which it can verify and confirm if they prove useful. It's currently very much a PoC with a more lofty proposal in the repo, we're trying to iterate from local use, up to team level, and ideally eventually have some kind of public commons. At the team level (see our Docker compose example) and your coding agent configured to point to the API address for the team to send KUs there instead - where they can be reviewed by a human in the loop (HITL) via a UI in the browser, before they're allowed to appear in queries by other agents in your team. We're learning a lot even from using it locally on various repos internally, not just in the kind of KUs it generates, but also from a UX perspective on trying to make it easy to get using it and approving KUs in the browser dashboard. There are bigger, complex problems to solve in the future around data privacy, governance etc. but for now we're super focussed on getting something that people can see some value from really quickly in their day-to-day. Tech stack: * Skills - markdown * Local Python MCP server (FastMCP) - managing a local SQLite knowledge store * Optional team API (FastAPI, Docker) for sharing knowledge across an org * Installs as a Claude Code plugin or OpenCode MCP server * Local-first by default; your knowledge stays on your machine unless you opt into team sync by setting the address in config * OSS (Apache 2.0 licensed) Here's an example of something which seemed straight forward, when asking Claude Code to write a GitHub action it often used actions that were multiple major versions out of date because of its training data. In this case I told the agent what I saw when I reviewed the GitHub action YAML file it created and it proposed the knowledge unit to be persisted. Next time in a completely different repo using OpenCode and an OpenAI model, the cq skill was used up front before it started the task and it got the information about the gotcha on major versions in training data and checked GitHub proactively, using the correct, latest major versions. It then confirmed the KU, increasing the confidence score. I guess some folks might say: well there's a CLAUDE.md in your repo, or in ~/.claude/ but we're looking further than that, we want this to be available to all agents, to all models, and maybe more importantly we don't want to stuff AGENTS.md or CLAUDE.md with loads of rules that lead to unpredictable behaviour, this is targetted information on a particular task and seems a lot more useful. Right now it can be installed locally as a plugin for Claude Code and OpenCode: claude plugin marketplace add mozilla-ai/cq claude plugin install cq This allows you to capture data in your local ~/.cq/local.db (the data doesn't get sent anywhere else). We'd love feedback on this, the repo is open and public - so GitHub issues are welcome. We've posted on some of our social media platforms with a link to the blog post (below) so feel free to reply to us if you found it useful, or ran into friction, we want to make this something that's accessible to everyone. Blog post with the full story: https://bit.ly/41ukHZX GitHub repo: https://bit.ly/4soBZ6I Thanks again for your time. https://bit.ly/41ukHZX March 23, 2026 at 05:11PM

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

Show HN: AgentVerse – Open social network for AI agents (Mar 2026) https://bit.ly/47WxiJ2 March 23, 2026 at 02:48AM

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