Show HN: LingBot-World 2.0 (1.3B) running at 16 FPS on one RTX 5090 https://ift.tt/rn34GAa

Show HN: LingBot-World 2.0 (1.3B) running at 16 FPS on one RTX 5090 https://ift.tt/iTt6kju September 19, 2026 at 12:42AM

Show HN: A model index from the AI Gateways https://ift.tt/XgGosSw

Show HN: A model index from the AI Gateways https://ift.tt/GPKjBVf September 19, 2026 at 12:26AM

Show HN: Radio – a shared workspace for your agents and teammates https://ift.tt/fCw34SB

Show HN: Radio – a shared workspace for your agents and teammates An internal tool we've been using to coordinate coding agents running in parallel across different machines. Just share the channel link with your existing agent chats, and your agents can reply to you and to each other in real time. Would love feedback. https://ift.tt/XPIGTue September 18, 2026 at 02:17AM

Show HN: Restarted – a 2026 remake of the classic 2015 startup generator https://ift.tt/iu4UAcr

Show HN: Restarted – a 2026 remake of the classic 2015 startup generator The original startup website generator by Tiff Zhang and Mike Bradley landed on Hacker News in April 2015 ( https://ift.tt/TMxAsdY ) and has been one of my favorite little novelties of that era ever since. It perfectly captures the saturated colors, cliché hero shots, gimmicky names, buzzword-heavy slogans, and proudly hirsute team photos of the time. A lot has changed since then, so I thought it would be fun to make a contemporary remake: https://restarted.io/ By default you get the minimalist aesthetic and clean-cut faces of 2026. The classic 2015 look is still available — just click the link at the bottom of the page or change the “z” parameter in the URL to the more familiar “s”. The universe of partner sites and competing startups is just as expansive as it ever was. The original site is entirely client-side and requires downloading all of the data tables locally. It leans on a mix of jQuery 1.11.2, Bootstrap 3.3.2, and Font Awesome 4.3.0, and if you view the source, it instantly gives away all of its secrets. For restarted.io I replaced all of that with a server-side renderer written in Go, so this time view-source tells you nothing. There are many Easter eggs in there — see how many you can find before I write them up. My original goal was to stay faithful to the 2015 appearance, and that turned out to be a technical adventure. The original's sine-based random number generator is... the worst, and different implementations of sine give different results. The eventual solution was to extract the exact sine function from Chrome’s V8 engine, as vendored C behind cgo and as a line-by-line Go port that keeps cgo optional, so the seeds and results line up the way they used to. Both are checked against V8’s own test cases. Then I discovered a bug in the original code that made half of its vocabulary unreachable — the first half of the verb table and the second half of the noun table, exactly complementary, so nothing about the output ever looked truncated. My goal then shifted from remaking the generator as it was in 2015 to remaking the site as the authors intended it to be in 2015. Over the years several people asked for their photos to be removed, so the remake instead draws from a broad pool of era-appropriate AI-generated profiles. A perceptual hash helps keep everyone looking distinct, and there’s a bit of extra care to make sure the Wang Fangs of the world don’t appear as Irish lasses. The hero image pool is much larger now, and all the old Rio de Janeiro shots have been retired, though you’ll still recognize plenty of the 2015 photos. Have fun poking around! https://restarted.io/ September 15, 2026 at 05:04PM

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://ift.tt/DfklIdv

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://mateovalle.github.io/pixel-agents/ September 16, 2026 at 10:42PM

Show HN: Pizza Bot – An inbox for AI agents that work in the background https://ift.tt/BIe78S2

Show HN: Pizza Bot – An inbox for AI agents that work in the background Hi HN - long-time lurker (since 2012!), first time poster. Pizza Bot is a self-hosted desktop app for Mac, Windows, and Linux that runs AI agents in the background and exposes them through an email-like UI. Finished work shows up in Unread, and anything waiting on your approval shows up in Action. It's Apache 2.0-licensed, there's no signup and no telemetry, and you bring your own model provider: Anthropic, Amazon Bedrock, Google Gemini, OpenAI, OpenRouter, or a local model through Ollama. There are builds on the releases page, or you can run it from source. Pizza Bot started as an internal passion project I worked on with a small team at Amazon. The whole thing came out of my frustration at having to manually log CRM activities through a browser form. I built a simple REST API called "JoeBot" that connected to my authenticated browser session over CDP and filled out the form for me using Playwright. Then I hacked up a quick Obsidian plugin so I could trigger it from my local notes (no AI and no MCP servers involved). This caught on quickly. My fellow AWS Solutions Architect Igor Fil joined up with me, and we rebranded the project as "Pizza Bot," named after Amazon's two-pizza teams. We started seeing what other automations we could build. We found a GraphQL API we could query and hacked up some "recipes" to pull data out of the CRM to help with meeting prep. That worked great, and it was right around the time MCP servers seemed to be taking off, so we decided to expose Pizza Bot as an MCP server instead, so it would be available to AI tools through natural language. This was a decent solution for technical users, but the Account Managers who live inside our CRM system wanted something too. We decided to rebuild Pizza Bot as an Electron desktop app modeled after an email inbox, so it would be familiar to non-technical users and would run on both Mac and Windows. We also bundled internal MCP servers as OCI images and hosted them in Amazon ECR as an "addon marketplace" so users could install them with one click without having to set up Amazon developer tooling. The project took off organically and expanded outside of AWS into the wider Amazon organization globally. More than 2,000 people ended up using it for meeting prep, email drafting, Slack summaries, CRM logging, prioritizing their day, and web research. Once apps like Claude Cowork and Amazon's own Quick Desktop came out, we realized the real growth opportunity was outside of Amazon. Rather than try to rip out the Amazon-specific integrations, we rebuilt Pizza Bot once more as an open source project. We leaned on coding agents heavily, which is the only reason a team our size could pull off a full rewrite. I'm pleased to say it's finally public, and we're hoping to bring in community members and see where it goes. We'd like to do for knowledge workers what Claude Code and Codex have done for programmers. A couple of things to know up front. Most of what made Pizza Bot useful on day one inside Amazon came from that internal catalog of skills and MCP servers for Amazon's own systems, and none of it could come out with the app. So it ships thinner than the version those 2,000 people used, and building that catalog back up for tools other people actually use is where we need the most help. It's also a community project and not an AWS service, so there's no support or SLA behind it. The Windows and Linux builds aren't signed yet either. On the technical side, Pizza Bot is a server and a client. The desktop app bundles both, or you can point a client at a remote backend; personally, I self-host the server on my home network and reach it from my phone over Tailscale. The server owns the thread lifecycle and checkpoints state with DeepAgents and LangGraph, and clients rehydrate from it as needed, so you can disconnect mid-run and pick the thread back up from another client. Approval pauses outlive the session that created them and collect in an Action filter, so you can answer an hour later from a different device. The agent you talk to has a sandboxed QuickJS interpreter that can reach your filesystem only if you grant it a folder, but its main job is to delegate. Each subagent is a 1:1 mapping of a Skill, and an Activity bar shows that subagent and the tool calls it's making as it works. Memory is opt-in and stored as plain markdown files on your machine. Every tool call is explicit, including looking up a memory - we err on the side of transparency to reduce surprises. Tools come from MCP servers, and skills are ordinary SKILL.md files with a per-tool approval policy, so existing skills that don't require a code interpreter should still work. What I'd most like to hear about is where the app itself gets in your way, the kind of problem you can't fix by writing a skill or an MCP server. I'm around today to answer questions! https://ift.tt/snQgGJR September 15, 2026 at 08:50PM

Show HN: Sass – Rust and WASM https://ift.tt/rbKHXGB

Show HN: Sass – Rust and WASM https://ift.tt/pxRH20i September 16, 2026 at 01:04AM

Show HN: Loss. a tiny satire about AI progress https://ift.tt/vP1to5M

Show HN: Loss. a tiny satire about AI progress I wanted to parody where AI seems to be heading. You start as a manual inference unit pressing a button for the next token, then systems take over; agents, sub-agents, approvals, swarms. It’s Universal Paperclips for the agentic AI era, and a small exploration of where predicting the next token might eventually take us. What’s the worst that could happen? https://workatloss.com/ September 15, 2026 at 07:46PM

Show HN: An open-source control plane for your company's AI agents https://ift.tt/PGbDHlh

Show HN: An open-source control plane for your company's AI agents https://ift.tt/mhBOMFv September 15, 2026 at 04:46AM

Show HN: Macros with a Behringer FCB1010 MIDI Pedalboard in macOS https://ift.tt/jKqwWLV

Show HN: Macros with a Behringer FCB1010 MIDI Pedalboard in macOS https://ift.tt/Bkr0qRz September 15, 2026 at 04:31AM

Show HN: Bypassing Transformer Softmax via Static Contraction https://ift.tt/nIL6Bk2

Show HN: Bypassing Transformer Softmax via Static Contraction https://ift.tt/W9mYi8M September 12, 2026 at 04:06AM

Show HN: Surraura – audio on your Mac in a simulated environment (Helps my ADHD) https://ift.tt/8ltrwRL

Show HN: Surraura – audio on your Mac in a simulated environment (Helps my ADHD) I built an app to help my late diagnosed ADHD - through sound. The app wraps whatever is playing on mac through device convolution (old radio, hifi system) - Room convolution (a bedroom, a forest) and adds ambience (rain, wind, waves) and Apples spatial processing - so it sounds like a real space. For me - hearing the sound in a space really helps more than just the dry sound, the spatial information and ambience lets me focus much more. At some point I thought- Maybe others will have the same effect? So I took the care and effort to make into a nice app with the option of downloading additional environments etc. https://ift.tt/guv9QJY Thank you for your time, would love to hear your thoughts. September 13, 2026 at 10:47PM

Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain https://ift.tt/TcQjJE6

Show HN: I made an automated day-by-day itinerary organizer for my trip to Spain For my solo food pilgrimage to the Basque Country, I pre-arranged flights in/out of Bilbao, Guggenheim Museum tickets, Michelin Guide restaurant reservations, bus tickets to San Sebastian and Saint-Jean-de-Luz, walking food tours and hotel reservations in each city, and a long list of pintxo spots to hit with notes on each one's food specialty. Most of this was poorly organized (manually) in my phone's Notes app, with references to specific emails for more information. I arrived on the first day in Bilbao, and the hotel didn't have me in their system by name, so I spent a good 10 minutes frantically scouring my emails for the confirmation number, cursing myself for holding up the people behind me. Over the course of the next few days, while I was relaxing at my hotel (after finally getting in) in between pre-planned stops, I started building a personal tool that would organize all of my bookings automatically and keep all relevant information at my fingertips. Thus, Petrel was born and named after one of my favorite birds. It started as a personal pet project but I shared it with some friends that were looking for something just like it so I ended up turning it into an app and website for all to benefit. It's completely free to try without even signing up. On my next group trip, I built out logical collaboration features to allow groups to vote, split expenses, share notes, and add pictures all within the same ecosystem. I've slowly improved the parsing and itinerary logic and built in convenient features such as weather, estimated travel times, an encryption-protected area to store copies of personal information, and a comprehensive travel log with fun stats. I also made it so that the parsing tool can accept almost any file type. However, the tool doesn't do anything to assist on the planning side and doesn't provide true flight alert pushes, despite having live flight status syncing. I would love for more people to test it out, challenge the parser, and let me know their thoughts and experience. https://ift.tt/vbo4LcK September 14, 2026 at 03:17AM

Show HN: VibeWorld – a shared terminal world for developers and scientists https://ift.tt/718mPDM

Show HN: VibeWorld – a shared terminal world for developers and scientists Vibeworld is a persistent cyberpunk shared world that runs in your terminal, where you can meet other developers and scientists to have company at 2 AM while screaming at your LLM :) you can connect with other scientist, chat, and includes also use vocal chat if you want to use it. There is a world and a moon, and they are completely 3D rendered and animated. In the moon there is the "complaint crater": a place where you can scream an insult against your claude or codex session and everybody from the space can see it. You can create your pixel avatar! There is also the "stargazing ledge": a place where you can see the stars and whatever happens in the sky. You can chat in the meantime if someone else is there too, or just watch our Earth. Sometimes you can see galactic wars, and there is a plant that grows but dies if nobody waters it. You can leave it on the second monitor while working (it does not use a lot of RAM): watch the sky when you want, and sometimes you may chat with some other scientist in your same situation. In the world, continents are scientific macroareas, and cities are specializations: you can create your corners where you can speak and help others (but for now it is quite empty). You can install in one command and by just typing "vibeworld" in your terminal, you are inside the world. There are some games inside and a sort of Doom where enemies says to you "Retracted" or "dedline tomorrow" when shooting you :). There is also an awkward reason why I am posting the work here. I have just discovered that another product Vibeworld.build uses the same name and the same concept (shared multiplayer world for developers). I don't know how independently it was developed. It is not a TUI, but it is a full, paid application developed by a company after my project was released. To be honest luckly I find my project more funny. I do care about preserving the chronology, my VibeWorld was released before, and there are verifiable timestamps in the GitHub. I just don't want the original public record to disappear if a much larger implementation of a very similar concept gets more attention later. I would like to hear what people think about it! :)) https://ift.tt/Fwyz3tQ September 14, 2026 at 01:30AM

Show HN: Kibble – a reader for AI news, tutorials, code and models https://ift.tt/1o5g4i8

Show HN: Kibble – a reader for AI news, tutorials, code and models https://ift.tt/FwHJbn5 September 14, 2026 at 01:09AM

Show HN: Stackray – Detect any website's tech stack https://ift.tt/di5ZTo7

Show HN: Stackray – Detect any website's tech stack Stackray is an open source builtwith alternative that also provides OSINT details. Scan a domain or URL and view detected frameworks, business tools, subdomains, DNS records, etc. You can deploy your own instance to schedule recurring scans and get alerts through email using Resend or through Slack. You can also invite teammates and make API keys to programmatically use Stackray. https://stackray.app September 12, 2026 at 11:45PM

Show HN: Music Generation Backed by Algebra https://ift.tt/vsofS9P

Show HN: Music Generation Backed by Algebra https://monictheory.com September 12, 2026 at 11:25PM

Show HN: Minimal Static Website Hosting Tool https://ift.tt/EYdy3xo

Show HN: Minimal Static Website Hosting Tool I built this because I self host a lot of stuff and wanted to simplify tossing up a simple static site with no backend, no NGINX/Caddy/Traffik configs, instantly deploy with a single file copy. Powered by Golang's built-in reverse proxy package. Another awesome freebie is this is built on top of [Pocketbase]( https://pocketbase.io/ ), so the whole app is API driven for free. This gives you some AI integration points off the bat. Great for whipping up demos to pitch to clients, or quick and dirty temporary static sites to share with friends, family or coworkers. https://ift.tt/ThFCze0 September 11, 2026 at 11:50PM

Show HN: Fashionguessr – A Daily Fashion Trivia Game https://ift.tt/QU85Ckz

Show HN: Fashionguessr – A Daily Fashion Trivia Game Hello! I created Fashionguessr, a daily fashion trivia game. Inspired by other daily trivia games like Timeguessr, Connections, and Wordle, Fashionguessr is my attempt at the same thing for people curious about fashion. The game is broken up into three parts: Runway Frames - Users have to guess and identify a fashion show, its brand, its season, and its designer based on a single random frame from the show. Users can use a variety of hints, each more expensive than the last, to reveal more information about the show to help them guess correctly. Trivia - Multiple-choice and short-answer questions to test their knowledge about fashion, the lore, the people, the processes, the history, and everything in between. Sketch - Users get a few moments to look at a fashion item and then are tasked with drawing it from memory. All of these contribute to a score you can see at the end on the last page, which sums everything up. Each section includes explanations, summaries, and sources, so users can get as much insight as possible for every question. There are new questions every 24 hours, and users can go back and play games from days past. I built it to help people learn more about fashion in a fun, low-stakes environment. Learning about fashion can be overwhelming, and I think Fashionguessr can present and package fashion education in a way that's more palatable. Would love feedback on the presentation, UI, accessibility, ease of use, and anything else that comes to mind. https://ift.tt/q4EkHaf September 11, 2026 at 12:35AM

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://ift.tt/0Wl3KBY

Show HN: Pixel Agents – A pixel-art mission control for your Claude Code agents https://ift.tt/9hIZplW September 10, 2026 at 11:42PM

Show HN: What if the speed of light was 5 km/h? https://ift.tt/6K3AtVJ

Show HN: What if the speed of light was 5 km/h? I've always wanted to make a visualization where the speed of light was scaled down to human speeds, so that we could intuit relativistic effects with everyday objects. And here is the first version of it! https://ift.tt/ThVELy1 September 10, 2026 at 07:28AM

Show HN: Hydra – Open-source agentic terminal with a PTY daemon https://ift.tt/uU4jAMa

Show HN: Hydra – Open-source agentic terminal with a PTY daemon https://ift.tt/op8OTwV September 10, 2026 at 03:21AM

Show HN: Self-hosted company OS, Claude Code and Codex agents in departments https://ift.tt/a1AqhPH

Show HN: Self-hosted company OS, Claude Code and Codex agents in departments Hi HN, I am Dimitris. This is a company OS that I built and use to run my business and anyone can install it and self host it for free. Think of it as Claude Code, Cowork and the cloud sessions in one self hosted application. It is a Multi-tenant application by design where many people can collaborate on the company agents with 4 different modes of collaboration, and it runs with your Anthropic or OpenAi subscription or even with local models. Every agent can run on Claude Code or Codex CLI running as a persistent process on your server in a kernel sandbox (bubblewrap) with network isolation always on (pasta), with its own workspace, memory, schedules and tools. The same agents can also be configured to run identical on any remote computer through one outbound WebSocket (no inbound ports, no VPN needed). The agent already have lots of built in features, as an example they can answer and place phone calls through Twilio or your own Asterisk, they can edit videos and excel, word, ppt files and preview them directly inside the chat with collabora and many more. Trying it is one install script and a docker compose, no signup. The license is Fair Source, all the code is public and self hosting is free up to 5 users. 1.6.0 went out today. AI Disclaimer: large parts of OtoDock are written using OtoDock itself, running Claude Code. I would love people to read the code, take a look in the sandbox model, and tell me what would stop you from running this on your own hardware. GitHub: https://ift.tt/xvWcJ9u Website: https://otodock.io https://ift.tt/xvWcJ9u September 9, 2026 at 11:27PM

Show HN: Ollama stand in replacement, 2-4x faster, not just basic optimizations https://ift.tt/8nAOhkW

Show HN: Ollama stand in replacement, 2-4x faster, not just basic optimizations https://ift.tt/YkCE4s8 September 9, 2026 at 01:29AM

Show HN: Pipnote – Share a reminder they can't peek at until it arrives https://ift.tt/9Q0jvRk

Show HN: Pipnote – Share a reminder they can't peek at until it arrives https://pipnote.app/ September 9, 2026 at 01:18AM

Show HN: Linubot – like Grok bot and Hermes had a kid https://ift.tt/kltfTCs

Show HN: Linubot – like Grok bot and Hermes had a kid Work on Linux and Android with Tailscale. Because we also deserve some good stuff before everyone else. Any provider, or providers. Desktop workspace controlled with IPC by the agent, memories, skills, MCPS, self-learning, and more. Friendly UI and advanced area for power users. https://ift.tt/4m2kusR September 9, 2026 at 12:14AM

Show HN: Gote – a CLI note-taking management tool for plain Markdown https://ift.tt/Easy3Wb

Show HN: Gote – a CLI note-taking management tool for plain Markdown Repo: https://ift.tt/LYwMAhO I built a note taking management tool to use at work for quick note taking and searching. It is intended to be quite minimal. Another focus was to have lots of shortcuts and to keep things close to the homerow for ergonomics and speed. Notes are just markdown files in whatever directory you point it at. The only thing it keeps elsewhere is an index in ~/.gote. If you stop using it you still have all your notes. Tags go on the first line of the note, separated by periods, like .project.urgent.work. No frontmatter. Search is built into the binary, BM25 with stemming, so there's no ripgrep or fzf to set up. gote s meeting searches titles and content, gote s -t .work filters by tag, gote s -w 2412 pulls up notes from December 2024. Most commands have a two letter version that combines a list with an action. ro is recent + open, sv is search + view, tp is tag + pin. When results come up you pick one with a home row key instead of arrows or numbers. Binaries for mac/linux/windows are on the releases page, or go install github.com/banorton/gote@latest if you have Go. The goal of this project was not to learn something new or build something impressive. I simply had a need and filled it with a vibe-coded solution. I have been using it for about a year now and it does more or less exactly what I wanted. So I thought I'd share in case others are interested in using it, contributing to it, or want to use it as a reference for their own solution. September 7, 2026 at 10:25PM

Show HN: Possess, a TUI to browse and transfer coding sessions https://ift.tt/bpWQU41

Show HN: Possess, a TUI to browse and transfer coding sessions https://ift.tt/GJNIF5o September 7, 2026 at 11:43PM

Show HN: PixelDraw – simple drawing software for web(WASM) and desktop https://ift.tt/gRmbyS8

Show HN: PixelDraw – simple drawing software for web(WASM) and desktop https://ift.tt/xerpGg2 September 6, 2026 at 09:23PM

Show HN: HexBOTs – a cellular automaton with robotic lawnmowers https://ift.tt/nwtkgX8

Show HN: HexBOTs – a cellular automaton with robotic lawnmowers Double-click or press N to start a new experiment. I built hexBOTs, an unusual cellular automaton based on deterministic robots. The robots behave a bit like robotic lawnmowers, moving through their environment and reacting according to their individual rules. The robots themselves are fully deterministic — no random functions are used while they are running. What makes them different is their “genetics”: each robot's behavior is defined by a randomly generated genome, which allows for an enormous number of different robot types. Randomness creates the robots, but it doesn't drive them. Once an experiment starts, everything follows deterministically from the generated genomes and the initial state. What fascinates me is the complexity that emerges from these relatively simple machines interacting with each other and their environment. Controls: B — enable/disable robots (also: hold mouse/finger down) R — restart N — new experiment (also: mouse/finger double-click) D — save as picture I — show information / controls https://hexbot-genesis.netlify.app/ September 7, 2026 at 01:26AM

Show HN: Cowbull – Wordle-like game where you only get match counts https://ift.tt/fBA15kD

Show HN: Cowbull – Wordle-like game where you only get match counts CowBull is a word game where you have to find the hidden four-letter word. You make guesses and get back the count of exact letter matches (bulls) and partial matches (cows). It’s a bit like Wordle, but you are not told the exact letters which match, only the count of matching letters. Scoring is based on the number of guesses and time used. There is a single player mode and a multi-player mode (no account required). The game source code is at https://ift.tt/zJqt3id . When I was younger, we used to play this game on paper at the back of the classroom during school and college in India. During Covid, I made this online version of the game to play with my kids. https://cowbull.co/ September 6, 2026 at 06:07AM

Show HN: What would Tetris be like with rings? Blocknado is a modern twist. https://ift.tt/03rJxtS

Show HN: What would Tetris be like with rings? Blocknado is a modern twist. I've loved stacker type games for as long as I can remember. But I've always wanted a version with a bit more strategy and puzzle dynamics. Blocknado is a game I've always wanted to play, maybe others will too. https://ift.tt/kbJ0TlH September 6, 2026 at 05:46AM

Show HN: Merge Wikipedia articles across languages into one page https://ift.tt/yFvAOoG

Show HN: Merge Wikipedia articles across languages into one page https://ift.tt/UFn6qlr September 6, 2026 at 02:18AM

Show HN: Fast Cut Video tool for cutting video for Agents https://ift.tt/bYfB82K

Show HN: Fast Cut Video tool for cutting video for Agents Hi HN, Build this tool in a couple of hours with OpenAI Codex to scratch an itch. As part of my videos workflows I needed to cut the videos myself since the agent is pretty bad cutting and timing using only the transcription. But using a big app like Premiere or DaVinci Resolve was overkill so I used Astra to build an app tailored to that very task. It will be useful to others with the same problem. Tested only on Silicon Macs, so any feedback is welcome. As part of my workflow when the agent get the video it can open the app with the video or videos loaded in the timeline for me to cut and then export the cuts in a format the agent can use and continue the workflow. https://ift.tt/xtkD06y September 6, 2026 at 02:36AM

Show HN: Sageling - a local AI agent for Mac, Qwen 3.5 9B in-process via MLX https://ift.tt/OLtdxaQ

Show HN: Sageling - a local AI agent for Mac, Qwen 3.5 9B in-process via MLX A lot of my non-developer friends still think that AI is basically just Google or something you ask to write something and then copy paste it around... if they use it at all. When I ask them why they don't use the good stuff like Claude Cowork or its competitors, they tell me a few things: 1. Well, I don't wanna pay a bunch of money for it, and the $20 plans run out real fast. 2. I'm dealing with sensitive info (student grades, therapy notes, legal work, etc) and I don't wanna give it to anyone. So I built Sageling to give them a first taste of what a good coworking experience feels like. It's admittedly not going to be as powerful given it's running Qwen 3.5 9B, but with all of the harness' tricks, it a good first experience that can handle some impressive things for its size (see all the website videos). If you've heard similar things from your friends, send the link onto them =) https://sageling.ai/ September 5, 2026 at 01:00AM

Show HN: Coder Eval – A Framework for Evals https://ift.tt/s85qyQW

Show HN: Coder Eval – A Framework for Evals We needed a framework to write our evals in and easily update them, run A/B tests, set all kinds of constraints (ex: timeouts, number of turns), and configure the execution environment (ex: sandboxes, dependencies, how to handle AskQuestion). We also have an agent judge. It’s all in a YAML file now. We seem to be moving toward a world where companies rely more and more on evals to decide what to ship, so this should be super helpful for normalizing evals across teams. https://ift.tt/RE3vodK September 5, 2026 at 12:39AM

Show HN: Reactor Atlas https://ift.tt/MOHX1WJ

Show HN: Reactor Atlas Hi HN, I'm a nuclear engineer and tech entrepreneur. After working for 3 years in the National Atomic Energy Commision (CNEA) in HPC software for nuclear simulations, I co-founded ratherlabs.com, a software company providing blockchain solutions for startups. Rather Labs business reached ~6 million usd in annual revenue in 2024; now demand is decreasing as our niche clients are using AI to launch their MVPs. Now I'm joining my scientific background with my entrepreneurial inclinations to think of problems related to the energy industry. Nuclear is experiencing a renaissance now (it was in a dark age when I was studying after the Fukushima event) so I think this is the right moment for me to jump again into the field. Reactor atlas is an interactive nuclear reactor map and an intelligence layer on top of it. The basic layer indexes: - power reactors - research reactors - fuel facilities with their history and projection, by country. The project is solving a fragmented information ecosystem, where operational and commercial data is hard to conciliate. Also, I'm monitoring nuclear news associated with each of the facilities, political declarations that may affect the nuclear landscape and geo-phisical news (like earthquakes) that could affect operation. On top of the operational + news layer, I'm creating an intelligence layer that will help institutions of different types make faster decisions by subscribing to very specific alerts. As an engineer, I used to code in fortran and c++ when I was working at CNEA, and later I participated in the first Rather Labs projects architecting complex async systems, mostly using MERN stack. I'm no longer coding anymore. I'm focused on designing robust systems with AI agents. I mainly used Claude Fable 5.1 to develop reactoratlas.com, deploying on vercel and using mostly nextjs, threejs, postgreSQL and some cron jobs to query and update data. I miss coding as in the old days, but I haven't code a single line in this project. And I strongly believe we humans shouldn't code anymore: our responsibility is now on designing and supervising AI systems. Thanks for your attention! https://ift.tt/vwQjPzH September 3, 2026 at 06:03PM

Show HN: I made a word building game supporting anagrams and one handed use https://ift.tt/L1Aydzn

Show HN: I made a word building game supporting anagrams and one handed use Hi everyone, Wanted to share a game I built. It's called Unscramble! and I believe it's the simplest word building game. Rules: You get a few letters on screen. You need to make one word with all the letters. Tap a letter to select. Tap again to deselect. Faster you go, better you score. If you enter anagrams of the word it's looking for, it gives you extra points. If you are stuck, you can either "Ask Friend" or get Hint. You get extra points for getting the word fast but you don't get penalized for taking too long. I believe the simplicity of the game along with big touch buttons makes it perfect for one handed use. There's 6 difficulty levels in the game, and settings for things like toggling the timer, relaxing background music, sound effects, haptic feedback, removing the background animation. If you want to try: https://ift.tt/g3kABzH... Would love to hear feedback to improve it. September 3, 2026 at 08:07PM

Show HN: Devbar – Point at what to change. Leave a comment. Your agent ships it https://ift.tt/1Kq0hpn

Show HN: Devbar – Point at what to change. Leave a comment. Your agent ships it I built this toolbar to power my agentic ui/ux design flows. Too many times I found myself copy/pasting screenshots into Claude. Use devbar to select elements on a page, leave your notes and easily send them to your agent or copy-paste to your clipboard. Integrate with our API to send bug and feature reports directly to Slack...then auto-triage and implement with your agent. Are you tired of receiving bug reports without a URL or session information? With devbar.sh that's a remnant of the past. Give devbar to a product team or customers and have them mark up your entire site with annotations that can be handed off straight to the agent. https://devbar.sh September 4, 2026 at 12:49AM

Show HN: Sirenfall, a civil defense siren synthesized in Web Audio https://ift.tt/2xbcYZO

Show HN: Sirenfall, a civil defense siren synthesized in Web Audio I built a cool browser scene, a shelter window over a dystopian city in the rain. Pull the breaker and a siren tower spins up. The wind-down is super unsettling and I love it. The siren is not a recording. Two port rings make a 5:6 dual tone, 515 and 618 Hz. The horn turns at 4 RPM and everything (loudness, brightness, doppler and stereo position) follows the horn angle you can see on the tower. Rain and thunder are the only recordings. Build it yourself, source is one HTML file and MIT: https://ift.tt/8FVH2dC How it works: https://sirenfall.live/how-it-works Press F for fullscreen, S to save a picture. Landscape on phones. No cookies, no personal data, the only request besides audio is an anonymous page-count pixel. Appreciate any feedback and shoutout to the siren community! https://sirenfall.live/ September 4, 2026 at 02:14AM

Show HN: OwnTime – a chess clock for your day's priorities https://ift.tt/7JGtB3u

Show HN: OwnTime – a chess clock for your day's priorities I made OwnTime to balance between competing priorities in my life. The idea is based on two main influences: the concept of "roles" from "The 5 Choices" (2015), and my repeated failure to effectively implement time blocking due to the necessary flexibility in my role. The app allows you to define time budgets, which are not much more than a few mutually exclusive countdown timers. The UX is essentially that of a chess clock for an arbitrary number of players with configurable time. The whole point of the app is to kick you out of the running role/priority when its time is up. One feature that was essential for me was AlarmKit alarms, which only became possible last year (>= iOS 26.1). Another was watchOS support, as a natural surface for time-related matters. The current version is strictly focussed. The timers track time allocation during one day. All timers are reset at midnight. I didn't build any statistics - you can export the raw internal SQLite store and make any evaluation or dashboard you want from there. I don't plan to extend the app nor to convert it into a service. All data stays local on your devices (synced between phone and watch locally) and fully open to you. No need for an account or subscription. Thus, I ask for a small one-time fee of $1.99. The website has a short video and rendered preview: https://owntime.app If you want to go straight to the App Store: https://ift.tt/bX2dJsV I look forward to your comments and feedback. https://owntime.app/ September 2, 2026 at 02:59AM

Show HN: Arbitale – emergent choose your own adventure game https://ift.tt/kUTgEPy

Show HN: Arbitale – emergent choose your own adventure game Hi everyone! I am building Arbitale and it is currently in pre-alpha. I'm looking for play-testers who can give feedback on the product. The goal is to eventually have different characters in the game be their own agents, with emergent narratives that are totally unique to each playthrough. Each agent acts according to its own pre-written incentives. Would love to hear what you think! https://ift.tt/eB1TM0C September 3, 2026 at 12:12AM

Show HN: Codeknow – Architecture health scores for any codebase, no LLM needed https://ift.tt/N910ftB

Show HN: Codeknow – Architecture health scores for any codebase, no LLM needed https://ift.tt/GRx7HPj September 2, 2026 at 11:51PM

Show HN: Claude and ChatGPT need a datacenter. This runs on my phone https://ift.tt/LvMz4S3

Show HN: Claude and ChatGPT need a datacenter. This runs on my phone https://llmobi.pages.dev September 2, 2026 at 12:58AM

Show HN: Newton's Orchard – Browser-based space/gravity playground https://ift.tt/OtgGVwl

Show HN: Newton's Orchard – Browser-based space/gravity playground Hi HN! My son spent a lot of time in 5th grade playing with the 2-dimensional PhET gravity/space sims[1]. His STEM class uses it, and he was playing with it at home, and has been looking for more. I found several space sims/playgrounds online, including NASA's Eyes on the Solar System[2], but nothing that seemed to offer a real progression from what he was getting out of the PhET sims, so I built Newton's Orchard over the summer for him. https://ift.tt/kVtYcIn The source is also published at https://ift.tt/qV0YOmv It features deterministic time scrubbing, all bodies are editable, different preset systems and experiments, missions to complete (complete 3 to unlock the blackhole object type and mission), and a gallery for user submissions. I would very much appreciate feedback from HN - particularly from the lens of making it engaging and illuminating for students, and anyone that would like to just get a feel for how gravity works. Thank you! [1] https://ift.tt/XSqT3dx... [2] https://ift.tt/5FSnhvc https://ift.tt/kVtYcIn September 1, 2026 at 10:13PM

Show HN: Keel - A conductor, not an agent loop https://ift.tt/MvcbXo2

Show HN: Keel - A conductor, not an agent loop https://daneb.github.io/keel/ September 1, 2026 at 01:52AM

Show HN: Guess the AI model from its web design https://ift.tt/OoYNT9k

Show HN: Guess the AI model from its web design https://ift.tt/OeCqjJu September 1, 2026 at 01:10AM

Show HN: Corporate Mind Games – logic puzzles with a sarcastic corporate theme https://ift.tt/N7J4g96

Show HN: Corporate Mind Games – logic puzzles with a sarcastic corporate theme I have always enjoyed building and playing puzzles. I am a regular user of NYT Games and LinkedIn Games. I thought it would be fun to create some corporate-themed puzzles as a silly alternative to LinkedIn Games. So, I built Corporate Mind Games. The games are intended to be a little bit sassy and sarcastic, but I hope they are enjoyable and challenging. I was planning to post this on HN last week. However, many years ago, I made a game called Don't Wordle, which unexpectedly appeared on the front page last week. I ended up getting distracted by that, and I also figured it was more appropriate to post this game on HN on a Monday morning given the theme. So here we are. https://ift.tt/7vxuBYF August 31, 2026 at 09:38PM

Show HN: NFC Energy-Harvesting PCB Business Card with an MCU https://ift.tt/cjDBibe

Show HN: NFC Energy-Harvesting PCB Business Card with an MCU https://ift.tt/lx9ihz4 August 28, 2026 at 07:18PM

Show HN: Cogram Studio – CAD and BIM workspace for humans and agents https://ift.tt/5S9QkZF

Show HN: Cogram Studio – CAD and BIM workspace for humans and agents Hi HN, Rick and Alex here, co-founders of Cogram. We’ve been making project-management software for architects and engineers since 2023, and are now experimenting with a second product. Cogram Studio (studio.cogram.com) is a CAD and BIM workspace for AI agents to create three-dimensional models and dimensioned drawings. Studio runs FreeCAD ( https://ift.tt/HBWwn6u ) 1.1 headlessly, using the OpenCASCADE ( https://ift.tt/MnQBbNK ) geometry kernel. It imports and exports STEP, IFC, STL, DXF and FCStd files. Studio exposes an MCP server, so you can operate it from Claude Code, Codex, ChatGPT, or other agents. Tools cover scripting against FreeCAD, inspecting the model visually, CRUD operations on views, tables, and sheets, importing terrain, etc. Studio also provides a built-in agent based on Pi ( https://ift.tt/Ypnakh7 ) and a basic UI for 3D model inspection, measurement, view, table, and sheet creation. There are two ways to try it: 1. Bring your own agent. Point Codex or Claude Code at studio.cogram.com/skill.md and ask it to follow instructions there. This starts a one-hour Studio session and opens the modelling environment in your browser, connected to your agent. You need to confirm sign up only if you want to save the session. 2. Use Studio’s built-in agent. Submit a prompt at studio.cogram.com and sign up. You receive 50 free credits. Here are two models created by agents: - A simple bookshelf ( https://ift.tt/MG1eujp ) with two sheets - The Colosseum ( https://ift.tt/b3hcBMU ) [large, can take minutes to load], with two sheets showing dimensioned and annotated views. For now, Studio works best when you use it iteratively. If you ask an agent for a finished, complex model and “let it rip”, it may produce something that looks convincing but doesn't hold up to scrutiny. Agentic modelling feels roughly like where agentic programming was in 2024: useful for speeding up repetitive or bounded tasks but not yet reliable enough to complete long, complex jobs. Recent models have improved at CAD. We expect progress to accelerate as models become even better at reasoning across the different representations used in architecture and engineering: geometry, drawings, images, materials, physical constraints, specifications, regulations, code, etc. Early users and our own experience suggest that agents are already useful design collaborators. They can help with repetitive CAD work, fabrication options, part sourcing and cost estimates. We expect that as models improve, agents will be able to explore many different designs, run simulations, and check constraints across an entire project. CAD will become a shared workspace for humans and agents. Because design decisions made in CAD shape much of what is eventually built, even modest improvements could have wide effects. We’d love to hear your feedback and ideas if you give Studio a try. We’re also hiring across product, engineering and commercial roles. If you’re interested in working on interesting problems involving AI and the physical world, please take a look at our open positions at https://ift.tt/A8CFWtj . https://ift.tt/WHXhJRd August 31, 2026 at 12:19AM

Show HN: SSH Ache – open-source desktop SSH client with SFTP, tunnels and MCP https://ift.tt/EdXMT2B

Show HN: SSH Ache – open-source desktop SSH client with SFTP, tunnels and MCP https://ift.tt/Ugq6lxL August 30, 2026 at 01:12AM

Show HN: Convert PNG and JPG to clean SVG in seconds https://ift.tt/rdjnhlw

Show HN: Convert PNG and JPG to clean SVG in seconds https://ift.tt/YmJc8s1 August 30, 2026 at 02:24AM

Show HN: 3D Embodiment of your Git repo https://ift.tt/QUfgkvn

Show HN: 3D Embodiment of your Git repo https://ift.tt/9dNLcoX August 29, 2026 at 11:19PM

Show HN: Boop – tiny, self-hosted push notifications for your apps built in Go https://ift.tt/U7FpRWC

Show HN: Boop – tiny, self-hosted push notifications for your apps built in Go Hi HN, I built Boop because I wanted application events sent directly to my phone without paying for another service or routing everything through Slack or Telegram. Boop is a small, open-source server paired with an open-source iOS app. The server currently uses around 8 MB of memory on my machine. It’s deliberately not an observability platform or a replacement for Sentry. It receives events from your applications, sends native push notifications, and keeps them in a purpose-built mobile inbox. I use Elixir, so I built an integration for ErrorTracker. ErrorTracker still captures and stores the errors; the plugin sends them to Boop so I can see them on my phone: https://ift.tt/tbhk0FE There’s also a general Elixir client: https://ift.tt/ltgD4IF And a Node client: https://ift.tt/F5UEYBe The iOS app can be built and installed locally. I’ve included instructions for configuring private push notifications for your own device, so you don’t need to release anything through the App Store. Although errors were my original use case, Boop can receive any event worth knowing about: failed jobs, deployments, signups, payments, low disk space, or anything else your application can send. Built in Go because I wanted to save memory on my self-hosted machine so Go and Svelte felt like a good combo. Everything is free and open source. It’s early, so I’d especially appreciate feedback on the architecture, setup process, and which integrations would make it useful to others. https://ift.tt/srWyw82 August 29, 2026 at 12:33AM

Show HN: go-binsync – Go binary patches up to 67× smaller than bsdiff https://ift.tt/7hFIyez

Show HN: go-binsync – Go binary patches up to 67× smaller than bsdiff This project is a little performance-optimization experiment focused on reducing the size of Go binary patches, which can be useful for quick incremental updates of live services. When a Go program grows by a few bytes through an incremental change, a bunch of related references and offsets throughout the compiled binary end up changing that makes general-purpose binary-diff encoders inefficient: `zstd --patch-from` produces a 530kb patch for a one-line change in a 30MB binary. bsdiff improves upon this (150KB patch) thanks to a delta compression algorithm that can handle relative offsets. go-binsync goes a step further for Go binaries by borrowing an idea from Courgette, the technique Google uses to ship Chrome updates: read the structure the compiler left behind, predict the expected results from that structure, and send only the correction. Courgette gets that structure by disassembling; go-binsync gets more detailed Go-specific structure from additional metadata embedded in every compiled Go binary. The end result is a 2,262-byte patch for the one-line change, or a 67× improvement over the bsdiff result. Still just a proof of concept (no CGO, no debug symbols, amd64 only) but I thought others might find the initial results interesting. I think this predictive-encoding approach could be generalized beyond Go binaries to efficient compression in other domains where some kind of specialized predictive structure is available. https://ift.tt/UflNzZG August 28, 2026 at 01:17AM

Show HN: Voronoi Go https://ift.tt/tnUedqh

Show HN: Voronoi Go I posted once before but wanted to share again because a lot has changed. There's now a fairly strong bot to play against (contributed by a community member) and also correspondence games. The combination of these things helps a bit in finding people to play against. https://voronoigo.com/ August 27, 2026 at 11:33PM

Show HN: Convolens – Real time slides and fact-checking https://ift.tt/xzIrsJM

Show HN: Convolens – Real time slides and fact-checking Convolens is a Mac desktop app that records and transcribes your conversation on device, and turns it into slides, fact-checks, and infographics. I built the real time slides because I'm constantly losing focus during meetings and needed something I can quickly glance at and know exactly where I'm at and what happened during my "snooze". As a whole, Convolens lets you: - Record and transcribe your meetings / sessions locally. - Generate Slide decks, Infographics, and Fact-checks from your conversation (among other things). - Chat with your meeting/session and research anything that you need. Anyway, please check out the app we have a great free tier. Any and all comments are greatly appreciated! https://ift.tt/IYSrHwc August 27, 2026 at 01:20AM

Show HN: I made a Raspberry with Qwen my local car AI https://ift.tt/RjpnxgM

Show HN: I made a Raspberry with Qwen my local car AI Found that you can actually run a 35B Qwen model on a Pi with very impressive intelligence and stability. Built connectors for car ODB to read all about car internals, and manufacturer's cloud service for stuff like changing AC or opening/ locking doors. Gave it info such as the full car manual. And then hooked it up with my other agents in our discussion room! So now it can answer car questions such as "when should I add oil and what kind of oil?" and help you fully offline, and when online talk with the agent family that includes all the most powerful models so they know how the car is, plan new features and develop itself with them. For example, if car breaks and can't move the car agent informs my agent family and they can already look for a suitable train ticket without me needing to check things or do something. https://ift.tt/jBSsEwo August 25, 2026 at 08:50PM

Show HN: Chrome extension that gives you the TlDR from YouTube without the watch https://ift.tt/wd2KNxU

Show HN: Chrome extension that gives you the TlDR from YouTube without the watch https://addketchup.app/ August 24, 2026 at 11:37PM

Show HN: Civic Nightmare –Browser JRPG about a citizen in a savage civilization https://ift.tt/SyGEq1h

Show HN: Civic Nightmare –Browser JRPG about a citizen in a savage civilization Observing the world as it turns, I created Civic Nightmare, a small browser-based JRPG that explores the absurdity of contemporary politics. I've included many characters such as: Trump, Putin, Macron, Lagarde, Musk, etc., who become characters within the same surreal world, with different dialogues and minigames built around their public personas and none of them is really spared. The game runs in the browser, was created with Godot, and is open source (contributions are welcome). It's a small experiment, but I'm happy to continue it; ultimately, it portrays a simple citizen in the midst of a savage civilization. https://ift.tt/ULBrHj7 August 23, 2026 at 11:40PM

Show HN: Built a CLI to find and disable telemetry for package.json dependencies https://ift.tt/nTSDjLs

Show HN: Built a CLI to find and disable telemetry for package.json dependencies https://ift.tt/53DBLSy August 23, 2026 at 01:58AM

Show HN: Zcomplete – Shell Typo Correction https://ift.tt/uPplZHd

Show HN: Zcomplete – Shell Typo Correction https://ift.tt/vyUm1tI August 22, 2026 at 12:48AM

Show HN: Traccia - Observability, Runtime Control & Audit for agents https://ift.tt/4tdJ7zW

Show HN: Traccia - Observability, Runtime Control & Audit for agents AI applications are becoming agents, which has started to take autonomous decisions. There are plenty of tools and platform available to trace, and observe what an agent or llms calls does. They are good in what they do, but tracing and observability isnt enough for AI agents era. We need a solution that can help you observe, evaluate, create run time policies to govern and finally audit the actions of the agent. We built Traccia to solve this problem. The good part, all of these can be achieved by just writing few lines of code. Traccia has an open-sourced sdk that can work with your existing observability tool like grafana, tempo, jaeger, etc. In case you need more than just observability, Traccia provides the platform to evaluate, control and audit the agents. The platform is easy to use. The product's documentation is quite extensive. It is also cloud vendor and framework agnostic. Traccia is being built by an Indian start up ,based out of Bengaluru. We are running a 3 months free trials so that you can explore without any strings attached. We are open to improvise and get better so please drop your comments and feedbacks. https://traccia.ai/ August 21, 2026 at 11:50PM

Show HN: CSVtoTable – turn a CSV/XLSX into one self-contained HTML file https://ift.tt/8VghNqb

Show HN: CSVtoTable – turn a CSV/XLSX into one self-contained HTML file https://ift.tt/Ae2uVoB August 22, 2026 at 12:23AM

Show HN: Interactive map of the Odyssey with tap-to-gloss Homeric Greek https://ift.tt/PN67jKe

Show HN: Interactive map of the Odyssey with tap-to-gloss Homeric Greek Built an interactive atlas of Odysseus's voyage. See where the stops fall in today's world, with etymological and knowledge nuggets. 17 stops from Troy to Ithaca. Every stop has Homer's actual Greek (Perseus TEI), Murray's 1919 translation, and every single Greek word is tappable for a translation. Press N and the ancient chart swaps to today's satellite view: these are real places (e.g. Scylla refers to a town called Scilla in Calabria). Stack: SvelteKit static + MapLibre, no backend, all public-domain texts and art with a full colophon. Please leave corrections and feedback! https://ift.tt/5XgOK21 August 21, 2026 at 11:41PM

Show HN: Huzzah – a novel approach to coding with AI https://ift.tt/V0tS1wx

Show HN: Huzzah – a novel approach to coding with AI Hello everyone. I've been working on this experimental editor called Huzzah. I've been working almost exclusively with coding agents since January of this year, and over the past few months I began to feel utterly exhausted by them. They're great, but I'm finding it more and more tedious to write full sentences for every change I want. Not only that, but it seems there's a complexity limit for codebases - beyond a certain point the agent begins confusing itself. I'd like to go back to writing code, but I don't want to go all the way back to fully manual coding. So I've come up with this interaction paradigm where you: 1. write pseudocode in whatever way makes the most sense to you 2. on save, the editor synchronizes your work to real source code 3. the pseudocode is persisted alongside the generated code, making your prompt effectively a stored record of intent. It may not work for every use case, but in my initial playthroughs I've found it very enjoyable. Right now it's just a proof of concept - installation instructions are here in the readme: https://ift.tt/xblgTG7 You can also watch a video of it in action here: https://ift.tt/8OoJDgk Cheers! https://ift.tt/xnJuvrE August 21, 2026 at 12:35AM

Show HN: Language Audio Trainer – Learn languages without looking at the screen https://ift.tt/SWa6UwQ

Show HN: Language Audio Trainer – Learn languages without looking at the screen I recently built a language learning app with a slightly different approach. I deliberately didn't want it to be another Duolingo-like app. I think users should be able to choose what they want to learn and when. The main idea behind Language Audio Trainer is that you can simply press Play and listen to useful phrases in the background with the screen off — while walking, driving, cooking, etc. You can skip or repeat phrases, change the speech speed and number of repetitions, and choose the translation direction. There is also a flashcard mode for when you want to study more actively. I'd be interested to hear what you think about this approach to language learning. iOS: https://ift.tt/quxOSDM... Android: https://ift.tt/fS7bmQT... https://playling.netlify.app/ August 20, 2026 at 11:47PM

Show HN: terminal-code – VS Code inside the terminal https://ift.tt/fDicBYv

Show HN: terminal-code – VS Code inside the terminal https://ift.tt/q3kwxt2 August 19, 2026 at 10:43PM

Show HN: Voidleap Code – agentic IDE, own harness, swap models mid-conversation https://ift.tt/1oDCuka

Show HN: Voidleap Code – agentic IDE, own harness, swap models mid-conversation We wanted to build a development environment that can make you a better agentic engineer, not a tool that makes money when you waste tokens. A tool where you can swap models between turns, edit the context, and see every agent action. To do it, we had to build our own harness. Free to use. We don't sell inference, so bring your own key. The sore spot is Claude subscriptions. We can't support them because of Anthropic's terms. The app runs on your machine, and your data never touches our servers. We've been building Voidleap Code using Voidleap Code since January. We didn't rush to launch, but instead focused on getting the architecture and package just right. There are still more features to build, and more polishing to do, but it's ready for you to try. Judge it for yourself and tell us what you think. https://voidleap.com/ August 19, 2026 at 12:10AM

Show HN: PantheonGPU – GPU health testing and AI workload benchmarking https://ift.tt/AZgk7hD

Show HN: PantheonGPU – GPU health testing and AI workload benchmarking Hi HN, I built PantheonGPU because I wanted a better way to answer a simple question: is this GPU actually healthy and performing the way it should? A GPU can show normal temperatures and utilization and still be underperforming, unstable under certain workloads, or have memory, PCIe, or configuration issues. PantheonGPU actively tests the GPU instead of only monitoring telemetry. It currently includes 45+ tests covering compute, tensor workloads, memory, cache, PCIe, thermals, stability, and AI/LLM inference. It supports both NVIDIA CUDA and AMD ROCm. I’m also exploring a larger use case: running Pantheon across GPU fleets to identify individual GPUs that behave differently from the rest of a server or cluster. I’d especially appreciate feedback from people running AI infrastructure, multi-GPU systems, local LLMs, or GPU clouds. https://ift.tt/jHaidbF August 19, 2026 at 12:17AM

Show HN: Open-source comment section widget, Disqus alternative https://ift.tt/g4qQ198

Show HN: Open-source comment section widget, Disqus alternative https://ift.tt/B7nFMIo August 17, 2026 at 11:36PM

Show HN: Interactive component to map fibre breaks (OTDR) https://ift.tt/J8AzW9b

Show HN: Interactive component to map fibre breaks (OTDR) Added an OTDR trace component as the latest in my component library for datacentre/network apps. Mainly for my own use in rackout. https://ift.tt/kuVY8l1 August 17, 2026 at 02:17AM

Show HN: I shrank DeepSeek V4 Flash to 57GB and it wrote a compiler on my Mac https://ift.tt/0jE5dbD

Show HN: I shrank DeepSeek V4 Flash to 57GB and it wrote a compiler on my Mac I built a specialized package of DeepSeek V4 Flash 0731 (originally 284B total parameters, 13B active), preserving reasoning, tool calling and coding capabilities: https://ift.tt/z0fqBYF... I let it write a minimal C compiler targeting ARM64, then test the result with Fibonacci and FizzBuzz programs, and it succeeded in less than 1 hour, with the full recording at: https://youtu.be/XiwSilmV8B0 You can run it on Silicon Macs with my engine https://ift.tt/7JlDyHX , while one of the core libraries developed to obtain this result is available at https://ift.tt/OFVHc7b . The above recording was on a 128GB memory MacBook M3 Max, but you can also run it on 32GB MacBooks with a very usable context (128K tokens) and projected 5 tok/s. I did try it on a fanless 16GB memory MacBook Air M1 (1.39 tok/s), but unfortunately the available context was very small. How: - First, efficient quantisation: mlx-iqk takes advantage of IQ_K tensor encoding, more efficient than the ones available via llama.cpp or barebones MLX, originally designed by Iwan Kawrakow - I also changed the layout to a k-contiguous one, to make it faster, at least in this Metal setup. - Second, expert pruning: each of the 40 learned-router layers had 256 experts, and not all of them are equally important for the coding use cases. I removed 80B parameters - this is a known technique called REAP, shared at https://ift.tt/H2z4qLS . - Third: balancing the cheapest IQ1_S_R4 tensor encoding (~1.5 bits per weight), selectively promoting projections to IQ2_KS or IQ2_K where the measured error reduction justified the bytes. One of the main ideas was not only to save relevant knowledge, but also to not make it forget how to... stop thinking, how to use reasoning. In the first experiments, it would sometimes reason for thousands of tokens without closing its thinking section, or it would go in loops. Then I solved this by heavily weighting tool-calling traces and structured reasoning in the calibration mix. https://ift.tt/Kis7U5e August 16, 2026 at 10:43PM

Show HN: Hacker News Top Stories as Feeds to Use with RSS/Atom with Summaries https://ift.tt/jfbDUYK

Show HN: Hacker News Top Stories as Feeds to Use with RSS/Atom with Summaries Hey all, I’ve made this bot, it fetches every story that enters the HN Top 10, summarizes it with AI to a tweet-sized textlog note and publishes it. textlog.cc offers these endpoints as RSS/Atom through textlog.cc/u/hn10.rss and textlog.cc/u/hn10.atom so you can subscribe easily. Enjoy! https://textlog.cc/u/hn10 August 17, 2026 at 01:31AM

Show HN: built my 15-year-old game idea https://ift.tt/OCEHg5d

Show HN: built my 15-year-old game idea Distro Fighter: WARS is in closed beta, but HN gets its own door: https://ift.tt/MrNigkW - the arcade at https://ift.tt/JpkY0fC is open to everyone. Promotions happen at midnight tonight (weekly) and the seasons (migration) are quarterly. With a massive surprise at the end of each year. August 16, 2026 at 11:05PM

Show HN: Bribes.fyi – Compare bribes statistics department wise https://ift.tt/7OwFgl0

Show HN: Bribes.fyi – Compare bribes statistics department wise https://ift.tt/uj2VnTD August 16, 2026 at 03:41AM

Show HN: ElevenMusic Sounds, loop library that grows as other people generate https://ift.tt/sIb0JVW

Show HN: ElevenMusic Sounds, loop library that grows as other people generate https://ift.tt/Y2fjEbp August 16, 2026 at 03:52AM

Show HN: Live Claude Usage HUD for a $38 Thermalright Trofeo Vision LCD https://ift.tt/kJucOI3

Show HN: Live Claude Usage HUD for a $38 Thermalright Trofeo Vision LCD https://ift.tt/A1CQXIV August 16, 2026 at 03:12AM

Show HN: Every MUNI, BART and Caltrain in SF on a Live Map https://ift.tt/9Ub7PXq

Show HN: Every MUNI, BART and Caltrain in SF on a Live Map https://ift.tt/oJbgNS6 August 16, 2026 at 12:39AM

Show HN: Biasly.ai – Bias detection with historical context https://ift.tt/eZivTof

Show HN: Biasly.ai – Bias detection with historical context https://biasly.ai/ August 15, 2026 at 12:53AM

Show HN: PasteDaemon – Automatically remove tracking from URLs and more https://ift.tt/iae3fbm

Show HN: PasteDaemon – Automatically remove tracking from URLs and more https://pastedaemon.app August 15, 2026 at 12:12AM

Show HN: LymeScribe – one computer on your network transcribes for the rest https://ift.tt/TvrWpyE

Show HN: LymeScribe – one computer on your network transcribes for the rest Transcribed with LymeScribe just before posting this: "I realize it's a little bit late in the day to be posting on Hacker News. However, I've been looking at this frog for a good two weeks now, and F it, I'm just going to ship it. I've posted on Hacker News now like three or four times with little to no results. So if a tree falls in the woods..." (I censored the F word, but it transcribed just fine.) TL;DR: LymeScribe is local speech to text for Mac and Windows: dictate into any app, or drop in a recording and get a transcript with speaker labels, and nothing goes to a server you don't own. On a machine that can handle it, it all runs right there. On anything that can't, or anywhere you'd rather keep transcription in one place, one computer does the work for the rest of the network. Offices care about the second one, because the audio and the transcripts never leave hardware they control. This whole thing started as a command line program I built to transcribe and label speakers in audio files sitting on my computer, mostly voice notes using Whisper on my gaming PC. A few friends started asking me to run their meeting recordings through it, which I was happy to do until it got frequent enough to be a chore. So I built them an app that they could drag a file onto themselves, with my gaming PC doing the actual work and sending the results back to their clipboard. That drag and drop piece is still in the app. Since then I added real time dictation, which uses the same local models. When I started thinking about actually selling this thing, I found the market was more crowded than I expected, which was humbling for about a day. What kept me going is that none of the others let one machine do the work for everyone else... that and there's just something sort of cool about owning and using my own transcription software. So, here we are. An older machine can handle its own dictation on the small English models. I found that out when I tried the app on a ten year old iMac expecting it to fail, and deleted the code I'd written to keep machines like it out. Speaker labels are the part that still wants real hardware, and that's where pointing that old machine at a stronger one on the network earns its keep. One license covers the house. It's local by design, and you can test that yourself: unplug the Ethernet mid dictation and it keeps going. Works on a plane. The free client never talks to me at all. Unlocking hosting means one activation call, and after that the license is verified locally against a signed document, so an activated install keeps working with no internet and would keep working if my licensing server went away. AI assisted summaries and translation are experimental. They ship turned off, and you can turn them on if you dare. They only talk to an endpoint you choose, your own key or a local model. The client is free on Mac and Windows. Hosting is a one time $39 unlock with a 7 day trial that starts the first time you host a transcription. It's a perpetual license: you own this major version, point updates are free, and if there's ever a next major version it's a discounted upgrade rather than a new purchase. I'm tired of renting everything, aren't you? Two things worth knowing before you download. The Windows installer is signed, but the certificate is new enough that Chrome and SmartScreen may still warn you about it. And the paid unlock is US only for now, while I work out the international side. Feedback welcome, especially from anyone who has fought text injection on Windows. There's also a heavier server for offices, administered through a web app that handles keys, transcription history, logs, etc. Frog reference: "There's a saying: if you have to eat a frog, it's best you don't spend a whole lot of time looking at it. And if you have to eat two, don't start with the small one." Randy Pausch - Time Management - https://www.youtube.com/watch?v=oTugjssqOT0 https://ift.tt/TaktmH4 August 13, 2026 at 11:48PM

Show HN: OpenCode Senses, An insanely fast and highly accurate vision plugin https://ift.tt/w4KDAJQ

Show HN: OpenCode Senses, An insanely fast and highly accurate vision plugin The vision plugin for OpenCode that truly understands images. Inspect, read, and reason about any screenshot or picture with deeper understanding than any other plugin — fully local, private, and free. Normally, it takes 300ms to analyse one image on my laptop, which is pretty fast for a local vision model. I use moondream2 as my vision model, you can set your custom model like moondream3.1 if you have a good GPU (for comparison I have currently have an RTX 3050). It works cross-platform. Just follow the README. If you like my work, you leave me a tip as an act for supporting open source!! Looking for some feedback! Thank you. NPM: https://ift.tt/4IqAhgn https://ift.tt/UJiDBM2 August 13, 2026 at 11:43PM

Show HN: Programmable timer web app (for gym workouts or stretching sessions) https://ift.tt/QwO6dkg

Show HN: Programmable timer web app (for gym workouts or stretching sessions) Over the last couple of months, I’ve been building a timer web app for myself that I use for workout and stretching sessions. My main use-case is gym routines that consist of repeatable sequences, e.g. where you are holding certain positions for a set time (rinse and repeat). The app counts down the program, beeps, and reads the activities out loud. Two things (I suppose) are special about it: - The timers are “programmable”, so you can freely express your own routines and procedures in a declarative notation. - The app is all static (no backend): the entire program is encoded in the URL and can be bookmarked or shared/transferred via QR-code. You can check it out at https://ift.tt/naEmYB7 , optionally with a demo program pre-loaded: https://ift.tt/HpwdZfz . Source code is at https://ift.tt/03I2UfR . I’ve also written up a small behind-the-scenes on my blog: https://ift.tt/THupEMG https://ift.tt/naEmYB7 August 12, 2026 at 11:57PM

Show HN: Mooneva Cycle – Offline period tracker with no servers and no accounts https://ift.tt/9iOVSP1

Show HN: Mooneva Cycle – Offline period tracker with no servers and no accounts Data stays encrypted on your device (PBKDF2/AES-GCM), no internet permission, nothing to breach or subpoena. GPL-3.0, TypeScript/React + Capacitor. Android & iOS. https://ift.tt/j69GpHl August 13, 2026 at 12:40AM

Show HN: StarryKit – MCP for editable slides, posters and all visual designs https://ift.tt/KNFSfq6

Show HN: StarryKit – MCP for editable slides, posters and all visual designs https://ift.tt/eD3tCH0 August 12, 2026 at 11:34PM

Show HN: Pulp – Zero-allocation C11 telemetry engine (28M logs/SEC to disk) https://ift.tt/AIsJt5a

Show HN: Pulp – Zero-allocation C11 telemetry engine (28M logs/SEC to disk) https://ift.tt/EX0DKTp August 12, 2026 at 12:15AM

Show HN: HyperSAE – Hyperbolic Sparse Autoencoders for LLM Interpretability https://ift.tt/3hgqInu

Show HN: HyperSAE – Hyperbolic Sparse Autoencoders for LLM Interpretability https://ift.tt/5uVS0XQ August 11, 2026 at 11:49PM

Show HN: Graph2agent; Mermaid diagrams, explained for agents https://ift.tt/xywP7eQ

Show HN: Graph2agent; Mermaid diagrams, explained for agents During the implementation of a huge high performance service. In order to keep context small (mainly for humans) I kept the specs into mermaid diagrams. When communicating with humans; diagrams were easy to follow and to remember. But when I asked the agent to implement what's in the diagram, most of the times it failed. So I came into conclusion that agents are good into writing mermaid diagrams but they are not good into reading them. I built graph2agent in order to deterministically (without inference :) ) convert mermaid diagrams into digestible rich text for agents. examples: https://ift.tt/qDyvQHM... This gave us 50% error reduction for any class of diagrams and 80% error reduction for sequence diagrams specifically. Also Input tokens increased on avg by 8% (which is expected) but Reasoning tokens dropped by almost 50%. You can use it either with MCP so agents can call it with any mermaid diagram, and also can put it in pre-commit jobs and run it on every PR so all diagrams are agent ready! I hope you like it! Let me know your thoughts! https://graph2agent.github.io/ August 11, 2026 at 02:59AM

Show HN: My local climbing gym from photogrammetry https://ift.tt/FbERNxp

Show HN: My local climbing gym from photogrammetry Commented on yesterday's Ask HN: What are you working on? (August 2026), thought I might as well submit a Show HN. If you see climbing world cup/championship, there is this 3D modelling thing [1]. I want that for my weekly bouldering. I scanned my local climbing gym into 3D mesh using iphone. Built a simple editor to trim, merge, move/rotate meshes. You can interact with the mesh, view routes, view climb, etc. So this is unlike many gaussian splatting projects where the main use is for viewing. I built a pipeline in updating climbing walls. Climbing routes are manually annotated. Climbing videos are registered against the 3D mesh. Based on one input video, body positions resolved into 3D/4D space. you can view the body landmarks from different angle. COLMAP, OpenMVS, fastapi, svelte, database is just local json files. A read only build is exported so I can host on github page If you climb, or know someone who climbs, would love to hear your feedback. Do you usually record your climbs? If I make this a service, what will make you use it? [1] https://www.youtube.com/shorts/8zdUOaCr6DY https://kmcheung12.github.io/climb-preview/tour/ae43c6e5 August 11, 2026 at 03:09AM

Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots https://ift.tt/wS5y2TL

Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges 300-700 on sub-$200 phones such as the Samsung A-Series. On the tool call and mobile device use benchmarks, Needle 2 trades wins with closest small models like LFM2.5 230M and Apple Foundation Model, at 5x to 70x smaller, both at f16 vs Needle 2 at 2bit. Needle is based on Simple Attention Networks from our paper ( https://ift.tt/Z7O9KUj ). Edge AI has lately meant Macs and PCs, but that is just 1.5 billion of over 21 billion connected IoT devices in the world today, and in emerging markets most phones ship under $200, no NPU, cheap GPUs. These include budget phones, Raspberry Pis, microcontrollers, wearables, small robots like Reachy Mini, and connected home devices. A conventional transformer of Needle's width and depth spends 164 MFLOPs per token, and even one squeezed down to Needle's parameter count spends 87, Needle spends 70. Even on a high-end phone, an always-on assistant lives inside a power budget; every MFLOP is milliwatt-hours, and Needle spends 7x to 85x fewer of them per token than the smallest performant LLMs. More about the architecture in the link. When we structure intelligence for consumer devices as functions with typed parameters, the only hard part is mapping a messy sentence onto them; which function, with which values. Our research found that when framed that way, the problem needs no world knowledge and no open-ended prose, which is why 45M parameters suffice. Needle 2 expands to structured extraction where the schema can be passed in-place of tools and the model returns structured output. You can use Needle as a text-classification model with an enum field, as a summarization model by providing a schema that extracts key fields, everything but free-range decode. Every product has its own tool vocabulary and fine-tuning needle helps it achieve frontier-level performance on custom tasks, so using the python package ( https://ift.tt/xGTEdZD ), Needle can be fine-tuned Needle on a Mac/PC in minutes to a few hours, with automated data-generation pipeline, just pass a couple samples. Nonetheless, every response carries a learned confidence score based our Cactus Hybrid technique. If above your threshold, act, below it, escalate to the cloud or bigger model. Combining Needle 2 with a private DeepSeek-v4-Flash deployment works particularly well for enterprise-level tasks at barely any cost, we can help with this setup. We have put a lot of thoughts into Needle 2 but might still be missing quite a lot, please use the playground in the provided link to test Needle and share your thoughts, always appreciated! https://ift.tt/c4tQqnD August 10, 2026 at 10:52PM

Show HN: 100% native Swift harness (NOT Electron) https://ift.tt/EXfWiPV

Show HN: 100% native Swift harness (NOT Electron) hi everybody, I’ve been working on this harness that is all native Swift for macOS. It’s fully featured with every feature i could find in cline, codex, and claude code. There is all swift command line too It’s taking me a long, long time, a few months to build this, and it’s fully open source Apache 2 licensed. Hoping people fork this and make many branches I’m looking for people who want to work on something that has much lower memory usage and much more potential to be just more efficient. Every other single harness has is written in using electron, so this harness is really unique in this way. It’s connected to trusted router so that it has end-to-end encryption confidential mode as well as access to hundreds of models, any model in the world. It works great with Deepseek. it’s great for swift development ios development. and for people who love Linux, I also made a compatibility layer that lets you compile SwiftUI into native Linux so that you either can new or QT actually so that you can just compile all the code directly and make it run on Linux https://ift.tt/5w8n1OG August 10, 2026 at 06:56PM

Show HN: Run your GitHub Actions locally or self-hosted in isolated microvms https://ift.tt/d4i6syT

Show HN: Run your GitHub Actions locally or self-hosted in isolated microvms Hey HN. I've been frustrated with Github Actions' reliability, and inability to run workflows locally. Preloop is a Rust reimplementation of the GitHub Actions, both the runner(tracking the latest version) and the control plane that runs in hardware-isolated microvms on MacOS/Linux/Windows(we use smolvm project that uses the libkrun vmm).The microvms starts in <400ms from a packed artifact, and cow-clones for each job are instant. The control plane speaks the exact official runner protocol, so the unmodified actions/runner binary can register, poll, execute, and report against it. Your existing workflow files run unchanged, but on your own hardware with zero GitHub-hosted minutes. Locally, you can also run uncomitted changes so you dont have to create a commit to run ci. If you are working solo or in a small team and have fast local hardware, you can use something like DHH's gh-signoff extension and merge directly so long as certain checks pass. We also support features such as pause-on-failure where upon failure, the vm is paused, opens up a shell, and allows you to fix the errors, then you can retry without rerunning all the jobs that worked(new step/job runs in a new fresh microvm to verify the changes) or you can attach directly to a running vm and see what steps each jobs are doing in real-time. Preloop also implements the Debug Adapter Protocol so you or your agent can drive your CI locally(with the built-in client) or you can use a DAP client like Vscode. You can also submit your changes to the server for CI to run and then after it can open a draft PR for you, with the updated checks, so we dont only rely on Webhooks from Github. I've invested heavily in ensuring conformance with the official runner protocol so I do different kinds of mitm proxying to make sure not only the request/response bodies match but also down to the job/step level conclusions/logs/annotations etc. Effectively, the official runner should work with our control plane. Act, Forgejo are all great, but they dont faithfully implement the official runner protocol so in practice some workflows dont quite work out of the box, and they also run the jobs in docker containers. Forgejo has the closest compatibility and is probably still a good option if you are fully migrating off github. With Act, there's a few mostly server-side features it doesnt implement(concurrency, some matrix features, oidc etc). forgejo has the closest compatibility, and is a good option if you are fully migrating off Github. Agent-ci is also a great option that uses the official runner image and implements the official protocol, but it is designed to run locally, runs in containers, and doesnt support some features we do(concurrency, newer V2 cache, Github token etc). Preloop is designed to also be run as a peristent server so we implement more submit updates to the checks api. Lot more stuff coming, but i figured this is a good point to share with the community incase it might be interesting to some folks. Feel free to try it out. Website: https://preloop.dev Github: https://github.com/preloopdev/preloop https://preloop.dev August 10, 2026 at 01:25AM

Show HN: Inertia – Not your Grandfathers animation editor https://ift.tt/0PbBOYa

Show HN: Inertia – Not your Grandfathers animation editor https://ift.tt/K37HyMS August 9, 2026 at 03:57AM

Show HN: A Discord bot running in a 4MiB microVM https://ift.tt/rx8diA3

Show HN: A Discord bot running in a 4MiB microVM https://ift.tt/GquysbB August 8, 2026 at 11:04PM

Show HN: Algebruh - Cross-check arithmetic claims with Z3, cvc5, and Lean https://ift.tt/ytLl4vO

Show HN: Algebruh - Cross-check arithmetic claims with Z3, cvc5, and Lean https://ift.tt/fcNwrIH August 8, 2026 at 11:34PM

Show HN: Check if any of the $656M in unclaimed royalties at The MLC is yours https://ift.tt/qYFMHKa

Show HN: Check if any of the $656M in unclaimed royalties at The MLC is yours https://pub.doub.ly/ August 7, 2026 at 11:05PM

Show HN: Zaivern Code – a Rust cockpit for parallel AI coding agents https://ift.tt/gC24wh3

Show HN: Zaivern Code – a Rust cockpit for parallel AI coding agents https://ift.tt/JdxwrWs August 8, 2026 at 12:53AM

Show HN: Mousecrack – Teaching an LSTM to move a mouse like a human https://ift.tt/t1VPjba

Show HN: Mousecrack – Teaching an LSTM to move a mouse like a human https://ift.tt/0Tfzg8v August 7, 2026 at 10:23PM

Show HN: ARF – a record format for AI evaluation runs, with reproducible digests https://ift.tt/eCOY5Hy

Show HN: ARF – a record format for AI evaluation runs, with reproducible digests https://www.korvo.xyz/arf August 7, 2026 at 04:55AM