Show HN: Shipwithmuse.live – a catalog of things people built with Muse https://ift.tt/OitHzVo

Show HN: Shipwithmuse.live – a catalog of things people built with Muse https://shipwithmuse.live/ September 27, 2026 at 09:38AM

Show HN: CaughtShipping – curfew app for developers, enforced by a public wall https://ift.tt/VkWYQXA

Show HN: CaughtShipping – curfew app for developers, enforced by a public wall I am always working well past the normal work hours. Sometimes even past midnight. Then one day I thought, what if I could have something to keep me accountable for doing this? So I built a small app that will call me out when I break my downtime. You set a Curfew in the app (Curfew must start between 8:00 PM and 10:00 PM). If a dev app (editor, terminal, etc.) is used on your computer after the set curfew, a countdown starts. If you close the app before the timer runs out, you are safe. If you keep working, you get "caught". Your streak is now broken, and you will be posted on the Wall, on the public blotter section. If you keep your nights clean, you will rank higher and higher on the Wall of Rest instead. The App does not look at what work you do; we don't care about that. I would love to get feedback from as many users as possible. The app is free, and a 7-day report is available locally in the app itself. There is a paid plan that can give you up to 90 days of reports! https://ift.tt/zcSaKeL September 26, 2026 at 11:27PM

Show HN: Blender Copilot https://ift.tt/kMVueql

Show HN: Blender Copilot Deepseek generated Blender harness in 7USD. I wanted to remake my 6DoF spaceship flying prototype. What I did not want to do was model the spaceship. Manually. In Blender. So instead of spending a month learning to model, I built a Copilot inside Blender in a day. Which is the same thing, except I still cannot model. A chat panel in the 3D viewport sidebar. I type a sentence. The model writes Python, and it runs against my actual scene, the file open on screen, not a copy that some other process has to keep in sync. Then I sat down and had a conversation with my own addon. Five sentences: 1. Make a scifi looking spaceship. It should look scifi-y 2. Add RCS thrusters to get 6DoF flight 3. Make the RCS thrusters match the scifi look. And also position them properly. 4. Give the entire Spaceship a nice flying animation. Make it smooth. Roll and sway. 5. Add exhaust flames to main thrusters as well as RCS thrusters. animate the RCS thrusters to fire in sync with the animated motion. they should fire the correct ones so that expected motion should happen. 15 minutes. 52 tool calls. A ship with swept wings, a tail fin and a glass canopy. Four sets of steering thrusters, 22 exhaust flames. A full flight animation. The bit I did not expect. It checked every one of its own thrusters to make sure nothing was in the way. Found the rear ones were firing straight into the side of the ship. So it rebuilt them, angled them outward, moved them to the wingtips, and checked them all again. Nobody asked it to do that. It decided exhaust should not be firing into the ship it just built. Total bill for building the tool: $7.18. 3,833 requests, 613M tokens, 97% served from cache. One spaceship: about a seventh of a cent. Now the uncomfortable part. I didn't model a single vertex. I didn't read Blender's addon dev docs. I didn't learn its Python API, or how to draw a panel in it. Everything the tool needed to know, it asked the running Blender instead. I didn't learn how to build an agent harness either. I built one anyway. I didn't become a Blender artist. I became the person who gave hands to a model. Recently I read someone who described his new job: every spec, ticket and fix written by an AI, nobody reading any of it, twelve-hour days spent pressing enter. No sense of victory. I know exactly what he means. I just did the same. I am not proud of the prototype. Gamedevs were known to spend time making game engines before they started making the games. Its different now. No joy. https://ift.tt/OFdaqGA September 26, 2026 at 10:06PM

Show HN: Digitron – a virtual analog synth and sequencer https://ift.tt/m3OlL9S

Show HN: Digitron – a virtual analog synth and sequencer I’ve just released Digitron on iOS. It’s a virtual analog synthesizer with a sequencer. If I had to describe the rough idea, I’d say it’s something like a child of a Moog and a Pocket Operator. I started working on it about four years ago, mostly out of boredom. I was tired of building similar client-server apps that, in the end, were mostly different ways of displaying lists. I wanted to build something self-contained. The first version of Digitron was pretty simple: a 16-step sequencer and a monophonic synth with two oscillators and cross-modulation. I wrote the first audio engine in Kotlin. As long as it was rendering WAV files offline, everything sounded fine. But the first time I tried running it in real time on Android, the popcorn noises made it pretty obvious that this wasn’t going to work. So I rewrote the entire engine in C++, and along the way got much more familiar with real-time audio, DSP, optimization, and aliasing than I had originally planned. Over the next few years Digitron grew quite a bit: I added a patchbay, a more capable sequencer with patterns and parameter locks, 8 independent engines, a mixer, effects, polyphony, and a recorder, and I’ve surely forgotten something. The result is a fairly monstrous thing with a steep learning curve. But if you’re familiar with modular synths, it should be possible to find your way around it. The current Digitron stack is Kotlin Multiplatform for the application layer, backed by a cross-platform C++ audio engine. On Android it talks to the native layer through JNI, while on iOS I use Swift wrappers around the same C++ backend. The work on Digitron’s audio engine also eventually led to a new open-source project called PatchCore — a redesigned, more general-purpose modular audio engine: https://ift.tt/nJB2pvV After about four years of working on it, it feels pretty strange to finally see Digitron in the App Store. I'd love to hear what you think about the synth. https://ift.tt/kmFXaW6 September 25, 2026 at 11:01PM

Show HN: Jev Plays Pokémon Red https://ift.tt/IbFKA1S

Show HN: Jev Plays Pokémon Red Hey HN! Wanted to share a fun project I've been hacking on. Given Jev can make decisions really fast (but not fast enough to play Doom yet sadly), I wanted to try and push it to play a more complex game than Tetris. So I went with Pokémon. I've spent endless hours playing this game as a child so building this was a ton of fun. I open sourced everything in case you want to hack on it yourself here: https://ift.tt/iub3nRg The game is being streamed live including the tokens and cost - hopefully we get all the badges and don't get stuck in a cave :) https://jev-pokemon.vercel.app/ September 25, 2026 at 06:28PM

Show HN: A $25 DIY alternative to $159 AI voice recorders – BYOK or local https://ift.tt/kuI5R2s

Show HN: A $25 DIY alternative to $159 AI voice recorders – BYOK or local https://zephclick.com September 25, 2026 at 12:51AM

Show HN: Canary (YC) – Independent verification for AI code https://ift.tt/uaHs6Ay

Show HN: Canary (YC) – Independent verification for AI code Hey HN, we are Aakash and Viswesh and we are building Canary ( https://ift.tt/EWiU2Pw ) - independent verification for AI code. Claude/Codex calls Canary with the changesets, intended behaviour and team knowledge. Canary then deploys agent swarms to investigate potential failures and test suspected runtime bugs in remote sandboxes. To try it on your repository, paste this into your coding agent: Install the Canary CLI with npm i -g @runcanary/cli, then run canary skills and follow its instructions to onboard this repository. Verification starts with what software is supposed to do and most importantly what it must never allow. This means investigating how inputs, permissions, state, timing, dependencies etc interact with each other. Intent is not always fully declared as well but many expectations are clear: private files should stay private, credentials should not leak, and retries should not create unintended duplicate effects. We believe the future is a unified and independent verification system that starts with all those expectations and then chooses how to investigate each suspected failure. Source-only code reviews catches static issues in the implementation but even a clean review leaves a good chunk of behavioral only issues untested. Unit tests, integrations, E2E, static analysis, runtime experiments and formal verification are all means to establish that behavior thereby generating different kinds of evidence and guarantees. This is why we believe a dedicated verification harness that can think and reason through all these modalities and invariants is necessary on top of general intelligence. The harness needs to start with the system’s intended behavior, develop a series of potential failure scenarios and choose how to investigate them. It’s sole functionality is to pressure test and challenge the assumptions behind a change, create the conditions needed to test suspected failures and assess what the resulting evidence establishes How Canary works: it takes a cold snapshot of the codebase when called, combining the supplied intent and team knowledge with requirements, decisions, prior issues from tools like Notion, Linear. It can also route questions to you through the coding agents if anything is ambiguous. Canary’s harness coordinates agent swarms by leveraging the different strengths across model families. It compares the code before and after, traces the effects through callers, dependencies, state transitions etc. and each suspected failure becomes a concrete scenario with an actor, state, trigger, outcomes and many more runtime states., For each suspected failure, Canary chooses the best way to provide evidence through methods like runtime verification, static analysis, unit, integration or sometimes even combination of these as necessary. The agent executes these checks in remote sandboxes by seeding data, configuring permissions, mocking dependencies and third party integrations and much more. Canary then returns these findings and supporting evidence back to the coding agents which then fixes these failures and requests reverifications against the failed scenarios. To get started, give your coding agent this setup instruction and tell us what it caught and how we can do better. Install the Canary CLI with npm i -g @runcanary/cli, then run canary skills and follow its instructions to onboard this repository. We are still pretty early in our journey and would love feedback on the product and how we can do better. https://ift.tt/EWiU2Pw September 25, 2026 at 12:57AM