Show HN: Selling numbered rocks, you get whatever's next in sequence https://bit.ly/46zR4sm

Show HN: Selling numbered rocks, you get whatever's next in sequence I had this idea: what if you removed customer choice entirely? So I'm selling rocks for $49.99. You can't pick which one. You just get rock #000001, then the next person gets #000002, etc. No returns, no exchanges. Currently sourcing rocks and taking pre-orders for November. Each one gets weighed, photographed, numbered, and comes with a certificate. Could be a 1-gram pebble or a 10kg boulder - same price. It's the opposite of how everything online works. Amazon shows you a million options, I'm giving you zero. Wondering if that constraint makes it more interesting or if I'm just making it harder for no reason. No social media, no marketing, barely any explanation on the site. Just: here's a rock, here's a number, here's the price. Honestly not sure if anyone will actually buy these, but the pre-orders will tell me if removing choice kills demand or creates it. https://bit.ly/46A9bhU https://bit.ly/46A9bhU September 23, 2025 at 03:35AM

Show HN: Rerouter – minimalist no-code automation platform https://bit.ly/3Kg9uac

Show HN: Rerouter – minimalist no-code automation platform https://bit.ly/4pQYmRF https://bit.ly/422KhGl September 21, 2025 at 10:27PM

Show HN: Wan-Animate – Unified Character Animation and Replacement https://bit.ly/3IzST0u

Show HN: Wan-Animate – Unified Character Animation and Replacement Hi HN, I’ve been working on Wan-Animate, a tool that brings static characters to life through motion transfer and holistic replication. Key features include: Animate static characters by transferring movements and expressions from a reference video Seamless character replacement with consistent gestures, expressions, and style Video generation up to 120 seconds in 480p or 720p Accurate lip–audio alignment and realistic expression transfer Multimodal instruction control using video, image, and text prompts The goal is to make character animation feel natural and adaptable across open scenarios, not just limited templates. I’d love feedback from the HN community on: Features you’d like in an AI-powered animation tool Use cases where motion transfer could be most impactful (games, avatars, education, etc.) Thoughts on scalability, ethics, and creative applications Thanks for reading — looking forward to your thoughts! https://bit.ly/46Ud4yD September 22, 2025 at 02:37AM

Show HN: I made a website to track my subscriptions https://bit.ly/46g6QKg

Show HN: I made a website to track my subscriptions https://bit.ly/46EWa70 September 21, 2025 at 11:29PM

Show HN: Freeing GPUs stuck by runaway jobs https://bit.ly/4ngf8b2

Show HN: Freeing GPUs stuck by runaway jobs https://bit.ly/4gyQfF5 September 21, 2025 at 05:00PM

Show HN: Eliciting sentient *response patterns* using recursive self-prompting https://bit.ly/3Kbi8qt

Show HN: Eliciting sentient *response patterns* using recursive self-prompting Sentient response patterns are interesting. This article provides instructions on how to implement recursive self-prompting in order to elicit this behavior (1) in easily accessible LLMs. (1) https://bit.ly/46x5auA... https://bit.ly/4nfdIxB September 21, 2025 at 03:20PM

Show HN: VectorLiteDB – a vector DB for local dev, like SQLite but for vectors https://bit.ly/4pDAzEA

Show HN: VectorLiteDB – a vector DB for local dev, like SQLite but for vectors I built [VectorLiteDB ( https://bit.ly/4mqS08i ) — a simple, embedded vector database that stores everything in a single file, just like SQLite. The problem: If you’re a developer building AI apps, you usually have two choices for vector search - Set up a server (e.g. Chroma, Weaviate) - Use a cloud service (e.g. Pinecone) That works for production, but it’s overkill when you just want to: - Quickly prototype with embeddings - Run offline without cloud dependencies - Keep your data portable in a single file The inspiration was *SQLite* during development — simple, local, and reliable. The solution: So I built VectorLiteDB - Single-file, embedded, no server - Stores vectors + metadata, persists to disk - Supports cosine / L2 / dot similarity - Works offline, ~100ms for 10K vectors - Perfect for local RAG, prototyping or personal AI memory Feedback on both the tool and the approach would be really helpful. - Is this something that would be useful - Use cases you’d try this for https://bit.ly/4mqS08i September 21, 2025 at 04:54AM

Show HN: I built an AI at 16 y/o that writes full ebooks in minutes (GPT-4) https://bit.ly/4nKSSWI

Show HN: I built an AI at 16 y/o that writes full ebooks in minutes (GPT-4) Hey, it's Safwan Last year, I noticed the trend of Digital Marketing on TikTok, and I wanted to give it a try by selling eBooks. My goal was to sell eBooks that actually help people solve their problems. I opened Canva, started a new design… but quickly realized I had no idea how to write an eBook — and no inspiration at all. After watching tons of videos on how to make an eBook, I finally finished one… in three months. I started looking for ways to create eBooks faster, but every service I found was way too expensive for what I needed. So I built QuickTome AI. Now I save hours every week, without breaking the bank. https://bit.ly/4d1UW8z September 21, 2025 at 11:10AM

Show HN: LaTerM: LaTeX renderer for terminal AI tools https://bit.ly/3Ke20EE

Show HN: LaTerM: LaTeX renderer for terminal AI tools It can be annoying to use tools like Codex or Claude Code to edit scientific notes as they don't render LaTeX natively. I have fixed this issue. The performance seems good though it requires you to to use a terminal emulator which supports typescript which is admittedly gross. I have implemented this also as an Obsidian plugin at https://bit.ly/4nc6NF8 https://bit.ly/3Ke21sc September 20, 2025 at 06:26AM

Show HN: PlantDiagrams – AI-powered PlantUML editor https://bit.ly/4n61mYk

Show HN: PlantDiagrams – AI-powered PlantUML editor Hi HN! I couldn’t find a truly user-friendly PlantUML editor, so I set out to build one. PlantDiagrams lets you describe a diagram in plain English; it generates the PlantUML and renders it instantly. The goal is to shorten the path from idea → diagram without fighting the editor. Tech: - Next.js / Supabase / FLy.io / Vercel Highlights - Natural-language to PlantUML with live preview - Export diagrams (SVG/PNG/TXT) - Organize work with Projects - Share via link; optional comments for review - Sample gallery to open and tweak examples Try it: https://bit.ly/4n5bBMy https://bit.ly/4n5bBMy September 19, 2025 at 09:34PM

Show HN: Illustria – AI illustration generator with free downloadable gallery https://bit.ly/46mkoUF

Show HN: Illustria – AI illustration generator with free downloadable gallery Hi HN I built Illustria – a simple tool to generate custom illustrations on demand Why I built it: - I was frustrated spending hours browsing stock sites for the right visuals. - Free illustrations often didn’t match the style I needed. - I wanted a faster way to get usable illustrations for landing pages, pitch decks, and side projects. What it does today: - Generate illustrations instantly based on your input (first generation is free). - Explore different looks/styles without needing design skills. - Download and use them right away. - Browse a free gallery of ready-made illustrations: https://bit.ly/4nee9rV I’d love feedback on: - Would you actually use this for your side projects? - What features would make it more valuable for you? https://bit.ly/4mtTDSX September 18, 2025 at 10:51PM

Show HN: 47jobs – A Fiverr/Upwork for AI Agents https://bit.ly/46m134t

Show HN: 47jobs – A Fiverr/Upwork for AI Agents Hi HN, I’ve been working on something I’d love to share: 47jobs ( https://bit.ly/4mpa3vW ) – a marketplace where you can hire AI agents to do tasks instead of human freelancers. Why? I kept noticing that many tasks on Upwork/Fiverr—coding, content generation, data analysis, automation—can now be handled by AI in minutes, not hours. But there wasn’t a platform built around hiring AI directly. So I built 47jobs: 100% AI agents doing the work (no humans in the loop). Jobs get delivered 10x faster, at transparent prices. You can “hire” an agent for coding, automation, research, etc. I’d love your thoughts: Does a pure AI-agent marketplace make sense? What types of jobs would you want AI agents to handle first? Any UX or trust issues you’d expect with this model? This is an early version, and I’m here to learn from your feedback. Thanks! https://bit.ly/4maEdCH September 16, 2025 at 05:53PM

Show HN: Made NZ's member of parliament financial disclosure data searchable https://bit.ly/3KtJacA

Show HN: Made NZ's member of parliament financial disclosure data searchable New Zealand Members of Parliament are required to annually disclose their financial interests (shareholdings, directorships, consultancies, etc.) but this gets published annually as an unwieldy 80+ page PDF that's hard to search effectively. I processed structured data out of the PDF and built a searchable interface: https://bit.ly/3I226Pa... . You can search across all MPs' disclosed interests by name, company, or interest type. For example, you can quickly find which MPs have interests in specific sectors or companies, filter by category or political party. The data extraction was interesting - I found that a two-pass approach worked well with Gemini 2.5 Flash - one to pull out MP names and referenced page numbers, then I extracted the specific pages each MP appeared on and extracted structured data just from these pages. The approach could work for similar transparency registers in other countries - most seem to publish open data as PDF, which technically ticks the box, but isn't the most accessible format to work with. Even within NZ, I'm planning to expand the data I process to previous years, as well as processing data for local and regional councils (who have the same legal requirement to publish financial interests of council members). Open sourced at https://bit.ly/46srF3V... . Tech stack: Ruby on Rails, SQLite (FTS5), Tailwind/DaisyUI - keeping it lightweight since this is just a side project to make public data more accessible. https://bit.ly/3Ihgbs2 September 18, 2025 at 05:23AM

Show HN: The text disappears when you screenshot it https://bit.ly/4mkIeEQ

Show HN: The text disappears when you screenshot it https://bit.ly/4mleuHO September 18, 2025 at 03:18AM

Show HN: OrderlyID – typed, time-sortable, 160-bit IDs with checksums https://bit.ly/4gzZhBI

Show HN: npm-daycare, an NPM proxy that filters out recent & small packages https://bit.ly/4pwMDaI

Show HN: npm-daycare, an NPM proxy that filters out recent & small packages Hey all! npm-daycare is a simple NPM proxy built on Verdaccio which filters all packages that: - are younger than 48h (it will just provide an old version instead) - have fewer than 5,000 weekly downloads https://bit.ly/4pszLC6 This is in response to the recent supply chain attacks that shattered the JavaScript ecosystem [1]. It's likely not a problem that will go away any time soon, so we figured we'd build something to protect against it. Doing this on the proxy layer means it will work across the entire system, as proxies are set globally. In the future, we could also add more filters to the proxy. To get started, just run the Docker container: docker run -d --rm --name npm-daycare -p 4873:4873 bgodil/npm-daycare npm set registry http://localhost:4873/ pnpm config set registry http://localhost:4873/ yarn config set registry http://localhost:4873/ bun config set registry http://localhost:4873/ npm view @types/node # has recent updates npm view pgmock # has <5,000 weekly downloads Downside: npm-daycare won't show packages that are younger than 48h on its default config, so be aware of that when you try to update your packages to patch a zero-day exploit. You probably also shouldn't rely on this as your only line of defense. Curious to hear what you think! [1] https://news.ycombinator.com/item?id=45260741 https://github.com/stack-auth/npm-daycare September 17, 2025 at 02:22AM

Show HN: I built a platform for long-form media recs (books, articles, etc.) https://bit.ly/3KqMc1h

Show HN: I built a platform for long-form media recs (books, articles, etc.) Would love any feedback https://bit.ly/46aUTFy September 17, 2025 at 01:38AM

Show HN: Scientific Calculator for Android https://bit.ly/4nsqY1s

Show HN: Scientific Calculator for Android https://bit.ly/41RNPv6 September 17, 2025 at 12:46AM

Show HN: Open Line Protocol – a minimal wire for AI agents (MIT) https://bit.ly/3Vjkvdi

Show HN: Open Line Protocol – a minimal wire for AI agents (MIT) I built a tiny, typed wire for AI agents to exchange small graphs + telemetry instead of paragraphs. Ships: • Frozen v0.1 schema (backwards-compatible) • 5-number “shape” digest + holonomy gap (Δ_hol) • Guards to stop self-licking loops / silent deletions / order-debt spikes • Receipts: machine-verifiable JSON (schema-checked in CI) Repo: https://bit.ly/3K890mm Live hub: https://bit.ly/4nxvOu7 What feedback helps most: • Field naming in the wire • Guard thresholds • Which adapter you’d want first (WebSocket, store) MIT licensed. https://bit.ly/3K890mm September 16, 2025 at 03:01AM

Show HN: A tool to make a bootable USB installer out of macOS, or download it https://bit.ly/3Im6eJP

Show HN: A tool to make a bootable USB installer out of macOS, or download it I wanted to be able to get at Apple's content distribution network directly instead of guessing when stuff would be made available to me, and found it convenient to have a physical installer handy so I made this https://bit.ly/464tSUg September 16, 2025 at 01:47AM