Show HN: Ellipticc Drive – open-source cloud drive with E2E and PQ encryption Hey HN, I’m Ilias, 19, from Paris. I built Ellipticc Drive, an open-source cloud drive with true end-to-end encryption and post-quantum security, designed to be Dropbox-like in UX but with zero access to your data, even by the host. What’s unique: Free 10GB for every user, forever. Open-source frontend (audit or self-host if you want) Tech stack: Frontend: Next.js Crypto: WebCrypto (hashing) + Noble (core primitives) Encryption: XChaCha20-Poly1305 (file chunks) Key wrapping: Kyber (ML-KEM768) Signing: Ed25519 + Dilithium2 (ML-DSA65) Key derivation: Argon2id → Master Key → encrypts all keypairs & CEKs Try it live: https://ellipticc.com Frontend source: https://ift.tt/8KkVFRw Would love feedback from devs and security folks — particularly on encryption flow, architecture, or UX. I’ll be around to answer every technical question in the comments! https://ellipticc.com October 31, 2025 at 01:00AM
Show HN: Meals You Love – AI-powered meal planning and grocery shopping Meals You Love is a meal planning app that creates weekly meal plans tailored to your tastes and dietary preferences. It integrates with Kroger and Instacart's APIs so you can add your meal plan groceries directly to your cart. You can also import your own recipes to include alongside AI suggestions. I originally built this to help my wife with meal planning and grocery shopping. We were always struggling to decide what to make and inevitably forgot ingredients. Most meal planners felt too rigid or generic, and few handled the grocery side well (or at all). We've also used meal kits like Home Chef in the past but they end up being quite expensive and produce a comical amount of packaging waste, plus you still wind up needing to purchase groceries anyway. In all honesty, I also wanted an excuse to try building something "real" using AI and to see if it could be used in an actually useful manner. Would love feedback from anyone interested in food, meal planning, or product design! Tech stack: - Cloud Run - Firestore - Vertex AI / Gemini https://ift.tt/LM8P60G https://ift.tt/LM8P60G October 27, 2025 at 11:27PM
Show HN: I made CSV files double-click to open in Google Sheets instead of Excel I built my first macOS app to automatically open csv, xls files in Google Sheets. I work as marketing, revops person and often have to combine data from different platforms for reporting purposes. Google made the import flow super broken with too many clicks in between. So I built a simple solution that saves me some time. Sharing it here, you can test it out for free. No subscription bullshit, one time payment to get unlimited usage if you like it. Happy double clicking! https://csvtosheets.com October 30, 2025 at 11:25PM
Show HN: Pipelex – declarative language for repeatable AI workflows (MIT) We’re Robin, Louis, and Thomas. Pipelex is a DSL and a Python runtime for repeatable AI workflows. Think Dockerfile/SQL for multi-step LLM pipelines: you declare steps and interfaces; any model/provider can fill them. Why this instead of yet another workflow builder? - Declarative, not glue code: you state what to do; the runtime figures out how. - Agent-first: each step carries natural-language context (purpose, inputs/outputs with meaning) so LLMs can follow, audit, and optimize. Our MCP server enables agents to run pipelines but also to build new pipelines on demand. - Open standard under MIT: language spec, runtime, API server, editor extensions, MCP server, n8n node. - Composable: pipes can call other pipes, created by you or shared in the community. Why a domain-specific language? - We need context, meaning and nuances preserved in a structured syntax that both humans and LLMs can understand - We need determinism, control, and reproducibility that pure prompts can't deliver - Bonus: editors, diffs, semantic coloring, easy sharing, search & replace, version control, linters… How we got there: Initially, we just wanted to solve every use-case with LLMs but kept rebuilding the same agentic patterns across different projects. So we challenged ourselves to keep the code generic and separate from use-case specifics, which meant modeling workflows from the relevant knowledge and know-how. Unlike existing code/no-code frameworks for AI workflows, our abstraction layer doesn't wrap APIs, it transcribes business logic into a structured, unambiguous script executable by software and AI. Hence the "declarative" aspect: the script says what should be done, not how to do it. It's like a Dockerfile or SQL for AI workflows. Additionally, we wanted the language to be LLM-friendly. Classic programming languages hide logic and context in variable names, functions, and comments: all invisible to the interpreter. In Pipelex, these elements are explicitly stated in natural language, giving AI full visibility: it's all logic and context, with minimal syntax. Then, we didn't want to write Pipelex scripts ourselves so we dogfooded: we built a Pipelex workflow that writes Pipelex workflows. It's in the MCP and CLI: "pipelex build pipe '…'" runs a multi-step, structured generation flow that produces a validated workflow ready to execute with "pipelex run". Then you can iterate on it yourself or with any coding agent. What’s included: Python library, FastAPI and Docker, MCP server, n8n node, VS Code extension. What we’d like from you 1. Build a workflow: did the language work for you or against you? 2. Agent/MCP workflows and n8n node usability. 3. Suggest new kinds of pipes and other AI models we could integrate 4. Looking for OSS contributors to the core library but also to share pipes with the community Known limitations - Connectors: Pipelex doesn’t integrate with “your apps”, we focus on the cognitive steps, and you can integrate through code/API or using MCP or n8n - Visualization: we need to generate flow-charts - The pipe builder is still buggy - Run it yourself: we don’t yet provide a hosted Pipelex API, it’s in the works - Cost-tracking: we only track LLM costs, not image generation or OCR costs yet - Caching and reasoning options: not supported yet Links - GitHub: https://ift.tt/Cc2jhP1 - Cookbook: https://ift.tt/42wndlj - Starter: https://ift.tt/eE8tquv - VS Code extension: https://ift.tt/rDicmEz - Docs: [ https://ift.tt/Kq49cIY ]( https://ift.tt/DeaUHxj ) - Demo video (2 min): https://youtu.be/dBigQa8M8pQ - Discord for support and sharing: https://ift.tt/4RNkYj9 Thanks for reading. If you try Pipelex, tell us exactly where it hurts, that’s the most valuable feedback we can get. https://ift.tt/Cc2jhP1 October 28, 2025 at 09:49PM
Show HN: JSON Query I'm working on a tool that will probably involve querying JSON documents and I'm asking myself how to expose that functionality to my users. I like the power of `jq` and the fact that LLMs are proficient at it, but I find it right out impossible to come up with the right `jq` incantations myself. Has anyone here been in a similar situation? Which tool / language did you end up exposing to your users? https://ift.tt/DybN7kK October 27, 2025 at 09:52PM
Show HN: Dlog – Journaling and AI coach that learns what drives well-being (Mac) Hi HN! I’m Johan. I built Dlog, a journaling app with an AI coach that tracks how your personality, daily experiences, and well-being connect over time. It’s based on my PhD research in entrepreneurial well-being. How Dlog works • Journal and set goals/projects; Dlog scores entries on-device (sentiment + narrative signals) and updates your personal model. • A built-in structural equation model (SEM) estimates which factors actually move your well-being week to week. • The Coach turns those findings into specific guidance (e.g., “protect 90 minutes after client calls; that’s when energy dips for you”). • No account; your journals live locally (in your calendar). You decide what, if anything, leaves the device. The problem • Generic AI coaches give advice without understanding your personality or context. • Traditional journaling is reflective but doesn’t surface causal patterns. • Well-being apps rarely account for individual differences or test what works for you over time. What my research found (plain English) In my PhD I modeled how Personality, Character, Resources, and Well-Being interact over time. The key is latent relationships: for example, Autonomy can buffer the impact of low Extraversion on social drain, while time/energy constraints mediate whether “good advice” is actionable. These effects are person-specific and evolve—so you need a model that learns you, not averages. The solution Dlog pairs on-device journaling analytics with an SEM that updates weekly. You get a running estimate of “what moves the needle for me,” and the Coach translates that into concrete suggestions aligned with your goals and constraints. Early stories (anonymized from pilot users) • A founder saw energy dips clustered after external calls; moving deep work to mornings reduced “bad days” and improved weekly mood stability. • A solo designer’s autonomy scores predicted well-being more than raw hours worked; small boundary changes (client comms windows) helped more than time-tracking tweaks. Tech & security • Platform: macOS (Swift/SwiftUI). Data: local storage + EventKit calendar for entries/timestamps. • Analytics: on-device sentiment + narrative features; SEM computed locally; weekly updates compare to your baseline. • AI Coach: uses an enterprise LLM API for reasoning on derived features/summaries. By default, raw journal text does not leave the device; you can opt-in per prompt if you want the Coach to read a specific passage. • Why 61 baseline variables? The SEM needs multiple indicators per construct (Personality, Character, Resources, Well-Being) to estimate stable latent factors without overfitting; weekly check-ins refresh those signals. What I’ve learned building this • Users value clarity with depth: concise recommendations paired with focused dashboards, often 5–10 charts, to explain the “why” and trade-offs. • Cold start matters: a solid baseline makes the first week of insights credibly useful. • Privacy UX needs to be explicit: users want granular control over what the Coach can read, per request. I’m looking for feedback on: • Onboarding (baseline survey and first-week experience) • Coach guidance clarity and usefulness • Analytics accuracy vs. your lived experience • Edge cases, bugs, and performance Download: https://dlog.pro If you hit token limits while testing, email me at johan@dlog.pro Background PhD (Hunter Center for Entrepreneurship, Strathclyde), MBA (Babson), BComm (UCD). I study solo self-employment and well-being, and built Dlog to bring that research into a tool practitioners can use. Note: The Coach activates after your first scored entry. If you haven’t written one yet, you’ll see a hold state—add a quick journal entry and it unlocks. Appearance: On a few Macs the initial theme can render darker than intended. If you see this, switch to Light Mode as a temporary workaround; a fix is incoming. https://dlog.pro/ October 27, 2025 at 10:44PM
Show HN: Helium Browser for Android with extensions support, based on Vanadium Been working on an experimental Chromium-based browser that brings 2 major features to your phone/tablet: 1. desktop-style extensions: natively install any extensions (like uBO) from the chrome web store, just toggle "desktop site" in the menu first. 2. privacy/security hardening: applies the full patch sets from Vanadium (with Helium's currently wip). Means you get both browsers' excellent privacy features, like Vanadium's webrtc IP policy option that protects your real IP by default, and security improvements such as JIT being disabled by default, all while being a reasonably efficient FOSS app that can be installed on any (modern) android. It's still in beta, and as I note in the README, it's not a replacement for the full OS-level security model you'd get from running the GrapheneOS Vanadium combo. However, goal was to combine privacy of Vanadium with the power of desktop extensions and Helium features, and make it accessible to a wider audience. (Passkeys from Bitwarden Mobile should also work straight away once merged in the list of FIDO2 privileged browsers) Build scripts are in the repo if you want to compile it yourself. You can find pre-built releases there too. Would love any feedback/support! https://ift.tt/t1ZBcKA October 27, 2025 at 04:11AM
Show HN: MyraOS – My 32-bit operating system in C and ASM (Hack Club project) Hi HN, I’m Dvir, a young developer. Last year, I got rejected after a job interview because I lacked some CPU knowledge. After that, I decided to deepen my understanding in the low level world and learn how things work under the hood. I decided to try and create an OS in C and ASM as a way to broaden my knowledge in this area. This took me on the most interesting ride, where I’ve learned about OS theory and low level programming on a whole new level. I’ve spent hours upon hours, blood and tears, reading different OS theory blogs, learning low level concepts, debugging, testing and working on this project. I started by reading University books and online blogs, while also watching videos. Some sources that helped me out were OSDev Wiki ( https://ift.tt/SNEnhcG ), OSTEP ( https://pages.cs.wisc.edu/~remzi/OSTEP ), open-source repositories like MellOS and LemonOS (more advanced), DoomGeneric, and some friends that have built an OS before. This part was the longest, but also the easiest. I felt like I understood the theory, but still could not connect it into actual code. Sitting down and starting to code was difficult, but I knew that was the next step I needed to take! I began by working on the bootloader, which is optional since you can use a pre-made one (I switched to GRUB later), but implementing it was mainly for learning purposes and to warm up on ASM. These were my steps after that: 1) I started implementing the VGA driver, which gave me the ability to display text. 2) Interrupts - IDT, ISR, IRQ, which signal to the CPU that a certain event occurred and needs handling (such as faults, hardware connected device actions, etc). 3) Keyboard driver, which enables me to display the same text I type on my keyboard. 4) PMM (Physical memory management) 5) Paging and virtual memory management 6) RTC driver - clock addition (which was, in my opinion, optional) 7) PIT driver - Ticks every certain amount of time, and also 8) FS (File System) and physical HDD drivers - for the HDD I chose PATA (HDD communication protocol) for simplicity (SATA is a newer but harder option as well). For the FS I chose EXT2 (The Second Extended FileSystem), which is a foundational linux FS structure introduced in 1993. This FS structure is not the simplest, but is very popular in hobby-OS, it is very supported, easy to set up and upgrade to newer EXT versions, it has a lot of materials online, compared to other options. This was probably the longest and largest feature I had worked on. 9) Syscall support. 10) Libc implementation. 11) Processing and scheduling for multiprocessing. 12) Here I also made a shell to test it all. At this point, I had a working shell, but later decided to go further and add a GUI! I was working on the FS (stage 8), when I heard about Hack Club’s Summer of Making (SoM). This was my first time practicing in HackClub, and I want to express my gratitude and share my enjoyment of participating in it. At first I just wanted to declare the OS as finished after completing the FS, and a bit of other drivers, but because of SoM my perspective was changed completely. Because of the competition, I started to think that I needed to ship a complete OS, with processing, GUI and the bare minimum ability to run Doom. I wanted to show the community in SoM how everything works. Then I worked on it for another 2 months, after finishing the shell, just because of SoM!, totalling my project to almost 7 months of work. At this time I added full GUI support, with dirty rectangles and double buffering, I made a GUI mouse driver, and even made a full Doom port! things I would've never even thought about without participating in SoM. This is my SoM project: https://ift.tt/Re5nrSx . Every project has challenges, especially in such a low level project. I had to do a lot of debugging while working on this, and it is no easy task. I highly recommend using GDB which helped me debug so many of my problems, especially memory ones. The first major challenge I encountered was during the coding of processes - I realized that a lot of my paging code was completely wrong, poorly tested, and had to be reworked. During this time I was already in the competition and it was difficult keeping up with devlogs and new features while fixing old problems in a code I wrote a few months ago. Some more major problems occurred when trying to run Doom, and unlike the last problem, this was a disaster. I had random PFs and memory problems, one run could work while the next one wouldn’t, and the worst part is that it was only on the Doom, and not on processes I created myself. These issues took a lot of time to figure out. I began to question the Doom code itself, and even thought about giving up on the whole project. After a lot of time spent debugging, I fixed the issues. It was a combination of scheduling issues, Libc issues and the Qemu not having enough (wrongfully assuming 128MB for the whole OS was enough). Finally, I worked throughout all the difficulties, and shipped the project! In the end, the experience working on this project was amazing. I learned a lot, grew and improved as a developer, and I thank SoM for helping to increase my motivation and make the project memorable and unique like I never imagined it would be. The repo is at https://ift.tt/RmidclP . I’d love to discuss any aspect of this with you all in the comments! https://ift.tt/RmidclP October 27, 2025 at 02:13AM
Show HN: I Built DevTools for Blazor (Like React DevTools but for .NET) Hi HN! I've been working on developer tools for Blazor that let you inspect Razor components in the browser, similar to React DevTools or Vue DevTools. The problem: Blazor is Microsoft's frontend framework that lets you write web UIs in C#. It's growing fast but lacks the debugging tools other frameworks have. When your component tree gets complex, you're stuck with Console.WriteLine debugging. What I built: A browser extension + NuGet package that: Shows the Razor component tree in your browser Maps DOM elements back to their source components Highlights components on hover Works with both Blazor Server and WASM How it works: The NuGet package creates shadow copies of your .razor files and injects invisible markers during compilation. These markers survive the Razor→HTML pipeline. The browser extension reads these markers to reconstruct the component tree. Current status: Beta - it works but has rough edges. Found some bugs when testing on larger production apps that I'm working through. All documented on GitHub. Technical challenges solved: Getting markers through the Razor compiler without breaking anything Working around CSS isolation that strips unknown attributes Making it work with both hosting models It's completely open source: https://ift.tt/DXT3dOf Demo site where you can try it: https://ift.tt/gRU0QwH Would love feedback, especially from anyone building production Blazor apps. What debugging pain points do you have that developer tools could solve? https://ift.tt/tjqUXxh October 26, 2025 at 10:04PM
Show HN: Gisia – A Lightweight Self-Hosted DevOps Platform Hi HN, I've been building Gisia – a lightweight, self-hosted DevOps platform for individuals and small teams. It's simpler, more lightweight and you can self-host. Key Features: - Git repository hosting with SSH and HTTP access - CI/CD pipelines with YAML configuration - Issue tracking - Built with modern Rails stack (Rails 8, PostgreSQL, Stimulus/Turbo, Tailwind CSS) Why Gisia? - Lightweight with minimal dependencies - Developer-first design - Fully open-source and auditable - You own your data Current Status: Currently in Alpha with core features complete. Merge requests and notifications are planned. Try It Out: You can take Gisia for a test drive by following the quick start guide in the README. Feedback and contributions welcome! https://ift.tt/V3Ul4vk October 25, 2025 at 08:30PM
Show HN: Wsgrok – one of many ngrok alternatives I built it for myself because ngrok didn't let me add one more domain unless I paid $12 more. I probably should've looked for alternatives before building my own, but my grudge got in the way . Once I started, I wanted to make it better than the other options. Silly, I know. No one probably cares. I plan to open source it sometime next year because I’ve got other projects to finish first. It's free until I deplete my cloud credits, then it will switch to a tier-based model with a free option. https://wsgrok.com October 25, 2025 at 05:16AM
Show HN: Pensive – A bookmarking tool with full-text search and LLMs After Pocket shut down, I started working on a new bookmarking solution. My main goal was to make bookmarks searchable, something that Pocket was not good at. So I built Pensive, a bookmarking solution that saves the full page content and makes it searchable with full-text search. You can add pages using a browser extension or a Telegram bot (for saving on mobile). It is written in Go with PostgreSQL, all Dockerized on a $5 Hetzner server, and the front end is built with HTMX. I have also added embeddings (using Gemini Flash Lite) to let LLMs interact with your bookmarks contextually. It is stable enough that I now use it daily. I’m considering publishing it as open source, but first I want to have a proper version ready. Feel free to email me if you’re interested in helping out or if you have prior experience with open source. Feel free to try it at https://getpensive.com https://getpensive.com/ October 25, 2025 at 03:28AM
Show HN: The Σ-Manifold Manifesto This project explores the connection between *the linear structure of text* and its *emotional-aesthetic impact*. We identify *five fundamental relations* between consecutive sentences — labeled *A–E*. Each represents a shift of *subject-object*, i.e., a transformation of perspective and agency. When texts grow longer, these relations form *sequences* — and from the infinite combinatorial space, *eight stable patterns (Σ₁–Σ₈)* emerge empirically. Each pattern correlates with a distinct *semantic and emotional field* — cathartic, heroic, meditative, humorous, and so on. This allows us to instruct an LLM not through semantic prompts (“write a story about…”), but through *structural commands* — e.g., generate a narrative following sequence Σ₅ (Tragic Counterpoint). You can experiment with these archetypes directly here: [Narrative Generator]( https://ift.tt/aD2r4K7... ) or [via python]( https://ift.tt/5K7BFRa... ) Interestingly, there appears to be a parallel between these textual progressions and *musical harmony*. For example, if A–E are mapped to harmonic functions (I, IV, V, vi, ii), the narrative sequences behave like emotional “chord progressions” — where meaning flows, modulates, and resolves. Coherence in the generated text arises not only from syntax, but from the *associative field* that the LLM constructs around these shifting relations. When asked to “switch subjects,” it spontaneously moves from Poet to Writer , preserving aesthetic continuity rather than randomness. It might even hint at how *children acquire language*: by first sensing the melody of structural transitions, before mapping them to concepts and emotions. Such a method could eventually apply to *training neural systems*, where meaning is learned as flow — not as fixed representation. [Full text]( https://ift.tt/bmaKvE0... ) October 25, 2025 at 01:34AM
Show HN: Check what is hogging your disk zpace Hello world! I would like to share that I have created a simple open-source Python CLI app to check what's hogging all the disk space! You can install it with pip. It's like space but Zpace. pip install zpace and find the big files consuming your disk space. Be it apps, virtual environments, machine learning models etc. Just run zpace Once you find one, that you can say "bye" to, just run rm -rf /i_dont_need/this/file/right_now to get rid of it. It was born out of frustration while lack of disk space prevented me to use my laptop properly. It has been very useful to me so far. I hope that it can be useful to you as well. Feel free to check it out. Currently tested on MacOS only https://ift.tt/tazmG0c October 25, 2025 at 01:12AM
Show HN: Git for LLMs – a context management interface Hi HN, we’re Jamie and Matti, co-founders of Twigg. During our master’s we continually found the same pain points cropping up when using LLMs. The linear nature of typical LLMs interfaces - like ChatGPT and Claude - made it really easy to get lost without any easy way to visualise or navigate your project. Worst of all, none of them are well suited for long term projects. We found ourselves spending days using the same chat, only for it to eventually break. Transferring context from one chat to another is also cumbersome. We decided to build something more intuitive to the ways humans think. We started with two simple ideas. Enabling chat branching for exploring tangents, and an interactive tree diagram to allow for easy visualisation and navigation of your project. Twigg has developed into an interface for context management - like “Git for LLMs”. We believe the input to a model - or the context - is fundamental to its performance. To extract the maximum potential of an LLM, we believe the users need complete control over exactly what context is provided to the model, which you can do using simple features like cut, copy and delete to manipulate your tree. Through Twigg, you can access a variety of LLMs from all the major providers, like ChatGPT, Gemini, Claude, and Grok. Aside from a standard tiered subscription model (free, plus, pro), we also offer a Bring Your Own Key (BYOK) service, where you can plug and play with your own API keys. Our target audience are technical users who use LLMs for large projects on a regular basis. If this sounds like you, please try out Twigg, you can sign up for free at https://twigg.ai/ . We would love to get your feedback! https://twigg.ai October 23, 2025 at 08:42PM
Show HN: Distil-NPC: a family of models for non-playable characters in games we finetuned Google's Gemma 270m (and 1b) small language models specialized in having conversations as non-playable characters (NPC) found in various video games. Our goal is to enhance the experience of interacting in NPSs in games by enabling natural language as means of communication (instead of single-choice dialog options). https://ift.tt/q3Pan5Z October 23, 2025 at 10:55PM
Show HN: Create interactive diagrams with pop-up content This is a recent addition to Vexlio which I think the HN crowd may find interesting or useful. TL;DR: easy creation of interactive diagrams, meaning diagrams that have mouse click/hover hooks that you can use to display pop-up content. The end result can be shared with a no-sign-in-required web link. My thought is that this is useful for system docs, onboarding or user guides, presentations, etc. Anything where there is a high-level view that should remain uncluttered + important metadata or details that still need to be available somewhere. You can try it out without signing up for anything, just launch the app here ( https://app.vexlio.com/ ), create a shape, select it with the main pointer tool and then click "Add popup" on the context toolbar. I'd be grateful for any and all feedback! https://ift.tt/aG8H5p2 October 22, 2025 at 08:15PM
Show HN: Katakate – Dozens of VMs per node for safe code exec I've built this to make it easy to host your own infra for lightweight VMs at large scale. Intended for exec of AI-generated code, for CICD runners, or for off-chain AI DApps. Mainly to avoid Docker-in-Docker dangers and mess. Super easy to use with CLI / Python SDK, friendly to AI engs who usually don't like to mess with VM orchestration and networking too much. Defense-in-depth philosophy. Would love to get feedback (and contributors: clear & exciting roadmap!), thx https://ift.tt/7jCu1Gd October 21, 2025 at 08:52PM
Show HN: bbcli – A TUI and CLI to browse BBC News like a hacker hey hn! I (re)built this TUI tool for browsing BBC News in the terminal, it uses an RSS feed for getting headlines and previews and you can read articles too. Try it out and let me know what you think! :) https://ift.tt/Olk0Mwx October 19, 2025 at 04:28PM
Show HN: OpenJobHub – A Free and Open Job Board Hey everyone, I recently built OpenJobHub, a free and open source job board for engineers. My goal is simple: in these tough times, I hope more people can find good jobs, and that job information can be more open and transparent. Feel free to share it with any recruiters, HRs, or friends who are hiring. Let's build a healthier job ecosystem together. GitHub: https://ift.tt/zXifk3p Website: https://jobs.wowkit.net https://ift.tt/zXifk3p October 21, 2025 at 11:03PM
Show HN: Online Sourcerer – The best answer to 'source?' Hello, I made this site to combat misinformation on the internet by allowing users to prove that their claim is valid by linking multiple sources and combining them in a single link It's very early stage so I would love feedback on: - What types of claims would be most useful to you? - How can I make verification/sourcing more robust? - Any features that would make this actually useful vs just interesting? Thanks in advance, feel free to roast :) https://ift.tt/1IXTvnL October 21, 2025 at 03:46AM
Show HN: I built a Product Hunt alternative for African tech startups With the advance of AI, everyone is building and creating solutions. It is actually amazing to see people in Africa engage this creative field and produce products that could help their ecosystem. So I built a platform that will soon be the biggest directory of tech products made by people in Africa to solve African Problems. I am taking this path because I understand we have very different problems and different cultures and things work differently especially in Africa. What do you guys think? I want your feedback on everything. https://ift.tt/QouF3CY October 21, 2025 at 02:25AM
Show HN: I created a cross-platform GUI for the JJ VCS (Git compatible) Personally, I think the JJ VCS ( https://ift.tt/Nh3gj6v ) hit a point some time in this past year where I find it hard to find a great reason to continue using git. Over the years I've cobbled together aliases and bash functions to try to improve my git workflow, but after using jj, which works with ~any git repo and integrates great with Github repos, all of the workflow issues I ran into with git are not only solved, but improved in ways I couldn't manage with simple scripts. One example is the op log, which lets you go to any point in your repo's time and provides simple undo and redo commands when you want to back out of a merge, didn't mean to rebase, etc. Because I have a pretty strong conviction that JJ is at this point a cleaner and more powerful version of git, my hopes are that it continues to grow. With that, it seemed a proper full-featured GUI was missing for the VCS. There's some plugins that add some integration into VS Code, and there's one in the works to get Intellij support working, but many of the constructs JJ provides in my opinion necessitate a grounds-up build of a GUI around how JJ works. Right now, Judo for JJ is an MVP in an open beta. I did my best to support all of the core functionality one would need, though there's many nice-to-haves that I am going to add, like native merge support, native splitting, etc. Most of this will be based on feedback from the Beta. I'm really grateful for the great community JJ has built, alongside the HN community itself in the countless VCS-based posts I've read over the years, and am hoping for lots of input here during Beta under real usage - the goal is to be a full-featured desktop GUI for the VCS, similar to many of the great products that are out there for git. https://judojj.com October 20, 2025 at 09:05PM
Show HN: NativeBlend – Text to fully editable 3D Models that don't suck I'm a developer (not a 3D artist) who's been frustrated with current AI text-to-3D tools — most produce messy, monolithic meshes that are unusable without hours of cleanup. So I built NativeBlend, a side project aimed at generating editable 3D assets that actually fit into a real workflow. Key features: - Semantic Part Segmentation: Outputs separate, meaningful components (e.g., wheels, doors), not just a single mesh blob. - Native Blender Output: Generates clean, structured .blend files with proper hierarchies, editable PBR materials, and decent UVs — no FBX/GLB cleanup required. The goal is to give devs a usable starting point for game assets without the usual AI slop. I have a working demo and would love feedback: Does this solve a real need, or am I just scratching my own itch? Thanks for taking a look! https://native-blend-app.vercel.app/ October 21, 2025 at 12:27AM
Show HN: CheckHN – A checklist for the most popular Hacker News posts I realized that I'm more interested in the all-time top content on Hacker News than in whatever is popular right now. To better keep track of which posts I've already read, I built a small web app that displays all posts sorted by popularity and allows me to check them off or save them for later. https://ift.tt/CpibuLV October 19, 2025 at 10:58PM
Show HN: WP-Easy, framework to build WordPress themes The inspiration for this framework came from my brother, an amazing graphic designer who wanted to build WordPress themes using only his FTP-based code editor. He knows HTML and CSS really well, and some jQuery, but not modern JavaScript. In my experience, this is common for people whose jobs are tangential to frontend web development... designers, copywriters, project managers, and backend engineers. So this is for people who don't want to deal with the mess of modern build tools. It tries to nudge people into a more modern direction: component-based architecture, JS modules, SCSS, and template routing. WP-Easy lets people like my brother build professional, modern themes without the usual barriers, just code with your favorite editor and see the results instantly. Key features: 1. File-based routing - Define routes in router.php with Express-like syntax (/work/:slug/) 2. Single File Components - PHP templates with
,
Show HN: Code review for AI native teams Bottleneck is a desktop app for code reviewing AI-written pull requests. The goal is to be able to track PRs on GitHub authored by agents (i.e. Codex, Devin, Cursor, Claude Code) and compare branches. So if you throw multiple coding agents at a ticket, this would be an easier way to let agents "bake off" against each other and pick the best one. (No need to open the Github website and switch between slow loading tabs). I'd love feedback from any power users who are deep with AI coding agents. https://ift.tt/DRKLdHz October 18, 2025 at 05:52AM
Show HN: I turned my resume into a catchy song. It's a game changer I turned my resume into a catchy pop song. Thought you'd all appreciate it. Worked directly on the Song Style prompt, which you can duplicate for your own fun catchy resume song. Just replace the lyrics! https://ift.tt/R5jP9xs October 18, 2025 at 02:22AM
Show HN: We packaged an MCP server inside Chromium Hey HN, we just shipped a browser with an inbuilt MCP server! We're a YC startup (S24) building BrowserOS — an open‑source Chromium fork. We're a privacy‑first alternative to the new wave of AI browsers like Dia, Perplexity Comet. Since launching ~3 months ago, the #1 request has been to expose our browser as an MCP server. -- Google beat us to launch with chrome-devtools-mcp (solid product btw), which lets you build/debug web apps by connecting Chrome to coding assistants. But we wanted to take this a step further: we packaged the MCP server directly into our browser binary. That gives three advantages: 1. MCP server setup is super simple — no npx install, no starting Chrome with CDP flags, you just download the BrowserOS binary. 2. with our browser's inbuilt MCP server, AI agents can interact using your logged‑in sessions (unlike chrome-devtools-mcp which starts a fresh headless instance each time) 3. our MCP server also exposes new APIs from Chromium's C++ core to click, type, and draw bounding boxes on a webpage. Our APIs are also not CDP-based (Chrome Debug Protocol) and have robust anti-bot detection. -- Few example use cases for BrowserOS-mcp are: a) *Frontend development with Claude Code*: instead of screenshot‑pasting, claude-code gets WYSIWYG access. It can write code, take a screenshot, check console logs, and fix issues in one agentic sweep. Since it has your sessions, it can do QA stuff like "test the auth flow with my Google Sign‑In." Here's a video of claude-code using browserOS to improve the css styling with back-and-forth checking: https://youtu.be/vcSxzIIkg_0 b) *Use as an agentic browser:* You can install BrowserOS-mcp in claude-code or Claude Desktop and do things like form-filling, extraction, multi-step agentic tasks, etc. It honestly works better than Perplexity Comet! Here's a video of claude-code opening top 5 hacker news posts and summarizing: https://youtu.be/rPFx_Btajj0 -- *How we packaged MCP server inside Chromium binary*: We package the server as a Bun binary and expose MCP tools over HTTP instead of stdio (to support multiple sessions). And we have a BrowserOS controller installed as an extension at the application layer which the MCP server connects to over WebSocket to control the browser. Here's a rough architecture diagram: https://dub.sh/browseros-mcp-diag -- *How to install and use it:* We put together a short guide here: https://ift.tt/foNBubc Our vision is to reimagine the browser as an operating system for AI agents, and packaging an MCP server directly into it is a big unlock for that! I'll be hanging around all day, would love to get your feedback and answer any questions! https://ift.tt/15Ta72t October 17, 2025 at 09:52PM
Show HN: Inkeep (YC W23) – Agent builder that works both visually and in code Hi HN! I'm Nick from Inkeep. We built an agent builder with true 2-way sync between code and a drag-and-drop visual editor, so devs and non-devs can collaborate on the same agents. Here’s a demo video: https://ift.tt/5PZvJHE . As a developer, the flow is: 1) Build AI Chat Assistants or AI Workflows with the TypeScript SDK 2) Run `inkeep push` from your CLI to publish 3)Edit agents in the visual builder (or hand off to non-technical teams) 4) Run `inkeep pull to edit in code again. We built this because we wanted the accessibility of no-code workflow builders (n8n, Zapier), but the flexibility and devex of code-based agent frameworks (LangGraph, Mastra). We also wanted first-class support for chat assistants with interactive UIs, not just workflows. OpenAI got close, but you can only do a one-time export from visual builder to code and there’s vendor lock-in. How I've used it: I bootstrapped a few agents for our marketing and sales teams, then was able to hand off so they can maintain and create their own agents. This has enabled us to adopt agents across technical and non-technical roles in our company on a single platform. To try it, here’s the quickstart: https://ift.tt/vTMaOVB . We leaned on open protocols to make it easy to use agents anywhere: An MCP endpoint, so agents can be used from Cursor/Claude/ChatGPT A Chat UI library with interactive elements you can customize in React An API endpoint compatible with the Vercel AI SDK `useChat` hook Support for Agent2Agent (A2A) so they work with other agent ecosystems We made some practical templates like a customer_support, deep_research, and docs_assistant. Deployment is easy with Vercel/Docker with a fair-code license and there's a traces UI and OTEL logs for observability. Under the hood, we went all-in on a multi-agent architecture. Agents are made up of LLMs, MCPs, and agent-to-agent relationships. We’ve found this approach to be easier to maintain and more flexible than traditional “if/else” approaches for complex workflows. The interoperability works because the SDK and visual builder share a common underlying representation, and the Inkeep CLI bridges it with a mix of LLMs and TypeScript syntactic sugar. Details in our docs: https://docs.inkeep.com . We’re open to ideas and contributions! And would love to hear about your experience building agents - what works, hasn’t worked, what’s promising? https://ift.tt/4yfcZim October 16, 2025 at 06:20PM
Show HN: Coordable – Get better geocoding results with AI cleaning and analytics I’ve been working on a tool called Coordable, which helps analyze and improve geocoding results. If you’ve ever dealt with geocoding at scale, you’ve probably hit two recurring problems: Garbage in = garbage out. Addresses are often messy (“2nd floor”, “/”, abbreviations, multiple addresses in one line…). Most geocoders will fail or return incorrect matches if the input isn’t perfectly normalized. A result isn’t always a correct result. Many providers return something even if it’s wrong — e.g. shifting a house number, or confusing similar street names. Assessing whether a geocoded result is actually right is surprisingly hard to automate. Coordable tries to address both issues with AI and analytics: Uses an LLM-based cleaner to normalize messy addresses (multi-country support). Automatically evaluates geocoding accuracy by comparing input and output like a human would. Lets you benchmark multiple providers (Google, HERE, Mapbox, Census, BAN, etc.) side by side. Includes a dashboard to visualize results, quality metrics, and exports. It’s not a new geocoder — it wraps existing APIs and focuses on data quality, comparison, and automation. It’s currently in beta with free credits. If you work with geocoding or address data, I’d love to hear how you handle these challenges and what kind of analytics would be most useful to you. https://coordable.co/ October 16, 2025 at 11:11PM
Show HN: How Useless Are You? A brutally honest skills check We built this to answer "am I a fit for this role?" after noticing how hard it is to get honest feedback when applying to a YC startup or something else entirely. It's a custom 5-minute challenge that roasts you after. Added a leaderboard for those who want to see how they stack up. Roast us below. https://ift.tt/rkuvTo4 October 16, 2025 at 11:04PM
Show HN: Achilleus – Security monitoring for agencies managing client websites Most security tools are either free-but-limited (SSL Labs) or enterprise-priced ($200+/month). Nothing existed for freelancers and small agencies managing multiple sites affordably. So I built it. It scans all your domains in ~30 seconds, shows you a simple security score, flags issues, and generates professional PDFs you can send to clients. No complex setup, no security expertise required. Currently $27/month for 10 domains with unlimited scans. The MVP is live and working well, but I want real feedback before pushing hard on growth. Looking for beta users—especially freelancers or small agency owners managing 5+ client sites. If you're interested, I'd love to hear what works and what doesn't: https://achilleus.so Happy to answer questions in the comments. https://ift.tt/dNgz46b October 16, 2025 at 07:34AM
Show HN: Pxxl App – A Nigerian Alternative to Vercel, Render, and Netlify Hi HN, I built Pxxl App — a free web hosting and deployment platform for developers in Nigeria and beyond. It’s a Nigerian alternative to Vercel, Render, and Netlify, designed for those who want a simple, fast, and barrier-free way to host both frontend and backend apps. With Pxxl App, you can connect your Git repo and deploy in seconds — no credit card, no limits. You’ll get a live subdomain like yourapp.pxxl.pro, automatic builds, and continuous deployment. It supports: • Frontend frameworks: React, Next.js, Vue, Svelte, and more • Backend projects: Node.js, PHP, and Python • Features like environment variables, CI/CD, and instant rollback The goal is to make cloud deployment accessible to African and global developers without the typical payment or region restrictions. It’s completely free to start, and I’d love to hear feedback from the HN community on how to improve it or what features you’d want next. Check it out: https://pxxl.app https://pxxl.app October 15, 2025 at 11:55PM
Show HN: Specific (YC F25) – Build backends with specifications instead of code Hi folks! Iman and I (Fabian) have been building Specific for a while now and are finally opening up our public beta. Specific is a platform for building backend APIs and services entirely through natural-language specifications and tests, without writing code. We then automatically turn your specs into a working system and deploy it for you, along with any infrastructure needed. We know a lot of developers who have already adopted spec-driven development to focus on high-level design and let coding agents take care of implementation. We are attempting to take this even further by making the specs themselves the source of truth. Of course, we can’t blindly trust coding agents to follow the spec, so we also support adding tests that will run to ensure the system behaves as expected and to avoid regressions. There is so much ground to cover, so we are focusing on a smaller set of initial features that in our experience should cover a large portion of backends: - An HTTP server for each project. Authentication can be added by simply stating in the spec how you want to protect your endpoint. - A database automatically spun up and schema configured if the spec indicates persistence is needed. - External APIs can be called. You can even link out to API docs in your specs. You currently can’t see the generated code, but we are working on enabling it. Of course, we don’t claim any ownership of the generated code and will gladly let you export it and continue building elsewhere. Specific is free to try and we are really eager to hear your feedback on it! Try it here: https://ift.tt/cAePvkf https://specific.dev/ October 15, 2025 at 10:51PM
Show HN: Cmux – Coding Agent Multiplexer HN, I'm stoked to share this product I've been working on non-stop for the past few weeks. It's an immersive GUI experience for working with many coding agents in parallel. The UX should be familiar to Claude Code users, but we took advantage of the GUI nature to add in a bunch more. cmux is early but certainly usable—almost all of our internal cmux development rolls through cmux itself. Please let me know your thoughts and feedback! https://ift.tt/fmnFbDS October 15, 2025 at 11:10PM
Show HN: Wispbit – Keep codebase standards alive Hey HN! Ilya and Nikita here. We're building wispbit ( https://wispbit.com ) - a tool that helps keep codebase standards alive. With the help of AI coding tools, engineers are writing more code than ever. Code output has increased, but the tooling to manage this hasn't improved. Background agents still write bad code, and your IDE still writes slop without the right context. So we built wispbit. It works by scanning your codebase for patterns you already use, and coming up with rules. Rules are kept up to date as standards change, and you can edit rules any time. You can enforce these rules during code review, and because we have this rules system, you can run a CLI locally to review using these rules. You can think of it as a portable rules file that you can bring anywhere. We put a lot of work into making a system that produces good rules and avoids slop. For repository crawling, we have an agent that dispatches subagents, similar to Anthropic's research agent. These subagents will go through and look for common patterns within modules and directories, and report back to the main agent, which synthesizes the results. We also do a historical scan on your pull request comments, determine which ones were addressed, filter out comments that wouldn't make a good rule, and use that to create or update rules. Our early users are seeing 80%+ resolution rates, meaning that 80% of comments that wispbit makes are resolved. Long-term, we see ourselves being a validation layer for AI-written code. With tools like Devin and Cursor, we find ourselves having to re-prompt the same solution many times. We still don't know the long-term implications on AI-assisted codebases, so we want to get in front of that as soon as possible. We've opened up signups for free to HN folks at https://wispbit.com . We're also around to chat and answer questions! https://wispbit.com October 15, 2025 at 01:22AM
Show HN: Ark v0.6.0 – Go ECS with new declarative event system Ark is a high-performance Entity Component System (ECS) library for Go. Ark v0.6.0 introduces a new event system built around lightweight, composable observers. These allow applications to react to ECS lifecycle changes like entity creation/removal, component updates, relation changes using declarative filters and callbacks. Observers follow the same patterns as Ark’s query system, making them easy to integrate and reason about. Custom events are also supported. They can be emitted manually and observed with the same filtering logic, making them ideal for modeling domain-specific interactions such as input handling, and other reactive game logic. As a new performance-related feature, filters and queries are now concurrency-safe and can be executed in parallel. This release also includes a load of performance improvements, from faster archetype switching over optimized query and table creation to improved performance of bitmask operations. The new World.Shrink method helps reclaim unused memory in dynamic workloads. Docs have been expanded with a full guide to the event system, examples for both built-in and custom events, and an Ebiten integration example. A cheat sheet for common operations has been added. Finally, Ark now has 100% test coverage. Changelog: https://ift.tt/6dohaxl Repo: https://ift.tt/6loEsmL Would love feedback from anyone building games, simulations, or ECS tooling in Go. https://ift.tt/6loEsmL October 14, 2025 at 12:34PM
Show HN: Wordle but you have to predict your score before playing If you want to compare your results feel free to join the HN team. However you can also play without signing up for an account. Its a SvelteKit application running on Cloudflare Workers. Would love some feedback on the idea and execution! https://ift.tt/nv8WD6o October 14, 2025 at 08:56AM
Show HN: AI Toy I worked on is in stores Alt link: https://ift.tt/38pl2kR Video demo: https://www.youtube.com/watch?v=0z7QJxZWFQg The first time I talked with AI santa and it responded with a joke I was HOOKED. The fun/nonsense doesn't click until you try it yourself. What's even more exciting is you can build it yourself: libpeer: https://ift.tt/1DdIEQ9 pion: https://ift.tt/O6C0dbh Then go do all your fun logic in your Pion server. Connect to any Voice AI provider, or roll your own via Open Source. Anything is possible. If you have questions or hit any roadblocks I would love to help you. I have lots of hardware snippets on my GitHub: https://ift.tt/wOo3qLR . https://ift.tt/wC842ds October 12, 2025 at 07:45PM
Show HN: Pyreqwest – Powerful and fast Rust-reqwest based HTTP client for Python Python has lacked a batteries-included HTTP library that would have both async and sync clients. Httpx (httpcore), which has offered this, is unfortunately pretty much unmaintained and suffering from huge perf issues ( https://ift.tt/eDXhG7n ). I built pyreqwest HTTP client for Python that is fully Rust based on top of reqwest. It includes all features reqwest offers plus some more. Also including unit testing utilities (mocking, ASGI app support). Go check https://ift.tt/yqf0cJi :) https://ift.tt/yqf0cJi October 13, 2025 at 01:17AM
Show HN: I built a simple ambient sound app with no ads or subscriptions I’ve always liked having background noise while working or falling asleep, but I got frustrated that most “white noise” or ambient sound apps are either paywalled, stuffed with ads, or try to upsell subscriptions for basic features. So I made Ambi, a small iOS app with a clean interface and a set of freely available ambient sounds — rain, waves, wind, birds, that sort of thing. You can mix them, adjust volume levels, and just let it play all night or while you work. Everything works offline and there are no hidden catches. It’s something I built for myself first, but I figured others might find it useful too. Feedback, bugs, and suggestions are all welcome. https://ift.tt/ZWfmypA... https://ambisounds.app/ October 12, 2025 at 08:19PM
Show HN: Recallie AI – Duolingo for learning anything I built an app with a Duolingo-style structured learning system where users can generate full courses from photos, documents, or typed input. Each course includes quizzes, flashcards, and notes, and users can also turn their notes into an AI-generated podcast for audio learning. It’s designed to help students and anyone who wants to learn a topic study smarter and retain more through interactive lessons, quizzes, and podcasts tailored to their learning style. Built with React Native Expo. https://youtu.be/jsRk1vN1xNA?si=iMGZFhj_N2iwBp5n https://ift.tt/4wgaJvz October 12, 2025 at 11:13PM
Show HN: Vello's high-performance 2D GPU engine to .NET VelloSharp v0.5.0-alpha.1 is now available, delivering Vello’s high-performance 2D GPU engine to .NET atop the wgpu 3D backend. Integrates cleanly with Avalonia, WPF, and WinForms to modernize rendering pipelines without disruptive rewrites. https://ift.tt/IJ1L6W4 October 12, 2025 at 03:32AM
Show HN: Sprite Garden - HTML Canvas 2D sandbox and farming Sprite Garden: https://kherrick.github.io/sprite-garden/ A 2D sandbox exploration and farming game that runs entirely in the web browser. As a fully HTML, CSS, and JavaScript game, it is highly readable, hackable, and customizable. Included on "globalThis" is the "spriteGarden" global object with the game config and state readily available. Drawing with tiles is as easy as opening dev tools (use the menu in the browser as keyboard is captured), or entering the "Konami Code," for a full screen view and a map editor. - Share games from the world state manager - Explore unique procedurally generated biomes - Dig for resources like coal, iron, and gold - Use collected materials to place blocks and shape the world - Discover underground cave systems filled with resources - Plant and harvest different crops with "realistic" growth cycles Examples: - Preparing a QR Code to be mined: https://gist.github.com/kherrick/1191ae457e1f6e1a65031c38c2d... - Drawing a heart in the sky: https://gist.github.com/kherrick/3dc9af05bccc126b11cc26fb30a... - Entering the Konami Code (map editor / fullscreen): https://gist.github.com/kherrick/effbe1463d9b78da046f27c5d42... I'm unsure how the game should be taken further, or whether it should progress. Some potential ideas for the future include: - Input Box with JS Execution: Provide a safe, sandboxed input area in the game's UI where players can write small JS functions or scripts (instead of exposing it on globalThis). - API Exposure: Expose a controlled API or object representing game state and functions, like terrain manipulation, crop growth, player movement, to the user script so players can automate or modify behaviors. - Event Hooks: Allow players to register hooks into game events (e.g., world update, planting crops) where their custom code runs, enabling mods or custom automation. - Multiplayer: Use WebRTC to allow many players in the same world. - Actual gamification: Make reasons to play, health meter, powerups, plant combinations, enemies? - Better mobile controls: Currently on screen, no swiping for movement. - Easier building with blocks: Currently block position based on location of player. Also featured on: - Microsoft Store: https://ift.tt/zRWnIj5 - Wayback Machine: https://ift.tt/WsJhRyK.... Feedback is highly welcome, and source is available at: https://ift.tt/2KbFSg6 https://kherrick.github.io/sprite-garden/ October 12, 2025 at 03:15AM
Show HN: Multiple choice video webgame experiment Hey all, just wanted to share a little game experiment. It's a rooms & keys kind of adventure with a lot of random deaths. It plays a Veo3-generated video in response to clicks, with Gemini used for coding. Prompting the videos was fun, but trying to vibe code everything was not. In the future I'll go back to using LLMs more sparingly for isolated functions, or at least try not to have it create anything that requires seeing the output to debug. https://ift.tt/EwDdjXp October 10, 2025 at 10:39PM
Show HN: Modeling the Human Body in Rust So I Can Cmd+Click Through It I started this trying to understand two things: why my Asian friends turn red after drinking, and why several friends all seemed to have migraine clusters. I was reading medical papers and textbooks, but kept getting lost jumping between topics. I thought: what if I could just Cmd+Click through this like code? What if "ALDH2 gene" was actually clickable, and took me to the variant, the phenotype, the population frequencies? So I started modeling human biology in Rust with my Ralph agent (Claude in a loop, ty ghuntley). Turns out the type system is perfect for this. Every biological entity is strongly-typed with relationships enforced at compile time. After 1 day of agent coding: - 277 Rust files, ~95k lines of code - 1,561 tests passing - 13 complete organ systems - Genetics with ancestry-specific variants - Clinical pathology models Try it: git clone https://ift.tt/bNMJ9nF cd open_human_ontology cargo run --example ide_navigation_demo Then open `examples/ide_navigation_demo.rs` and Cmd+Click through: Understanding Asian flush: AsianGeneticVariantsCatalog::get_metabolic_variants() // Click through to: // → ALDH2 gene on chromosome 12q24.12 // → rs671 variant (Glu504Lys) // → 40% frequency in Japanese population // → Alcohol flush reaction // → 10x esophageal cancer risk with alcohol // → Acetaldehyde metabolism pathway Understanding migraines: Migraine { subtype: WithAura, triggers: [Stress, LackOfSleep, HormonalChanges], genetic_variants: ["rs2075968", "rs1835740"], ... } // Click through to: // → 17 migraine trigger types // → 12 aura symptom types // → Genetic risk factors // → Why clusters happen (HormonalChanges → Menstruation) Now I can actually navigate the connections instead of flipping through PDFs. Heart → CoronaryArtery → Plaque. VisualCortex → 200M neurons → NeuralConnection pathways. It's like Wikipedia but type-checked and with jump-to-definition. This isn't production medical software - it's a learning tool. But it's way more useful than textbooks for understanding how biological systems connect. The agent keeps expanding it. Sometimes it OOMs but that's part of the fun. Tech: Rust, nalgebra, serde, rayon, proptest I am not a dr or medical professional this is for my education you can commit to it if you want to or review and open some PR's if you find wrong information or want to add references. https://ift.tt/bNMJ9nF October 10, 2025 at 11:29PM
Show HN: Created macOS app to help you keep your distance from your screen Hey everyone, If you're anything like me, you spend a good chunk of your day (and night) on your computer. I often find that when I'm zoned in, my posture gets worse and worse and my face ends up being really close to the screen. And over a course of a workday, when I finally unplug, my eyes have a hard time focusing on things that are far away. This has become a big enough problem for me that I decided to create an app to help me keep my face far enough from the screen. Now, I could've gone with a simple notification with a timer built into it but, as with all reminder notification, they soon become noise for me and I end up just dismissing it. I needed something to actively force me to move back. Which is where FarSight comes in. It uses your camera to gauge your distance and blurs the entire screen if it detects that you are getting close enough for a certain period of time. I made it so that it won't be extremely annoying and disruptive (e.g. blurring the screen every time you cross the line) but just enough of a nuisance to be helpful. I've been using it everyday since creating it and it's definitely helped me with eye strain, double vision, and surprisingly, my posture as well. I'm not sure if I'll keep it free forever but I wanted to release it first to ask for feedback. I only have the app in MacOS so if it has enough interest, I'll invest into making Windows counterpart. https://ift.tt/pWDy20F... Also, in case anyone is wondering, no data is collected and the snapshots during the app's usage are not saved but only used to calculate the distance. October 10, 2025 at 01:57AM
Show HN: Open-source UI for running multiple coding agents Hi HN! I've recently been finding productivity in running parallel CLI coding agents(after not believing in them initially). After having to do a ton of git stashing and branch fumbling, I decided I needed to something to more ergonomically run these agents in their own dedicated spaces. I tried a lot of the existing products but they either were too convoluted or flat out didn't work. Some of them also seem to roll their own chat UI which I don't think is the right approach, I wanted to something to lightly wrap my terminal sessions. So I built FleetCode! It uses git worktrees and let's you run multiple agents at once. It's made my multi agent coding workflow much easier. It's free and open source, would love some feedback! https://ift.tt/AT94uZ7 October 8, 2025 at 11:30PM
Show HN: KI Song Erstellen Kostenlos – AI Music Generator FüR Deutsche Musik Kostenloser KI-Musikgenerator für deutsche Songs. Text rein → professioneller Song in wenigen Minuten. Gebaut für Content Creator, die Copyright-freie Musik brauchen. https://ift.tt/g3Ptoxl GitHub: https://ift.tt/wEGrCAl Probiert es aus! https://ift.tt/g3Ptoxl October 8, 2025 at 10:26PM
Show HN: I built a local-first podcast app I worked on early podcast software in 2004 (iPodder/Juice) and have been a heavy podcast consumer ever since. I wanted a podcast app that respects your privacy and embraces the open web—and to explore what's possible in the browser. The result is wherever.audio, which you can try right now at the link above. How it works: It's a progressive web app that stores all your subscriptions and data locally in your browser using IndexedDB. Add it to your home screen and it feels native. Works offline with downloaded episodes. No central server storing your data—just some Cloudflare/AWS helpers to smooth out browser limitations. What makes it different: - True local-first: Your data stays on your device - Custom feeds: Add any RSS feed, not just what's in a directory - On-device search: Search across all feeds and episodes, including your custom ones - Podcasting 2.0 support: Chapters, transcripts, funding tags, and others - Auto-generated chapters: For popular shows that don't have them - AI-powered discovery: Ask questions to find shows and episodes (this feature does send queries to a 3rd party API, and also uses anonymized analytics while we work out the prompts) - Audio-guided tutorials: Interactive walkthroughs with voice guidance and visual cues The basics work well too: Standard playback features, queue management, speed controls, etc. I'm really interested in feedback—this is more passion project than business right now. I've been dogfooding it as my daily podcast app for over a year, and I'm open to exploring making it a business if people find it valuable. Curious if there are unmet needs that a privacy-focused, open web approach could address. https://wherever.audio October 8, 2025 at 10:16PM
Show HN: Rethinking audit trails in Django (structured and database-free) We were using django-easy-audit to track CRUD and API events in Django. The problem: every action meant an extra database write, which slowed transactions, increased infra costs, and left us with audit tables that weren’t great for analytics. I built django-activity-audit (PyPI) to fix this: - Extends Django’s logging system with custom AUDIT and API levels. - Captures CRUD + API request/response events as structured JSON logs. - Vector tails the logs and ships them into ClickHouse. - Grafana makes them queryable and visual. This removes the extra DB writes, gives structured data ready for analysis, and keeps costs down. Curious — how are others handling audit logging in Django (or other frameworks)? Do you log it, write it to a DB, or something else entirely? https://ift.tt/ocKCai3 October 7, 2025 at 10:25PM
Show HN: A Vectorless LLM-Native Document Index Method The word "index" originally came from how humans retrieve info: book indexes and tables of contents that guide us to the right place in documents. Computers later borrowed the term for data structures: e.g., B-trees, hash tables, and more recently, vector indexes. They are highly efficient for machines; but abstract and unnatural: not something a human, or an LLM, can understand and directly use as a reasoning aid. This creates a gap between how indexes work for computers and how they should work for models that reason like humans. PageIndex is a new step that "looks back to move forward". It revives the original, human-oriented idea of an index and adapts it for LLMs. Now the index itself (PageIndex) lives inside the LLM's context window: the model sees a hierarchical table-of-contents tree and reasons its way down to the right span, much like a person would retrieve information using a book's index. PageIndex MCP shows how this works in practice: it runs as a MCP server, exposing a document's structure directly to LLMs/Agents. This means platforms like Claude, Cursor, or any MCP-enabled agent or LLM can navigate the index themselves and reason their way through documents, not with vectors/chunking, but in a human-like, reasoning-based way. https://ift.tt/ydPw6fo October 5, 2025 at 10:09PM
Show HN: An open-source, RL-native observability framework we've been missing The RL ecosystem is maturing— verifiers are standardizing how we build and share environments. However, as it grows, we need observability tooling that actually understands RL primitives. Running RL experiments without visibility into rollout quality, reward distributions, or failure modes is a waste of time. Monitor provides live tracking, per-example inspection, and programmatic access—see what's happening during runs and debug what went wrong afterward. https://ift.tt/ZzNa4Ol October 5, 2025 at 03:05AM
Show HN: World Amazing Framework: Like Django for Civilization Any initial thoughts? This framework is meant to be a tool for construction, so if you want to play around with it for creating potential specific implementations, you can drop the contents of the website, the GitHub README, and the entire overview.md into an AI chat, and that should be enough to use the framework, at least conceptually. Would y'all want me to pre-prime a chat in Google AI Studio with the full context of the plan and some basic direction for discourse? I can share a link to a ready-to-go environment. The core documentation should answer most mechanical questions. And if you feed the docs into an AI chat, you can ask it any question you may have, or to simply ask it to explain something in different ways, or hypothesize solutions to any world issue, either systemic or regional. Gemini Pro 2.5 can take the full doc in one prompt, and its ability to co-create ideas is remarkable. I've been using it mostly through the AI Studio interface. Much of the overview is as much my work as it is a synthesis of my collaboration with Gemini Pro 2.5, ChatGPT-4o, and some early contributions from GPT-4 about a year ago. Before LLMs, I was building out pamphlet-style pages on a website (that are up at whomanatee.org, which is the base wrapper implementation of the framework), and I was planning to use them as talking points. I was anticipating that much of the deep thinking would have to happen in slow, public discourse. With LLMs, I've been able to stress-test these ideas from every possible angle, using any past event or theory to see if the framework could withstand scrutiny. At one point, a model argued that Adam Smith would have rejected this idea as fantasy. So I worked with it to develop an economic plan that "synthetic Adam" praised. It's incredible that we now have the ability to get synthesized thoughts from almost any perspective. You could ask it, "What would Barack Obama think of this plan? And using the framework, what would be your response to any hesitations he may have?" And it responds with incredible analysis, synthesis, and feedback. https://ift.tt/uXJKTbd October 5, 2025 at 03:44AM
Show HN: Run – a CLI universal code runner I built while learning Rust Hi HN — I’m learning Rust and decided to build a universal CLI for running code in many languages. The tool, Run, aims to be a single, minimal dependency utility for: running one-off snippets (from CLI flags), running files, reading and executing piped stdin, and providing language-specific REPLs that you can switch between interactively. I designed it to support both interpreted languages (Python, JS, Ruby, etc.) and compiled languages (Rust, Go, C/C++). It detects languages from flags or file extensions, can compile temporary files for compiled languages, and exposes a unified REPL experience with commands like :help, :lang, and :quit. Install: cargo install run-kit (or use the platform downloads on GitHub). Source & releases: https://ift.tt/Cn5M4Hl I used Rust while following the official learning resources and used AI to speed up development, so I expect there are bugs and rough edges. I’d love feedback on: usability and UX of the REPL, edge cases for piping input to language runtimes, security considerations (sandboxing/resource limits), packaging and cross-platform distribution. Thanks — I’ll try to answer questions and share design notes. https://ift.tt/Cn5M4Hl October 5, 2025 at 12:04AM
Show HN: Was pissed about Google Docs, So I made an Text Editor myself It’s been a while since I’ve started to write a book . The process of creation of it has not been easy , first because I’m not a writer , I’ve created well though out internet posts here and there, which ended up creating my first book. It was a good experience , but then I’ve started to think that a book that just gathered my thoughts online it’s not entirely “writing” a book , I needed more. And than I’ve opened google docs and start typing. Then I started to figure out what I wanted to write: should it be a fantasy story, a self-biography, or an observation of the world? I believe most writers have this figured out beforehand, but not me. I began writing pieces to see if they would fit together and make sense. I started gathering philosophical anecdotes based on my core beliefs and sensed something brewing. When I finally decided what the book would be about, and what I wanted to write, the type of writing I wanted to do, I saw an already sizable document with ideas scattered throughout it. That was good for me, as I could just join the pieces, but I didn’t want to be trapped in writing that could be repetitive. I wanted to have the ideas, philosophy, the whole reason why the book is like this, stored in a place I could easily access. I'm planning to use AI as a memory dump, where I can add information during a conversation. Then, whenever I consult it, I can check if I've already written something and if it reflects the temper and pace I want for my book. Everything seems fine, but we encountered a few problems. First, the AI's writing was a conundrum of errors. I could gain assistance and a sense of what to write, but the AI itself, due to our prolonged interchange, started to hallucinate and produce nonsense or "forget" our conversation. The second issue was that the AI couldn't consistently verify what was already written. As the text grew larger, the context window began to shrink, and the more I used the AI tool, the less helpful it became. So I decided to search for a tool that could do what I wanted. I found elements in each of the products I've used: some were extremely satisfying to write with, others had good features to enhance text, some allowed me to organize my book by scattering ideas effectively, and still others used AI for correction and proofreading tasks. The solutions for this market are diverse and offer numerous approaches. I could easily transition between tools, but I wanted something unified to keep my writing process in one place. That’s why I created this text editor and called it SourcePilot. It’s a tool that identifies your writing style as you write, allowing you to add notes, sources, and videos, and to use them as context for the AI, enabling more nuanced outputs tailored to your writing. It was interesting to build, and I’m providing a link you can try. It’s a desktop app, and you can use it for free, depending on the hardware you have. I’m looking for people who could give me feedback on what's wrong with it. People who could not install it (I’ve built it on Mac and could not test Linux and Windows), or have problems logging in. I keep getting loads of problems because I’m using the tool right now as I write this text. I'm planning to launch a new version soon, featuring an anti-slop algorithm I’ve developed, along with document branching. I just want to see if there are people interested in using it at the moment. If there aren't users, that's fine. I think I’ve made something for myself anyway. :) Thank you for your attention if you made it this far. You’re greatly appreciated. Cheers! https://sourcepilot.co/ October 4, 2025 at 01:28AM
Show HN: A VS Code Extension for Genesis DB – The event sourcing database I've been working on an extension that brings the full Genesis DB experience directly into Visual Studio Code. Genesis DB itself is a production-ready event-sourcing database engine, and with this extension you can now: - Manage multiple connections (dev, staging, prod) with token-based authentication - Explore events via a built-in Event Explorer UI - Commit new events, run GDBQL queries, and instantly view results - Manage schemas (register, browse, validate) directly in the editor - Use built-in GDPR features like event erasure, without leaving VS Code The goal: no more context switching between CLI, APIs, and docs, everything integrated into the editor you already use. You can check out the extension here: https://marketplace.visualstudio.com/items?itemName=patricec... I'd love to hear what you think: Is this something that would help your workflow? What would you expect from a database extension in VS Code? https://ift.tt/WuwFljX October 4, 2025 at 01:12AM
Show HN: FLE v0.3 – Claude Code Plays Factorio We're excited to release v0.3.0 of the Factorio Learning Environment (FLE), an open-source environment for evaluating AI agents on long-horizon planning, spatial reasoning, and automation tasks. == What is FLE? == FLE uses the game Factorio to test whether AI can handle complex, open-ended engineering challenges. Agents write Python code to build automated factories, progressing from simple resource extraction (~30 units/min) to sophisticated production chains (millions of units/sec). == What's new in 0.3.0 == - Headless scaling: No longer needs the game client, enabling massive parallelization! - OpenAI Gym compatibility: Standard interface for RL research - Claude Code integration: We're livestreaming Claude playing Factorio [on Twitch]( https://ift.tt/57bl2Js ) - Better tooling and SDK: 1-line CLI commands to run evaluations (with W&B logging) == Key findings == We evaluated frontier models (Claude Opus 4.1, GPT-5, Gemini 2.5 Pro, Grok 4) on 24 production automation tasks of increasing complexity. Even the best models struggle: - Most models still rely on semi-manual strategies rather than true automation - Agents rarely define helper functions or abstractions, limiting their ability to scale - Error recovery remains difficult – agents often get stuck in repetitive failure loops The performance gap between models on FLE correlates more closely with real-world task benchmarks (like GDPVal) than with traditional coding/reasoning evals. == Why this matters == Unlike benchmarks based on exams that saturate quickly, Factorio's exponential complexity scaling means there's effectively no performance ceiling. The skills needed - system debugging, constraint satisfaction, logistics optimization - transfer directly to real challenges. == Try it yourself == >>> uv add factorio-learning-environment >>> uv add "factorio-learning-environment[eval]" >>> fle cluster start >>> fle eval --config configs/gym_run_config.json We're looking for researchers, engineers, and modders interested in pushing the boundaries of agent capabilities. Join our Discord if you want to contribute. We look forward to meeting you and seeing what you can build! -- FLE Team https://jackhopkins.github.io/factorio-learning-environment/versions/0.3.0.html October 4, 2025 at 01:02AM
Show HN: YNOT – Free, Open-Source YouTube Downloader Hey HN! I built YNOT, a simple cross-platform YouTube downloader with a GUI. It's powered by yt-dlp and completely free/open-source (WTFPL license). Key features: - Simple GUI - just paste URL and download - Downloads HD/4K videos - Cross-platform (Windows, macOS, Linux) - No ads, no tracking, completely private - Lightweight and fast GitHub: https://ift.tt/GQ0dIMt I'd love to hear your feedback and suggestions! https://james-see.github.io/ynot/ October 3, 2025 at 04:26AM
Show HN: Uber for Flights My friend and I built BookMyFlight to finally modernize flight search + booking. Why we built this: - Personalization. I fly the same route every month, and there’s no platform that knows my preferences so that I can open it, find and book my flight, and close it within a minute. - Booking is slow. I hate seeing a long clunky airline form each time I need to book. I want booking a flight to feel more like booking an Uber. How it works: 1. Optionally make an account and save your traveler preferences. Personally, I've specified my routine route as SFO to CLE and that I only want red-eye direct flights for this route. 2. Search for flights using chat or the search panel. Chat feels especially time-saving when you have preferences saved (e.g. I just say “search my routine trip"). 3. Once you find the flight you want, use the one-click book feature which books your flight directly with the airline. The first time you book a flight, you’ll have to fill out your traveler info, but you won't see that form after that. Notes: - Your booking is directly with the airline (this means when something goes wrong, you get direct support from the airline—not a third-party) - You can add your rewards numbers for each airline to keep earning points/status The ultimate goal is to create the best possible experience that every traveler wants, but that OTAs and airlines don’t care to create. Also very receptive to hearing pain points from frequent flyers; we think this space is really outdated and could use some innovation. Try it out and let us know what you think :) https://bookmyflight.ai October 3, 2025 at 01:29AM
Show HN: Enhance – A Terminal UI for GitHub Actions I'm very excited to share what I've been working on lately! Introducing ENHANCE, a terminal UI for GitHub Actions that lets you easily see and interact with your PRs checks. It's available under a sponsorware model. Get more info on the site: -> https://ift.tt/HifE4ML This is an attempt to make my OSS development something sustainable. Happy to hear feedback about the model as well as the tool! Cheers! https://ift.tt/QCLftBe October 3, 2025 at 12:49AM
Show HN: Ubiquiti-themed memory game (fan-made, non-commercial) I built a small browser game in the style of memory/pexeso using images of Ubiquiti products. It's fan-made and non-commercial (I used to work at Ubiquiti) and made for my son to have fun. All product names and logos are trademarks of their respective owners. Would love feedback on UI/UX and performance tweaks. https://ui-game.com/ October 2, 2025 at 11:19PM
Show HN: Rostra is a P2P (f2f) social network A public instance is available at https://rostra.me/ . It will default to showing the interface from the perspective of my own identity, in a read-only mode. Click "Logout" and then "Random" to generate your own identity to play with. https://app.radicle.xyz/nodes/radicle.dpc.pw/rad%3AzzK566qFsZnXomX2juRjxj9K1LuF October 2, 2025 at 03:40AM
Show HN: Spit Notes – A songwriting app that keeps lyrics and audio together Any songwriter who uses the iOS Notes app to write their lyrics has a mess of New Recording 142 voice memos in their Voice Memos app. I made Spit Notes as basically the Notes app but with a built-in voice recorder that keeps your audio files neatly organized on the same line as your lyrics. Now you can quickly capture your song ideas while driving or when you wake up in the middle of the night without worrying about losing them in your pile of untitled voice memos. While you can attach audio to notes with other apps, adding and recording audio has a lot of friction, and often the layout of the audio elements in those apps are too pronounced to keep the text flowing seamlessly. This is not the case with Spit Notes. I've wanted this app to exist for years but I put off making it myself because I knew it would take me a lot of time to build manually without knowing Swift. In recent years I've been writing AI-assisted code, but with AI coding agents getting better and better, 3 months ago I decided to see if I could vibe code a full product. The code for this project was not AI-assisted, but human-assisted, with me providing the vision and feel of the app, while the AI agent takes that, makes a pass at the code base, and then I QA it, letting the AI know what worked/didn't work, and iterating. I started with paying for Cursor and using Opus 4 but after getting insanely good initial results with Opus 4 and seeing my cursor costs start to rise, I remembered this post https://ift.tt/ZPExvW3 and took the plunge with Claude Code max $200 plan. This turned out to be an incredible value because it allowed me to use claude basically without limit. However, Gemini still had the biggest context window and as the project grew I had to use Gemini to create plans for big features and find deep bugs across all of the AI-generated modules. Pro tip: create broad reference files for you and the AI, like an ARCHITECTURE.md where you keep a human-readable version of the technical big picture. You can then reference that for the AI so it stays aligned with your current progression. Once the Codex CLI became available on homebrew it was a wrap. I cancelled my claude code max plan and have been happily coding without ever hitting any rate limits (other than when they made that update that accidentally reduced rate limits instead of increase them). Today, I pay for for chatgpt plus and gemini $20 plan and am able to clear most obstacles on the first or second prompt. I haven't tried opus 4.5 but since I am not really getting stuck with codex, for now I'll stick with that. https://ift.tt/FvufGDb October 1, 2025 at 10:12PM
Show HN: I got tired of spreadsheets, so I built a Python GUI to track invoices Hey HN, As a freelancer, I found myself spending time every month manually opening PDF and Word invoices, copying the details into a spreadsheet, and tracking payments. It was tedious and error-prone. I decided to build a simple desktop app to automate this. It's a GUI built with Python and Tkinter that points to a folder of invoices, parses the key details (invoice #, amount, date), and stores everything in a local SQLite database for tracking and analysis. It's been quite a time- and headache-saver for me. A Note on Simplicity & Caveats I'm sharing this in case it's useful to any other freelancers or businesses, but I want to be upfront about its limitations: The UI is very basic. It's built with vanilla Tkinter and is all about function over form. It's not the prettiest app, but it gets the job done. The core automation relies on a "patterns" feature that matches invoice prefixes to clients. This is super useful for my own workflow but might be a bit niche if your invoice naming is less consistent. You can still use manual entry if patterns don't work for you. The stats dashboard is Euro-centric right now and aggregates all currencies into a total shown in Euros (€). I plan to fix this later. It's a simple personal project that solves a personal problem. The code is on GitHub, and I'd love to hear any feedback or suggestions you might have. https://ift.tt/RnMdjob September 30, 2025 at 08:33PM
संदेश
