Thursday 31 August 2023

Show HN: Name Checker – check your project name accross many sites https://bit.ly/3QZOKET

Show HN: Name Checker – check your project name accross many sites https://bit.ly/45zfC30 September 1, 2023 at 02:35AM

Show HN: Squabblr – A Twitter/Reddit hybrid platform https://bit.ly/3Z5USNZ

Show HN: Squabblr – A Twitter/Reddit hybrid platform Hey guys, I made a post about this about a week ago and was told to create a Show HN post. So here we are! Squabblr is a hybrid that takes Twitter style posting and combines it with Reddit style commenting. It came up from a personal want where I liked using Twitter to see what people I'm interested in are up to, but found that the reply system left a lot to be desired. It's very hard to have or follow conversations with their UI. While Reddit provided a great commenting system but didn't support following people very well (or had much usage of it at all). So I decided to create Squabblr. You can "tweet" random blurbs or have in-depth conversations in a single unified platform. You can follow people, and you can also have Reddit style communities for whatever niche subject you find interest in. If you find any interest in it, check it out here! https://bit.ly/3qXyQQX Tech stack: - Laravel - Vue.js - MySQL - DigitalOcean Appreciate your time! https://bit.ly/3L2ARlH August 31, 2023 at 07:26PM

Show HN: Video about the CPU vulnerability Zenbleed (CVE-2023-20593) https://bit.ly/44zjIqw

Show HN: Video about the CPU vulnerability Zenbleed (CVE-2023-20593) https://www.youtube.com/watch?v=9EY_9KtxyPg August 31, 2023 at 03:25PM

Show HN: A NextJS boilerplate to automate all the boring stuff https://bit.ly/3R1WKFC

Show HN: A NextJS boilerplate to automate all the boring stuff Hey HN, I'm a solopreneur and I ship apps like a madman. 16 startups in the last 2 years. I realized I was doing the same thing over and over: set up DNS records, connect DB, listen to Stripe webhooks... So I built ShipFast for 2 reasons: 1. Save time and focus on what matters: building a business 2. Avoid headaches like emails ending in spam or waiting 3 days for Google to approve I hope this boilerplate will be as helpful to you as it is for me. Would love your feedback pls Marc https://bit.ly/3R2sjPr August 31, 2023 at 09:12AM

Show HN: Vercel-like preview deployment comments but for every platform https://bit.ly/44yStfK

Show HN: Vercel-like preview deployment comments but for every platform Huddle is a cloud platform agnostic collaboration tool for preview deployments. With Huddle, your team can initiate discussions, share insights, and enhance website quality, all right within your deployment previews. Why Huddle Wins? Cloud Platform Agnostic: Huddle plays nice with all platforms – no more compatibility worries! Real-Time Interaction: Experience live collaboration with team members via cursor movement and real-time comments. No Per-User Pricing Drama: Say goodbye to perplexing pricing structures. Huddle keeps things simple and cost-effective. Would love to hear your feedback :) https://bit.ly/3P1l2Nr August 31, 2023 at 04:42AM

Show HN: 99% cheaper international business transfers – fixed fee, real rate https://bit.ly/47UFIiA

Show HN: 99% cheaper international business transfers – fixed fee, real rate Hello Hackers! One year ago we changed international transfers for consumers with only a fixed fee and made them on average 10x cheaper than Wise. Now we are thrilled to announce that we start “Atlantic Money for Business” to offer transfers up to £/€1m for a fixed £/€3 fee and at the current exchange rate. And while Revolut and Wise have recently raised their prices for business transfers by up to 50%, we enable savings of several thousand on every transfer. What are you waiting for? https://bit.ly/45ul47f August 31, 2023 at 10:51AM

Show HN: Yet Another Notepad App for macOS https://bit.ly/3L3zfbw

Show HN: Yet Another Notepad App for macOS Any suggestion is welcomed and appreciated! https://bit.ly/45ul3QJ August 31, 2023 at 10:37AM

Show HN: Vanity Git commit hash generator https://bit.ly/45xuDSZ

Show HN: Vanity Git commit hash generator Hi HN! This is just a fun little tool I made after I got nerdsniped by noticing that one of my commits naturally started with "fae". I thought that was cute, so I looked up existing tools that make vanity commit hashes, but none of them seemed great to me (and none supporting signing commits). I learned a fair deal about how git actually stores commits while making this, and I think I came up with a novel way to generate a vanity hash: adding an extra header to the commit file. This was just a quick project to satisfy my curiosity, but I thought you all might find it neat. Notice that all the commits in that repo start with "fae0"! - Anna https://bit.ly/3Eiy6J5 August 31, 2023 at 08:13AM

Wednesday 30 August 2023

Show HN: Write Github Actions Workflows in Typescript Rather Than YAML https://bit.ly/3OUIM5z

Show HN: Write Github Actions Workflows in Typescript Rather Than YAML Hey HN, I just released github-actions-workflow-ts, an NPM package that allows you to write GitHub Actions workflows in Typescript rather than YAML. The package then generates GH Actions workflow YAML files from your Typescript code. Why? - Type safety - Code re-usability: package and reuse common jobs and steps across different workflows. - Imperative edge: Utilize control flow to control the generation of different kinds of workflows easily. Essentially, I realized that as I write larger and more complicated GH Actions workflows in YAML, they become less readable and thus more prone to errors and harder to maintain/refactor. You can try it out on Replit (free but requires an account to fork my examples and run them yourself). Fork it and run the build command in the shell: - Simple Example: https://bit.ly/44vTqWc... - Advanced Example: https://bit.ly/44vTqWc... Read the accompanying blog post here: https://bit.ly/44r2X0V... Please check it out. I'm open to any feedback as I march towards the first stable 1.0.0 release. Thanks https://bit.ly/44xw1ne August 30, 2023 at 01:56PM

Show HN: Chatmate: Discover and create chatbots https://bit.ly/3PhZwoI

Show HN: Chatmate: Discover and create chatbots Chatmate.dev allows you to easily make gpt4 based chatbots by combining multiple chat completions and/or document retrievals. You can chain different components together or run them in parallel and then use their responses in future prompts/components. To get started, create a project and then create a chat component. A single chat component is the same as one chat completion. You can add more chat or document components that use the responses of previous components in their prompts. There are some simple demos in the "discover" page. You can also publish your own chatbots and share them at the share url. The first demo is a simple document extraction. I copied a few posts from today's hackernews and fed it as a pdf. I then used the document retireval in the prompt for the final chat completion. The second demo is a teaching assistant chatbot for a data structures course. It is made up of 4 components, 1) Standalone query, which converts the user input to a standalone question (so that the document retrieval can be improved) 2) Thought generator, generates a sentiment based on the user's input (i.e. the user seems stressed about their data structures homework) 3) Document retrieval, retrieves lecture notes from over 400 documents 4) combines all the components into one system prompt for a better response. Roadmap: 1) Code components - run any code (including network calls) 2) Conditional components - uses gpt functions to decide which components to run (components are the functions) 3) Multitenancy (i.e. publish your bot at {botname}.chatmate.dev 4) Verisoning - chat with multiple versions of your bot (easy comparison of prompts) If you have any feedback, feel free to reach out at "jmiran15@jhu.edu". https://bit.ly/3OQdQ7H August 30, 2023 at 05:22AM

Show HN: Preserve your families legacy for CENTURIES https://bit.ly/45xOEZG

Show HN: Preserve your families legacy for CENTURIES Hey everyone, creator of clann.app here. I will try to keep this short but at the end of the day you will be forgotten one day. I know this feels sad and it really is. I mean ask yourself who your great-grandfather is, you don't know! Heck, we don't even know how they lived their life. Now their generation had very little access to computers let alone the internet. The problem isn't about the future knowing who you are but them understanding how your generation lived their life. Further we often tend to forget about our extended family. I am from India and after every single exam someone from my extended family who I met ONCE in my life would ask me my results. I would rarely know how they are related to me. This is a problem. Further dinner table discussions about how people are related to me are always a pain. Why? Sometimes even my parents don't know! The Solution? What if you could get your entire family into the digital world, Yes, it is possible! Upload images (feature name: memories) of your family today so that your future generations would truly appreciate how much their lives have improved. Clann is built for intergenerational use and has a robust invites system (feature name: groups, invites) so that you only allow your extended family members to see a certain family. If you have any queries you can contact me on @PottiVarun. Think of Clann as Figma for families. Get your entire family on there, Invite other families (relatives) and link each family by how they are related. Everything is in a clean flow char based UI. The link is https://bit.ly/3YUzbQM . You and I need to be remembered for the coming centuries. We need to leave a mark on this world. Lets leave a small digital footprint so that the future understands and appreciates their world! Goodbye! https://bit.ly/3YUzbQM August 30, 2023 at 12:29PM

Show HN: Clippy and his friends, all in one page (Click to animate) https://bit.ly/47R86Cd

Show HN: Clippy and his friends, all in one page (Click to animate) https://bit.ly/47T6tE4 August 30, 2023 at 08:38AM

Tuesday 29 August 2023

Show HN: Hugo and Nebula Award Short Stories https://bit.ly/3OTAL0R

Show HN: Hugo and Nebula Award Short Stories https://bit.ly/3OYe77n August 29, 2023 at 10:38PM

Show HN: When Will I Run Out Of Money? (weekend project) https://bit.ly/3L2UOca

Show HN: When Will I Run Out Of Money? (weekend project) Hi everyone, I’ve been on Hacker News for a good number of years, but this is my first “Show HN”. I changed jobs recently. Tax is weird in Europe (and maybe other places as well?) in that different amounts go out at different times and repeat at various intervals. I needed to make sure I had enough cashflow to make all upcoming payments, I didn't want any surprises. So I created a little tool for my own purposes, then had fun putting a small HTML frontend on it as I thought it might be useful for someone else. I'm a backend developer in my day job, as you can probably tell from the design :) There are other tools out there that do a similar thing, but they normally require you to upload the relevant data to other people's servers, which I wasn't comfortable with for financial data. Also I didn't fancy paying anyone for a service as small as this. I'm posting it here in the hope that it's useful to someone. And to gather feedback, let me know what you think. https://bit.ly/3OTRykw August 29, 2023 at 03:14PM

Show HN: Dozens of fractals implemented in Rust and OpenGL https://bit.ly/3OVVwJp

Show HN: Dozens of fractals implemented in Rust and OpenGL https://bit.ly/3YYzzxY August 29, 2023 at 01:47PM

Show HN: Mu – A Micro App Platform https://bit.ly/3QZjWEl

Show HN: Mu – A Micro App Platform Hey all Sharing a new piece of work I've been doing with a friend. Mu is a new micro web app platform which enables building and sharing apps instantly with storage, auth and payments built in. Apps are single file, built in the browser and rendered as an iframe. They're "micro" because they're quite literally tiny single purpose utilities like a hackernews reader or old school guest book. It's mostly at this point something that scratches a personal itch. Making app development super simple and lightweight. Sort of like living GitHub gists. And trying to build a simpler, cleaner place to consume the web. Right now nothing more than a cool hack I'm sharing. Feedback obviously welcome. Cheers Asim https://bit.ly/3PhLbc7 August 29, 2023 at 12:42PM

Show HN: AI for Your Direct Email Marketing https://bit.ly/3YUpwtv

Show HN: AI for Your Direct Email Marketing https://bit.ly/3Pe687J August 29, 2023 at 11:34AM

Show HN: Toybox – A Laravel TALL starter kit for solopreneurs https://bit.ly/3YSa0OY

Show HN: Toybox – A Laravel TALL starter kit for solopreneurs Hey peeps! Here's a project I've been working on for the last two months. It initially started as trying to be a simplified boilerplate for Laravel, but I think it's gone a bit beyond that. With recent tooling releases in the Laravel ecosystem, there's a ton of exciting tools to work with, but it's either annoying to set it all up every time, or it's difficult to try and gather it all up for every piece you'll need for your SaaS. To that end, Toybox attempts to collate what is in my opinion the best of modern Laravel, and while being simple to start, run and launch with. This is how I also came up with the name - pick and choose all your favourite Laravel toys and see how quickly you can build products with it. I've never been a fan of Docker and similar tools. While I see their value, I've generally not had a good experience and it always felt like a waste of my time trying to debug infrastructure instead of writing application code. So on that front Toybox goes back to basics - it targets only one stack, and is made to be able to initialise its repository, provision the server it is currently on, and deploy itself from your local machine, all with Bash scripts. Lastly, I tried to include guidance and support for scaling beyond an MVP and Bash scripts: The README includes tons of recommendations for various services & tools for all manner of things you need for your SaaS. https://bit.ly/3EhD1u0 August 29, 2023 at 09:56AM

Monday 28 August 2023

Show HN: Speak in Gaelic to ChatGPT https://bit.ly/3YWOOaH

Show HN: Speak in Gaelic to ChatGPT https://bit.ly/3YWOOYf August 29, 2023 at 12:40AM

Show HN: Qramaank: Reuse and Reorganise internet content https://bit.ly/3EgsE9I

Show HN: Qramaank: Reuse and Reorganise internet content TLDR; It is a platform for you to create course like content by reusing existing content from Youtube, Github, Google Drive etc. I tried to create this for my personal use to make all the urls, document to be shown in an orderly fashion like a normal course do. But then tried to expand this to make it community driven and have functionality like cloning as well. I am still working on this, any suggestion would be good. https://bit.ly/3YRKFEK August 28, 2023 at 07:34AM

Show HN: Mail Organizer for Gmail https://bit.ly/3EbHleh

Show HN: Mail Organizer for Gmail This Google Apps Script labels emails accoding to the address the email was sent to. For example, you own the domain name "example.com", and you set up an email forwarding service such as Forward Email or ImprovMX to relay all emails sent to "*@relay.example.com" to your Gmail account. The script will label your emails according to a set of rules. For example: - "hello@relay.example.com" will be labeled "hello" - "hello-world@relay.example.com" will be labeled "hello" and "world" - "hello.world@relay.example.com" will be labeled "hello/world" ("world" as a sublabel of "hello") - "hello.world-yo.wassup@relay.example.com" will be labeled "hello/world" and "yo/wassup" https://bit.ly/3PfpQjq August 28, 2023 at 07:05AM

Show HN: Track your email is the key https://bit.ly/3OS5ifq

Show HN: Track your email is the key People don't ignore you on purpose, most of the time we are just trying to survive will all the demands we have. Track your proposal And act accordingly: send a follow-up if not read, send a follow-up if read but ignored, and be prompt to call if emails has been read multiple times https://bit.ly/3qTGKdW August 28, 2023 at 09:27AM

Show HN: FlagPalette – Flag Color Codes https://bit.ly/3EdUYcH

Show HN: FlagPalette – Flag Color Codes https://bit.ly/45LgUHV August 28, 2023 at 09:16AM

Show HN: MoodMinder – Swift Anger Regulation for Better Emotional Well-Being https://bit.ly/3ONBGQm

Show HN: MoodMinder – Swift Anger Regulation for Better Emotional Well-Being Hey Hacker News community! We're excited to showcase MoodMinder, a mental health app MVP that empowers individuals to swiftly regulate anger and enhance emotional well-being. MoodMinder was born out of a desire to provide quick anger regulation solutions for busy individuals. Unique Features: Rapid Mood Identification: Identify anger triggers and tension levels swiftly. Instant Personalized meditations: Receive tailored meditations for immediate anger control. Cognitive Reappraisal: Shift perspectives to defuse triggers in real-time. Quick Interactive Games: Engage in games designed for anger regulation in just minutes. As an MVP, we're seeking insights from the Hacker News community to shape our app's development. Your feedback is pivotal. Thank you for being part of our journey! https://bit.ly/3YWPkoT August 27, 2023 at 05:12PM

Sunday 27 August 2023

Show HN: Hermes – SMM backdoor and client for usermode privilege escalation https://bit.ly/3svClOY

Show HN: Hermes – SMM backdoor and client for usermode privilege escalation Hermes is an open source system management mode backdoor which allows a user mode application to elevate its own privileges and interact with memory without any direct access at smm level. https://bit.ly/3suxMo6 August 27, 2023 at 05:56PM

Show HN: RISC-V Linux Terminal emulated via WASM https://bit.ly/3EbtRiC

Show HN: RISC-V Linux Terminal emulated via WASM Weekend creation: A Linux terminal on top of a RISC-V emulator running in the browser via WebAssembly, powered by the Cartesi Machine. Check cool commands to experiment in the project page https://bit.ly/3EgsWxc https://bit.ly/3EfoYVK August 27, 2023 at 08:51PM

Show HN: Bicycle – A Database Tool (Rust, gRPC, RocksDB) https://bit.ly/45Mur28

Show HN: Bicycle – A Database Tool (Rust, gRPC, RocksDB) https://bit.ly/45NDShy August 27, 2023 at 05:54PM

Show HN: Graphweaver – Instant GraphQL API on Postgres, MySQL, SQLite and More https://bit.ly/47QpiYp

Show HN: Graphweaver – Instant GraphQL API on Postgres, MySQL, SQLite and More Graphweaver is an open-source GraphQL API Server that can connect many data sources to create a single API. Create a headless CMS, API Gateway, BaaS or use it as a BFF. https://bit.ly/45DnwZ6 August 27, 2023 at 12:00PM

Show HN: Customizable terminal UI for monitoring weather, app uptime, and more https://bit.ly/3stt1en

Show HN: Customizable terminal UI for monitoring weather, app uptime, and more https://bit.ly/45Of4Gr August 27, 2023 at 10:20AM

Saturday 26 August 2023

Show HN: Investor Radar, the Ultimate Database of Investors for Your Startup https://bit.ly/3QSeymv

Show HN: Investor Radar, the Ultimate Database of Investors for Your Startup https://bit.ly/3OQQZrp August 26, 2023 at 11:25PM

Show HN: Pilot your motorcycle across increasingly wild roller coaster geometry https://bit.ly/47S49xk

Show HN: Pilot your motorcycle across increasingly wild roller coaster geometry I began this project in the 2010s to teach myself Unity and C#. Each piece of 3D geometry was made inside of the Unity IDE with the free ProBuilder suite of simple modeling tools. Should work in the browser on both phones and personal computers! https://bit.ly/44qulvU August 26, 2023 at 01:17PM

Show HN: Pezzo – Open-Source LLMOps Plaform Tailored for Developers https://bit.ly/3OMgGtg

Show HN: Pezzo – Open-Source LLMOps Plaform Tailored for Developers Hello HN, Introducing Pezzo – a developer-centric LLMOps platform designed to streamline Generative AI integrations. As Generative AI gains traction, we've observed a gap in tools catering to product teams and developers. Most are oriented toward ML/AI experts. That's why we created Pezzo - fully open-source under Apache 2.0. GitHub: https://bit.ly/3YTbhoL Why Pezzo? - Centralized Prompt Management: Think email templates but for prompts. Design, test, and publish prompts without undergoing an extensive release cycle. - Observability & Insights: Comprehensive dashboards that offer insights into cost metrics, AI provider expenses, success/error rates, and anomaly detection. Be in control of your AI operations. - Efficient Request Caching: Out-of-the-box caching reduces costs and redundancy. Especially valuable during local development with repetitive LLM requests. Future Roadmap: We're working on issue auto-suggestions, continuous prompt improvements, cost optimization, and security threat flagging, among other features. If you'd like to try it out, we've made our Cloud version available: https://bit.ly/3QWieU9 . Note: It runs the identical code as our open-source version! Additionally, we're always looking for contributors, so if you're interested - we'd love to hear from you. https://bit.ly/3YTbhoL August 26, 2023 at 03:58PM

Show HN: Our latest AI creation, all feedback and discussions welcome https://bit.ly/3suUsVj

Show HN: Our latest AI creation, all feedback and discussions welcome Please Check out our Latest AI content generation Tool LogicBalls AI. Please give your feedback and suggestions. https://bit.ly/3QUoLP8 August 26, 2023 at 10:17AM

Show HN: Email Enricher, a Free, Offline Clearbit Alternative https://bit.ly/47RPMZU

Show HN: Email Enricher, a Free, Offline Clearbit Alternative At my prior employer, we got Slack alerts for big company sign-ups I wanted the same for my new startup ( https://bit.ly/3stj0xU ) but quickly found that Clearbit would cost us $7,000 / mo... Instead, I made this free npm package `email-enricher` the returns if an email is likely from a Fortune 1000 company Hope it's useful to someone else! https://bit.ly/3Ek6nYp August 25, 2023 at 10:21PM

Show HN: Display primary keys the way humans and developers prefer https://bit.ly/3OSUWvP

Show HN: Display primary keys the way humans and developers prefer https://bit.ly/3Efzjkk August 26, 2023 at 10:50AM

Friday 25 August 2023

Show HN: AhaApple – AI Idea Generator. One Click, Many Creative and Novel Ideas https://bit.ly/3qM0T5I

Show HN: AhaApple – AI Idea Generator. One Click, Many Creative and Novel Ideas AhaApple. AI Idea Generator. One click, Many Creative and Novel Ideas. Leveraging AI, many brainstorming techniques, and many innovative techniques, AhaApple make it easy for you to gain more inspirations and ideas. https://bit.ly/3KWOqmI August 26, 2023 at 05:52AM

Show HN: Full list of ChatGPT Plugins and stats https://bit.ly/45Bf1h0

Show HN: Full list of ChatGPT Plugins and stats https://bit.ly/3OPsydX August 25, 2023 at 04:42PM

Show HN: Release AI – Talk to Your Infrastructure https://bit.ly/47NVRWT

Show HN: Release AI – Talk to Your Infrastructure Hello, Hacker News! I'm David, cofounder of Release (YCW20). Introducing Release AI, a tool designed to empower users with instant access to DevOps expertise, all without monopolizing the valuable time of our experts. Developed with the developer and engineer community in mind, Release AI takes the power of OpenAI's cutting-edge GPT-4 public LLM and augments it with DevOps knowledge. In its initial phase, Release AI offers "read-only" access to both AWS and Kubernetes. This means you can engage in insightful conversations with your AWS account and K8s infrastructure effortlessly. Looking ahead, our roadmap includes plans to integrate more tools for commonly used systems. This will enable you to automate an even broader array of your daily tasks. If you would like more info you can check-out our launch YC (it has more details, screen casts): https://bit.ly/3ssoE3k... Our quickstart guide: https://bit.ly/47LzUb7 Signup and use it: https://bit.ly/3OO3GmZ Please give it a try! We would love your feedback as we are enhancing Release AI, reach out to us with any feature requests or crazy ideas that Release AI could do for you. Feel free to email me at david@release.com or leave a comment, looking forward to chatting with you. Join the conversation in our Slack community and discover the future of DevOps with Release AI! https://bit.ly/3qRdMeI August 25, 2023 at 05:20PM

Show HN: Budget Zen – Simple, Encrypted Budgets and Expenses https://bit.ly/3PdPiGa

Show HN: Budget Zen – Simple, Encrypted Budgets and Expenses https://bit.ly/3EbfDOz August 25, 2023 at 10:27AM

Show HN: JSON Wrapper for React Native https://bit.ly/3YRCF6L

Show HN: JSON Wrapper for React Native https://bit.ly/3Kz6PpM August 25, 2023 at 06:26AM

Show HN: A simple web app to combat phone addiction https://bit.ly/3EaYzbt

Show HN: A simple web app to combat phone addiction When I'm stuck on coding something, I find myself reaching for my phone even if I don't have any particular reason to do so. Inspired by Calm's DoNothingFor2Minutes.com which launched on HN 13 years ago [1], I made this simple webapp to see if my friends and I could go an hour without touching our phones. It is surprisingly difficult. According to a 2022 survey [2], the average US adult picks up their phone 352 times per day, or approximately once every 2m43s while they're awake. On browsers that support it (iOS 16.4+, most versions of Android Chrome), it uses the Screen Wake Lock API [3] to keep the page open, and falls back to nosleep.js [4] otherwise. From testing on my iPhone 14 Pro Max running iOS 16.6, battery life only went down 3 or 4 percentage points after an hour with the wake lock. Made this as a web app as a quick demo to be compatible across all mobile devices. As an app, we can probably save more on battery + not have the screen on. One caveat is that on iOS this will actually increase your Screen Time (although hopefully reduce your other category usage). I currently only track time on page through Google Analytics 4. No other calls are made to a server, although if we actually wanted to verify that you kept the page open vs. javascript/inspector-system clock-fu, we could add a verified mode that pings the server every X minutes. As a PWA, possibly due to an iOS/Mobile Safari quirk/bug [5], neither wake lock nor nosleep.js appear to work . [1] https://bit.ly/3YRNu8N [2] https://bit.ly/3Ec0k8p [3] https://mzl.la/3v65rTX... [4] https://bit.ly/3EdhaDU [5] https://bit.ly/3QQl5y3 https://bit.ly/3QScL0E August 24, 2023 at 09:45PM

Thursday 24 August 2023

Show HN: Collie – A minimal RSS reader just for you https://bit.ly/45mvdTn

Show HN: Collie – A minimal RSS reader just for you Collie is a minimal RSS feed reader application running on your desktop. With Collie, you can subscribe to multiple RSS/Atom feeds to organize your own news feed, receive a real-time notification when a new item is added to the subscribed feed, and save the items to read again or later. All you need is a local machine and the Internet. No virtual machine, no cloud infrastructures, no always-on database, and no account registration with privacy information required. I've been getting tech news from HackerNews, Lobsters, etc. on Twitter (It's X now, but I'll keep calling it Twitter anyway), but many of them have been terminated due to changes in Twitter's API policy. I went from place to place: Bluesky, Mastodon, Slack, and newsletter. However, I couldn't settle anywhere. The social media services such as Bluesky and Mastodon had too many unnecessary features as news feed. Slack RSS was good to get the news in real-time, but the notifications mixed with other workspaces overwhelmed me. The newsletters gave me a lot of high-quality information, but not in real-time. Then, I remembered Miniflux, the "minimalist and opinionated feed reader" that I had used past. This is the best option for my goal, but I had to pay for the hosted version or keep running docker machine on my local computer which did not have enough resources. Additionally, I didn't need a system that maintains multi-user sessions. Eventually, I had no choice but to create my own application, and that's why I made Collie, the minimal RSS reader just for me. https://bit.ly/45oD2YY August 25, 2023 at 06:28AM

Show HN: Gov.uk Vue, a Vue component library based on Gov.uk https://bit.ly/3P82P1S

Show HN: Gov.uk Vue, a Vue component library based on Gov.uk Hi everyone, TLDR: I've just released an alpha version of GOV.UK Vue, an easy to use, accessible component library for Vue 3, and I'd love to hear any feedback you have. This post links to the GitHub repo but there's full documentation on https://bit.ly/44ocrK7 I'm in the UK and our government is very bad at a lot of things, but it's very good at building digital services - there have been discussions praising how easy to use GOV.UK is in the past: https://bit.ly/3PbBxrx The frontend framework they've built, the GOV.UK Design System, is great, and I use it all the time in my day job. But no-one had built a Vue library for it yet, so I decided to do it. My aim is for it to be the most accessible Vue component library available - the Design System components already have brilliant accessibility, so all I have to do is not mess it up when porting it to Vue, and I think I've done OK (but let me know if you find any bugs) At the moment my focus has been on implementing the components in the Design System, so GOV.UK Vue doesn't include things like modals or autocomplete, but I'm planning to build a companion library which includes those kinds of components. Let me know if you'd be interested in that. Please check it out and let me know what you think! https://bit.ly/3qHeBXD August 24, 2023 at 02:42PM

Show HN: Web App with GUI for AutoML on Tabular Data https://bit.ly/3PcZTBe

Show HN: Web App with GUI for AutoML on Tabular Data https://bit.ly/47oEGv4 August 24, 2023 at 11:40AM

Wednesday 23 August 2023

Show HN: Automate complicated manual business processes https://bit.ly/45dhUVr

Show HN: Automate complicated manual business processes https://bit.ly/45BaUC9 August 24, 2023 at 05:57AM

Show HN: How the result of the Stack Overflow survey changes over the years https://bit.ly/3E7oBwr

Show HN: How the result of the Stack Overflow survey changes over the years https://bit.ly/3sfRh3t August 24, 2023 at 05:51AM

Show HN: E-Ink Powered UK Rail Departure Board Using Badger 2040W https://bit.ly/47HWIZn

Show HN: E-Ink Powered UK Rail Departure Board Using Badger 2040W Hey HN community, I've recently embarked on a tinkering project that merges the versatility of the Badger 2040W with the practicality of an E-ink display. Inspired by the UK Rail departure boards, I've created an E-ink version that updates in real-time with departure information. Would love to hear your thoughts, suggestions, or similar projects you've come across! https://bit.ly/47H7bEr August 23, 2023 at 08:49PM

Show HN: Chat with GPT about medical issues, get answers from medical literature https://bit.ly/45lLSGG

Show HN: Chat with GPT about medical issues, get answers from medical literature Clint is an open-sourced medical information lookup and reasoning tool. Clint enables a user to have an interactive dialogue about medical conditions, symptoms, or simply to ask medical questions. Clint helps connect regular health concerns with complex medical information. It does this by converting colloquial language into medical terms, gathering and understanding information from medical resources, and presenting this information back to the user in an easy-to-understand way. One of the key features of Clint is that its processing is local. It's served using GitHub pages and utilizes the user's OpenAI API key to make requests to directly to GPT. All processing, except for that done by the LLM, happens in the user's browser. I recently had a need to lookup detailed medical information and found myself spending a lot of time translating my understanding into the medical domain, then again trying to comprehend the medical terms. That gave me the idea that this could be a task for an LLM. The result is Clint. It's a proof-of-concept. I currently have no further plans for the tool. If it is useful to you as-is, great! If it is useful only to help share some ideas, that's fine too. https://bit.ly/45y61cE August 24, 2023 at 12:15AM

Show HN: Flintable – Fixable ESLint rules Playground https://bit.ly/3KP4VkA

Show HN: Flintable – Fixable ESLint rules Playground Hi community! I am glad to introduce to you my latest project! What? Flintable is a playground for experimenting lint rules, focusing on fixable layout and suggestions rules. I initially focused on ESLint, the most popular JavaScript linter. Flintable allows adding your code and regularly testing it with individual rules or custom configurations, composing your own configuration file. How? I developed Flintable using the PHP Laravel framework for the server side and the Vue framework linking them with Inertia JS, accompanied by Tailwind CSS for the client side. Laravel Horizon manages the queues and jobs, while Laravel Websockets and Laravel Echo enable the dialogue between the queue and the client. I used JSON Schema via AJS and OPIS to manipulate ESLint rule schemas and vue-codemirror for the code editor within the tool. Why? Working on the same code as a team can pose challenges, especially in terms of code conventions and working environments. That's why I created Flintable, which long-term goal is to allow everyone to configure their environment to the fullest without impacting others. Thus, developers can collaborate more effectively while respecting each other's workspaces. The short-term objective of Flintable is to simplify the understanding, the discovery and manipulation of rules with ease. How it works? Select a rule in the list of rules on your right. Activate the rule. Determine some options or not. And lint with this rule or with the configuration you made [ by activating other rules ]. When you're satisfied, download your configuration file. You can also try the rules on your own code by pasting it in the code editor. Next? - Implementing more plugins, more linters, more frameworks, more languages? - Creating custom rules sought by the community? - Storing configuration files online to facilitate reuse on other projects? - Launching lint of local and remote code via a command line throughout the development process, using version control tools like Git? I am thrilled about sharing my newborn project with you and would love to hear your feedback. See you in the comments. I don't know if I can share a post from my blog here about the Flintable journey, so ask me if you want it, and I will share the link in response. https://bit.ly/3YMdqmg August 23, 2023 at 02:35PM

Show HN: Fast vector similarity using Rust and Python https://bit.ly/3Pbhsla

Show HN: Fast vector similarity using Rust and Python I recently found myself computing the similarity between lots of very high dimensional vectors (i.e., sentence embedding vectors from LLMs), and I wanted to try some more powerful measures of similarity/dependency than just Cosine similarity, which seems to be the default for everything nowadays because of its computational efficiency. There are many other more involved measures that can detect more subtle relationships, but the problem is that some of them are quite slow to compute, especially if you're trying to do it in Python. For my favorite measure of statistical dependency, Hoeffding's D, that's true even if you use Numpy. Since I recently learned Rust and wanted to learn how to make Python packages using Rust, I put together this new library that I call Fast Vector Similarity. I was blown away by the performance of Rust and the quality of the tooling while making this. And even though it required a lot of fussing with Github Actions, I was also really impressed with just how easy it was to make a Python library using Rust that could be automatically compiled into wheels for every combination of platform (Linux, Windows, Mac) and Python Version (3.8 through 3.11) and uploaded to PyPi, all triggered by a commit to the repo and handled by Github's servers-- and all for free if you're working on a public repo! Anyway, this library can easily be installed to try out using `pip install fast_vector_similarity`, and you can see some simple demo Python code in the readme to show how to use it. Aside from exposing some very high performance implementations of some very nice similarity measures, I also included the ability to get robust estimates of these measures using the Bootstrap method. Basically, if you have two very high dimensional vectors, instead of using the entire vector to measure similarity, you can take the same random subset of indices from both vectors and compute the similarity of just those elements. Then you repeat the process hundreds or thousands of times and look at the robust average (i.e., throw away the results outside the 25th percentile to 75th percentile and average the remaining ones, to reduce the impact of outliers) and standard deviation of the results. Obviously this is very demanding of performance, but it's still reasonable if you're not trying to compute it for too many vectors. Everything is designed to fully saturate the performance of multi-core machines by extensive use of broadcasting/vectorization and the use of paralell processing via the Rayon library. I was really impressed with how easy and low-overhead it is to make highly parallelized code in Rust, especially compared to coming from Python, where you have to jump through a lot of hoops to use multiprocessing and there is a ton of overhead. Anyway, please let me know what you think. I'm looking to add more measures of similarity if I can find ones that can be efficiently computed (I already gave up on including HSIC because I couldn't get it to go fast enough, even using BLAS/LAPACK). https://bit.ly/3QY7Lrc August 23, 2023 at 01:34PM

Show HN: Make sense of all your files, links and messages in the cloud https://bit.ly/44haVJH

Show HN: Make sense of all your files, links and messages in the cloud Hello everyone! Like most of you, we also use a lot of tools and have all our files, links and messages scattered over all those different tools in the cloud. Which often leads to not knowing where that one file is that you need. At best this means you waste 5 minutes looking for a file or link and at worst it means that valuable knowledge gets lost in a company. That’s why we created a place for you to connect all your tools, organize your files, and allow you to search across all your apps. Right now, you can connect up to 8 different tools, but there are a lot more to come! Give it a try and let me know your feedback! https://bit.ly/3QTKp6b August 23, 2023 at 01:31PM

Show HN: Pip install inference, open source computer vision deployment https://bit.ly/3qEJxb1

Show HN: Pip install inference, open source computer vision deployment Deploying vision models is time consuming and tedious. Setting up dependencies. Fixing conflicts. Configuring TRT acceleration. Flashing (and re-flashing) NVIDIA Jetsons. A streamlined, developer-friendly solution for inference is needed. We, the Roboflow team, have been hard at work open sourcing Inference, an open source vision deployment solution. Our solution is designed with developers in mind, offering a HTTP-based interface. Run models on your hardware without having to write architecture-specific inference code. Here's a demo showing how to go from a model to GPU inference on a video of a football game in ~10 minutes: https://www.youtube.com/watch?v=at-yuwIMiN4 Inference powers millions of daily API calls for global sports broadcasts, one of the world’s largest railways, a leading electric car manufacturer, and multiple other Fortune 500 companies, along with countless hackers’ hobby and research projects. Inference works in Docker and supports CPU (ARM and x86), NVIDIA GPU, and TRT. Inference manages dependencies and the environment. All you need to do is make HTTP requests to the server. YOLOv5, YOLOv8, YOLACT, CLIP, SAM, and other popular vision models are supported (some models need to be hosted on Roboflow first, see the docs; we're working on bring your own model weights!). Try it out and tell us what you think! https://bit.ly/45lZl1g August 23, 2023 at 12:04PM

Show HN: To mute words on Twitter in batches, I created a browser extension https://bit.ly/45qFmPi

Show HN: To mute words on Twitter in batches, I created a browser extension Hello HN community :) For a while now I've been watching my Twitter feed fill up with more and more crap. The fact that it's now possible to monetise your tweets has made things even crappier. At the same time, adding words to mute is a pain. First you have to find the option, buried deep in Twitter's settings, and then you have to add them one by one. So I came up with the idea of writing a little browser extension that lets you add lists of muted words, which can come from more or less anywhere, as long as they're in a certain format (a multi-line text file or a JSON array). The extension doesn't collect any data, you don't need an account to use it, and you can store your lists anywhere (although I'd recommend Github gist or Pastebin). To be honest, I made this mainly as an exercise to learn how a browser extension works and how to make one, but if it's useful to people, that's great! Feel free to let me know what you think and give it a try. If there's ever an audience for it, I'm thinking of taking it further by adding lists of people to mute, extracting your existing list of muted words from Twitter, etc.If you have any other ideas for development, I'd love to hear from you. https://bit.ly/3sngJEi August 23, 2023 at 12:43PM

Tuesday 22 August 2023

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://bit.ly/45Hj2k7

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://bit.ly/3sgcbPY August 23, 2023 at 04:56AM

Show HN: Open-Source Chat AI Platform with Custom Knowledge https://bit.ly/3sv6f5G

Show HN: Open-Source Chat AI Platform with Custom Knowledge https://bit.ly/44gC0N7 August 22, 2023 at 05:08PM

Show HN: UpTrain (YC W23) – open-source tool to evaluate LLM response quality https://bit.ly/3YRzqfG

Show HN: UpTrain (YC W23) – open-source tool to evaluate LLM response quality Hello, we are Shikha and Sourabh, founders of UpTrain(YC W23) - an open-source tool to evaluate the performance of your LLM applications on aspects such as correctness, tonality, hallucination, fluency, etc. The Problem: Unlike traditional Machine learning or Deep learning models where we always have a unique Ground Truth and can define metrics like Precision, Recall, accuracy, etc. to quantify the model’s performance, LLMs are trickier and it is very difficult to estimate if their response is correct or not. If you are using GPT-4 to write a recruitment email, there is no unique correct email to do a word-to-word comparison against. As you build an LLM application, you want to compare it against different model providers, prompt configurations, etc., and figure out the best working combination. Instead of manually skimming through a couple of model responses, you want to run them through hundreds of test cases, aggregate their scores, and make an informed decision. Additionally, as your application generates responses for real user queries, you don’t want to wait for them to complain about the model inaccuracy, instead, you want to monitor the model’s performance over time and get alerted in case of any drifts. Again, at the core of it, you want a tool to evaluate the quality of your LLM response and assign quantitative scores. The Solution: To solve this, we are building UpTrain which has a set of evaluation metrics so that you can know when your application is going wrong. These metrics include traditional NLP metrics like Rogue, Bleu, etc., embeddings similarity metrics as well as model grading scores i.e. where we use LLMs to evaluate different aspects of your response. A few of these evaluation metrics include: 1. Response Relevancy: Measures if the response contains any irrelevant information 2. Response Completeness: Measures if the response answers all aspects of the given question 3. Factual Accuracy: Measures hallucinations i.e. if the response has any made-up information or not with respect to the provided context 4. Retrieved Context Quality: Measures if the retrieved context has sufficient information to answer the given question 5. Response Tonality: Measures if the response aligns with a specific persona or desired tone etc. We have designed workflows so that you can easily add your testing dataset, configure which checks you want to run (you can also define custom checks suitable for your use case) and conveniently access the results via Streamlit dashboards. UpTrain also has experimentation capabilities where you can specify different prompt variations and models to test across and use these quantitative checks to find the best configuration for your application. You can also use UpTrain to monitor your application’s performance and find avenues for improvement. We integrate directly with your databases (BigQuery, Postgres, MongoDB, etc.) and can run daily evaluations. We’ve launched the tool under an Apache 2.0 license to make it easy for everyone to integrate it into their LLM workflows. Additionally, we also provide managed service (with a free trial) where you can run LLM evaluations via an API request or through UpTrain testing console. We would love for you to try it out and give your feedback. Links: Demo: https://bit.ly/3QOYUs4 Github repo: https://bit.ly/3JeFnNP Create an account (free): https://bit.ly/3qzN0aS UpTrain testing console (need an account): https://bit.ly/45AkMLR Website: https://bit.ly/3QMXzlq https://bit.ly/3QOYUs4 August 22, 2023 at 03:08PM

Show HN: Visual DB – Airtable alternative for your own database https://bit.ly/3YH5J0J

Show HN: Visual DB – Airtable alternative for your own database Visual DB combines the familiar interface of a spreadsheet with the robustness and central management of a relational database. Spreadsheets are a popular choice for storing tabular data due to their familiar, row-by-column interface and ease of use. However, they can quickly become unwieldy as data grows. Spreadsheets aren't ideal for large-scale structured data or maintaining data integrity. When individuals copy the spreadsheet and introduce inconsistent updates, it leads to the problem known as "multiple versions of the truth." Visual DB provides a solution. It maintains the familiar interface of spreadsheets, but each row is backed by a database record. Updates sync to a centralized database, ensuring data consistency, scalability, and integrity. Visual DB performs double duty: In addition to providing a spreadsheet interface for updating data, it also has features traditionally seen in business intelligence reporting tools, such as grouping, aggregation, sorting and filtering. Visual DB is very good at helping you locate the record you want to update. It has advanced filtering that supports combining AND/OR conditions. It also has full-text filtering that instantly updates the screen as you type. Visual DB can display up to 100,000 records at a time. If your database table has more rows than that, you can use query parameters to let the user fetch a subset of the records (up to 100K) to the client. To enable this, Visual DB has a query builder and supports parameter prompting. Relational databases frequently function as bridges between various business applications. However, if a database is proprietary and is behind the firewall of another company, its effectiveness as an integration hub is compromised. Visual DB allows users to bring their own databases, ensuring they have complete control and ownership. This ensures interoperability with multiple applications beyond just Visual DB. This flexibility distinguishes Visual DB from competitors like Airtable. Here are the main features of Visual DB: - BYOD (Bring Your Own Database). - Your database can be hosted in any cloud provider, including Azure, AWS and Google cloud. - Supports MySQL, PostgreSQL, Oracle, SQL Server. - No code. Build sheets and forms with zero coding or SQL knowledge. - Role-based access control: Decide who can add/remove columns and who can only enter/update data. - Full-text filtering that instantly updates the screen as you type. - Advanced filtering that supports combining AND/OR conditions. - Grouping with unlimited levels of nesting. - Unlimited number of records per table (compare to 50,000 in Airtable). - Use query parameters to determine which subset of rows (out of millions) to display. - Display columns from lookup tables, not just the main table. - Instant scrolling of up to 100,000 rows. For more information visit https://bit.ly/3YH5JxL or go to https://bit.ly/45gtorp to start using Visual DB right away. https://bit.ly/3YH5JxL August 22, 2023 at 03:15PM

Show HN: Ploter – the all-in-one reader for learning https://bit.ly/45kfG6F

Show HN: Ploter – the all-in-one reader for learning Ploter is an all-in-one reader for your ebooks, audiobooks, pdfs, and more. Take highlights and annotations across all formats (including audio) and have these synced to your favourite note-taking app. https://bit.ly/47JXwg6 August 22, 2023 at 02:48PM

Show HN: Breaklist – A Morning Briefing Printed on a Tiny Thermal Receipt https://bit.ly/3qHdqY8

Show HN: Breaklist – A Morning Briefing Printed on a Tiny Thermal Receipt I built Breaklist to organize the essential info I need to start my day. It generates a personalized morning briefing, optimized for thermal printers. The morning report currently includes: Task list Reminders Weather forecast Summary of latest top articles on Hacker News The result is a tidy, receipt-sized report that I can print and take on-the-go each morning. https://bit.ly/3qwNZbS August 22, 2023 at 12:58PM

Show HN: Speleomorph, Shapeshifting Puzzle Metroidvania https://bit.ly/45idgpf

Show HN: Speleomorph, Shapeshifting Puzzle Metroidvania This was my entry for a Metroidvania Month game jam last year. I like how Metroidvanias make you rethink movement as the game goes on, and since I didn't want to design combat I focused on that. But I didn't want the different mechanics to be objects you pick up. The theme for the jam was "shapeshifting", which suggested the unusual mechanic seen here. Fortunately I'd forgotten about Snakebird or I might not have been bold enough to make the gravity+snake parts so prominent. And in the year since this came out, there have been at least three cool puzzle games nearby in design space: - Tetronimeow https://bit.ly/45k4eIn has a heavy focus on rotation (which I skipped to avoid confusion), it gets much more Metroidvania mileage out of the central idea - Growmi https://bit.ly/3YRBrZ9 does a great job building mechanics out of the snake+gravity idea - The Plumber Thing https://bit.ly/45hqgLS If this looks familiar, I did post a Show HN last year, but dang invited me to re-submit it. I kept putting it off in hopes I could make a big splash when launching a new version: I have some ideas for touchscreens (currently keyboard only) and for an earlier game with more restricted abilities (no free transformation, then swapping with just one previous shape). But it's looking unlikely that I'll revisit it. https://bit.ly/3PDHlIY August 22, 2023 at 04:11AM

Show HN: Github20k – Learn how to grow your open-source repository https://bit.ly/3sgTWtH

Show HN: Github20k – Learn how to grow your open-source repository Weekly newsletter on how to grow your GitHub repository based on actual use cases we have used over the years. https://bit.ly/3YM0a0V August 22, 2023 at 09:11AM

Monday 21 August 2023

Show HN: Footage – Full-featured private video editor, 1.04 MB in size (iOS) https://bit.ly/3OBJrZq

Show HN: Footage – Full-featured private video editor, 1.04 MB in size (iOS) https://apple.co/3OMDWr9 August 21, 2023 at 04:06PM

Show HN: Kypso – copilot to manage and scale your teams' operations https://bit.ly/3P5GdPB

Show HN: Kypso – copilot to manage and scale your teams' operations https://bit.ly/3P5Du8Q August 21, 2023 at 02:29PM

Show HN: DocXReducer – C# lib for docx size reducing without losses https://bit.ly/45yRJs2

Show HN: DocXReducer – C# lib for docx size reducing without losses https://bit.ly/3sossTi August 21, 2023 at 01:34PM

Show HN: Simple honeypot checker for a new L2 by Coinbase https://bit.ly/3sizEAj

Show HN: Simple honeypot checker for a new L2 by Coinbase https://bit.ly/3P4KFOx August 21, 2023 at 11:11AM

Show HN: I'm Sending a Weekly PHP Community Newsletter https://bit.ly/45xYdra

Show HN: I'm Sending a Weekly PHP Community Newsletter https://bit.ly/3YH2Ooy August 21, 2023 at 08:46AM

Show HN: The Uncolouring Book https://bit.ly/3P2Td8C

Show HN: The Uncolouring Book https://bit.ly/3YF9kwh August 21, 2023 at 12:54PM

Sunday 20 August 2023

Show HN: Efficiently Query BigQuery and Snowflake from Postgres https://bit.ly/3smFDUD

Show HN: Efficiently Query BigQuery and Snowflake from Postgres https://bit.ly/45fgJF6 August 21, 2023 at 03:01AM

Show HN: Simple open-source tool for mocking using TS interfaces https://bit.ly/3sjzsAC

Show HN: Simple open-source tool for mocking using TS interfaces https://bit.ly/47Cgx4i August 20, 2023 at 09:53PM

Show HN: HTBL – A stupid way to write back ends in HTML https://bit.ly/3OIUjoH

Show HN: HTBL – A stupid way to write back ends in HTML https://bit.ly/44jiDDk August 20, 2023 at 08:05PM

Show HN: Talk to AI Models in Terminal https://bit.ly/3quhZoM

Show HN: Talk to AI Models in Terminal Hi everyone, nice to meet you and I am a newcomer of HN. I have made a binary tool Aih that could communicate with Bard, ChatGPT, Claude, and Llama(HuggingChat) from the terminal. https://bit.ly/3QMlNfN Since CAPTCHA challenges and bots detecting have become increasingly difficult, I've changed my strategy from hacking the APIs to simulating a real browser's action. The tool first takes the logged-in cookies of Google, ChatGPT, Claude, and HuggingChat accounts from the real Chrome browser, then it opens an invisible instance of Chromium for communication, then displays the answers in terminal. I think it's useful especially when I am researching some topics and need to compare answers of those AI models at the same time. Feel free to test and welcome provide feedback! https://bit.ly/3QMlNfN August 20, 2023 at 01:10PM

Show HN: Easy Sell AI – AI that sells for you on marketplace apps https://bit.ly/3qDbyzG

Show HN: Easy Sell AI – AI that sells for you on marketplace apps Hey Hacker News! I've developed Easy Sell AI to address the challenges I faced when I had to quickly sell items on platforms like Facebook Marketplace and OfferUp. Problem: 1. Constantly getting lowballed by potential buyers, and I just didn't know what I needed to say to get the price I wanted. 2. Spending hours negotiating with potential buyers, only to often get ghosted. 3. Encountering fake accounts and scammers, making the process even more tedious. Solution: Enter Easy Sell AI, an AI-powered tool that does all the selling for you on Marketplace Apps. With it: 1. The AI takes over negotiations, giving the perfect line to get you the price you deserve. 2. You're only notified when a genuine deal is on the table. 3. Set your preferences, like your minimum acceptable price and availability, and let Easy Sell AI manage the rest. Check it out and let me know your thoughts! https://bit.ly/3QMDcEV August 20, 2023 at 03:24PM

Show HN: AI transforms eating – healthier choices in your busy life https://bit.ly/3QN6W4C

Show HN: AI transforms eating – healthier choices in your busy life Upgrade eating habits with Eat Fix! Our custom AI fosters a healthier lifestyle in your busy schedule. Prioritize well-being, no compromises! Let Eat Fix be your guide to improved health and balanced eating. https://bit.ly/45yWRMF August 20, 2023 at 02:27PM

Show HN: Superfunctions – AI prompt templates as an API https://bit.ly/457z5aV

Show HN: Superfunctions – AI prompt templates as an API Hi HN, https://bit.ly/45j4rvi I'm working on a web app that allows Ai prompts to function as an API. I want to make it easier for developers to use Ai. I've found it painful to monitor, cache, and iterate on prompts. superfunctions.com is designed to be the simplest building block to create Ai powered apps and scripts. Simplest example I can think of: You want an api to convert human-named colors to hex You can write a prompt like: "convert to color, only output hex for css" and then you can call your prompt with https://bit.ly/45B9S8B and the response will contain: #0000FF Watch a short video intro: https://www.youtube.com/watch?v=KdO1TBUbRuA Login without needing an account: https://bit.ly/3sgEq14 I'm still sorting out a few bugs, but it's usable in it's current state. This is my first solo project, so I'm very open to feedback and suggestions. -Trent https://bit.ly/45B9TcF August 20, 2023 at 10:36AM

Saturday 19 August 2023

Show HN: Just intonation keyboard – play music without knowing music https://bit.ly/3KOBEq7

Show HN: Just intonation keyboard – play music without knowing music This is a keyboard in just intonation. It can play the notes a piano can. The big difference from a piano is that all the notes become consonant. You can play without knowing any music theory. Hit arbitrary notes with the rhythm you want, and the pitches will work. Not understanding the buttons is fine. Even rolling your elbow around your keyboard is fine. If you are a musician and press the wrong key while playing a song, it will still fit. It will sound like you made an intelligent, conscious choice to play another note, even though you know in your heart it was an accident. Beginner jazz musicians rejoice. It's not an AI making choices for you; it's just a very elegant interface. What makes this possible is several new discoveries in psychoacoustics about how harmony works. While a piano lays out notes in pitch space, this keyboard is able to lay out notes in consonance space. When you play random notes, they tend to be "close together" on the physical keyboard. Distance on the keyboard maps well to distance in consonance space, so those random notes are close together in consonance space and sound good together. According to Miles Davis, a "wrong" note becomes correct in the right context. If you try to play a wrong note, the purple buttons you press will automatically land you in the right context, even if you don't know what that context is yourself. So you can stumble your way through an improv and the keyboard will offer the right notes without needing you to think about it. Harmonic consonance of chords can be read directly off the numbers in the keyboard, which implies that these numbers are a good language to think about music with. It doesn't take years of training, just reading the rules. The subset of playable songs is different from a piano, which means that songs in your existing piano repertoire will snip off some notes. Hardware for thumb keys would fix this, so you could play your existing piano songs in full, plus other songs a piano can't play. I don't have such hardware so I haven't implemented this. The other way is to have two keyboards and a partner. The remaining issue is that there is no sheet music in just intonation. Unfortunately, I have had no success in finding piano sheet music in a common, interpretable format. So while I do have a converter from 12 equal temperament to just intonation, there are no input files to use it with... https://bit.ly/3qHeHOT August 19, 2023 at 11:49PM

Show HN: CatGPT - Expert answers to any cat-related questions https://bit.ly/45dzJDH

Show HN: CatGPT - Expert answers to any cat-related questions https://bit.ly/45BKhw6 August 19, 2023 at 03:44PM

Show HN: Semi-Autonomous LLM with a dev workstation https://bit.ly/44lG1js

Show HN: Semi-Autonomous LLM with a dev workstation https://bit.ly/3KML0md August 19, 2023 at 04:33PM

Show HN: Linguist, a translation browser extension https://bit.ly/3siuXX2

Show HN: Linguist, a translation browser extension Hey everyone, check the Linguist - you can translate texts offline - dictionary + history for learn languages - it is are hackable - you can enter code to use your own translation service https://bit.ly/45dss71 August 19, 2023 at 03:28PM

Show HN: Find simple open source bounties to solve and get paid https://bit.ly/45h9Anu

Show HN: Find simple open source bounties to solve and get paid https://bit.ly/3sirQyk August 19, 2023 at 04:54PM

Show HN: A simple, open-source Notion-like avatar generator https://bit.ly/45Bsq8y

Show HN: A simple, open-source Notion-like avatar generator https://bit.ly/3P3Nlfc August 19, 2023 at 01:32PM

Friday 18 August 2023

Show HN: A Mastodon bot that writes poems about AWS status updates https://bit.ly/3sboInM

Show HN: A Mastodon bot that writes poems about AWS status updates https://bit.ly/3P4hVFm August 19, 2023 at 04:18AM

Show HN: This project allows you to easily implement parallel training https://bit.ly/45tYyvz

Show HN: This project allows you to easily implement parallel training https://bit.ly/3KJ3OTu August 18, 2023 at 01:01PM

Show HN: Superlines.io – The all-in-one AI marketing solution https://bit.ly/45AZP3g

Show HN: Superlines.io – The all-in-one AI marketing solution Superlines is an all-in-one marketing solution that automates content creation, analysis, optimization, and testing - basically, it takes care of the daily grind for marketing teams. Core target group are marketers such as social media managers, copywriters, content marketers, or marketing directors looking to scale their marketing team's impact without increasing resources. Many AI tools are popping up all the time but Superlines is different as it covers all major marketing use cases in one platform rather than being only focused, eg. on text generation. Our most popular feature is our landing page optimizer, which analyzes landing page content and instantly creates improvements. Just provide a URL and rock on. Superlines lets marketers input their brand and business details to their Brand settings and Superlines uses this knowledge to customize it's output. We've just launched in AppSumo and gotten a ton of feedback. https://bit.ly/3KOe4d7 Check it out and just tell me what you think. https://bit.ly/45AZPAi August 18, 2023 at 12:44PM

Show HN: Pulsly – No-code newsfeed and notification widget for website https://bit.ly/45hElsK

Show HN: Pulsly – No-code newsfeed and notification widget for website https://bit.ly/3KHfmH2 August 18, 2023 at 10:43AM

Show HN: A website for remote workers to find Airbnb's with good Internet https://bit.ly/45ez456

Show HN: A website for remote workers to find Airbnb's with good Internet I created this website about a month ago to solve a problem I was facing myself as an aspiring digital nomad. It is very important to find an accommodation with fast and reliable Internet. I also specifically wanted places with Ethernet access to minimize latency as much as possible since I (and many others) use a VPN hosted back at home. The database is in its infancy but covers 11 countries so far. I realize the UX is very basic and a minimum viable product. I intend to have someone help me overhaul the design (with ReactJS perhaps) to make it mobile friendly and more appealing. https://bit.ly/45AA2si August 18, 2023 at 03:49PM

Show HN: An Open-Source Collaborative Database Development Tool https://bit.ly/47B59pi

Show HN: An Open-Source Collaborative Database Development Tool A couple of years ago, we had an interesting idea. When a development team within an organization consists of around 10 members or fewer, controlling the risks associated with database changes might be achieved through trust and real-time communication. However, as the team grows, the responsibilities within the team become more specialized. Imagine a scenario where different branches of the business exist, each with its own set of developers, team leads, testers, testing leads, DBAs, and more. Relying solely on traditional communication methods becomes increasingly challenging when it comes to managing change risks. Envision a platform where a change request goes through a sequence of checks: it's first reviewed by colleagues familiar with the business, then approved by the business lead, followed by scrutiny from the database lead, and finally assessed for security by the security lead. Does this approach effectively control the risk associated with that change when it's executed? In 2019, we embarked on building the first piece of this puzzle: ODC. Fast forward to today, after more than three years of development, ODC has evolved from a specialized developer tool designed for OceanBase (OB) into an enterprise-grade collaborative control platform, with plans to support multiple data sources. And today, we are thrilled to announce that we are open-sourcing our project. You can find the entire four-year code history on GitHub ( https://bit.ly/47zF1v1 ). We're excited to hear your thoughts on this concept and whether you identify any potential challenges or opportunities that lie ahead. Your insights will play a crucial role in shaping the future of this project. Looking forward to your feedback! https://bit.ly/47zF1v1 August 18, 2023 at 11:36AM

Show HN: Kantankanban – A CLI to track to-do's, custom lists, and more https://bit.ly/3YEsyC4

Show HN: Kantankanban – A CLI to track to-do's, custom lists, and more https://bit.ly/44e9tbg August 18, 2023 at 07:43AM

Thursday 17 August 2023

Show HN : Low code cloud document database https://bit.ly/3qzOrWI

Show HN : Low code cloud document database Low code cloud document database https://bit.ly/3P0pYTG August 17, 2023 at 11:13AM

Show HN: I resurrected one of the top dead Show HNs https://bit.ly/3qIU58O

Show HN: I resurrected one of the top dead Show HNs OneView was first posted to HN in 2017, but died sometime around late 2019. Using the web archive I cobbled together something that works. According to this[0], oneview is the #5 top dead show hn. [0] https://bit.ly/454ng5j... https://bit.ly/3DU5hT1 August 17, 2023 at 03:56PM

Show HN: Create your own Discover Weekly https://bit.ly/47zPFlq

Show HN: Create your own Discover Weekly Choose a few playlists to get new tracks from, and they'll be filtered out every Monday to a new playlist. Kind of like Discover Weekly, but you get to choose the music sources. Hope you enjoy, and I would love feedback! https://bit.ly/3OD9u2I August 17, 2023 at 03:47PM

Show HN: Interactive exercises for GNU grep, sed and awk https://bit.ly/3OHPQTa

Show HN: Interactive exercises for GNU grep, sed and awk Hello! For the past few months, I've been using a Python framework called Textual to create TUI apps for interactive exercises. Released the app for GNU awk earlier today, so thought I'd create a post here. If you already know how to manage Python packages, you can use the following command to get all the three apps: pip install grepexercises sedexercises awkexercises `pipx` should also work, but I haven't tested it. The GitHub repo has the source code as well as more detailed installation instructions. You can use alternative CLI tools to solve these exercises as well. For example, Perl instead of GNU awk or ripgrep instead of GNU grep and so on. Hope you find these TUI apps useful. I'd highly appreciate your feedback. Happy learning :) https://bit.ly/47F2xqj August 17, 2023 at 11:13AM

Show HN: Strich – Barcode scanning for web apps https://bit.ly/3EjM9OR

Show HN: Strich – Barcode scanning for web apps Hi, I'm Alex - the creator of STRICH ( https://bit.ly/3YI1mSX ), a barcode scanning library for web apps. Barcode scanning in web apps is nothing new. In my previous work experience, I've had the opportunity to use both high-end commercial offerings (e.g. Scandit) and OSS libraries like QuaggaJS or ZXing-JS in a wide range of customer projects, mainly in logistics. I became dissatisfied with both. The established commercial offerings had five- to six-figure license fees and the developer experience was not always optimal. The web browser as a platform also seemed not to be the main priority for these players. The open source libraries are essentially unmaintained and not suitable for commercial use due to the lack of support. Also the recognition performance is not enough for some cases - for a detailed comparison see https://bit.ly/3DZ3yvN Having dabbled a bit in Computer Vision topics before, and armed with an understanding of the market situation, I set out to build an alternative to fill the gap between the two worlds. After almost two years of on-and-off development and 6 months of piloting with a key customer, STRICH launched at beginning of this year. STRICH is built exclusively for web browsers running on smartphones. I believe the vast majority of barcode scanning apps are in-house line of business apps that benefit from distribution outside of app stores and a single codebase with abundant developer resources. Barcode scanning in web apps is efficient and avoids platform risk and unnecessary costs associated with developing and publishing native apps. https://bit.ly/3YI1mSX August 17, 2023 at 02:24PM

Show HN: Rules – Shortcuts Automation Based on Calendar Events https://bit.ly/3OCP0ak

Show HN: Rules – Shortcuts Automation Based on Calendar Events Read and thought once too often that "This would be trivial if Calendar Events were triggers for Personal Shortcuts Automations". So decided to create a Mac app for it. The app works similar to Rules in Mail: - Specify some conditions (e.g. Calendar is "Work", Location contains "zoom") - Choose shortcuts to run on events that meet the conditions - you can have multiple actions, each with a different offset and custom input Good to know: - The app can only trigger automations while your Mac is awake (missed actions can be triggered on wake up) - The free version offers full functionality, but is limited to a max of 2 rules. Pro is a one-time purchase - All your data stays on device + no ads or data collection I would appreciate any feedback, especially what automations you might use the app for https://apple.co/3OIjmYO August 17, 2023 at 09:53AM

Wednesday 16 August 2023

Show HN: Marqo – Vectorless Vector Search https://bit.ly/45vE9Wf

Show HN: Marqo – Vectorless Vector Search Marqo is an end-to-end vector search engine. It contains everything required to integrate vector search into an application in a single API. Here is a code snippet for a minimal example of vector search with Marqo: mq = marqo.Client() mq.create_index("my-first-index") mq.index("my-first-index").add_documents([{"title": "The Travels of Marco Polo"}]) results = mq.index("my-first-index").search(q="Marqo Polo") Why Marqo? Vector similarity alone is not enough for vector search. Vector search requires more than a vector database - it also requires machine learning (ML) deployment and management, preprocessing and transformations of inputs as well as the ability to modify search behavior without retraining a model. Marqo contains all these pieces, enabling developers to build vector search into their application with minimal effort. Why not X, Y, Z vector database? Vector databases are specialized components for vector similarity. They are “vectors in - vectors out”. They still require the production of vectors, management of the ML models, associated orchestration and processing of the inputs. Marqo makes this easy by being “documents in, documents out”. Preprocessing of text and images, embedding the content, storing meta-data and deployment of inference and storage is all taken care of by Marqo. We have been running Marqo for production workloads with both low-latency and large index requirements. Marqo features: - Low-latency (10’s ms - configuration dependent), large scale (10’s - 100’s M vectors). - Easily integrates with LLM’s and other generative AI - augmented generation using a knowledge base. - Pre-configured open source embedding models - SBERT, Huggingface, CLIP/OpenCLIP. - Pre-filtering and lexical search. - Multimodal model support - search text and/or images. - Custom models - load models fine tuned from your own data. - Ranking with document meta data - bias the similarity with properties like popularity. - Multi-term multi-modal queries - allows per query personalization and topic avoidance. - Multi-modal representations - search over documents that have both text and images. - GPU/CPU/ONNX/PyTorch inference support. See some examples here: Multimodal search: [1] https://bit.ly/3qx0jc1... Refining image quality and identifying unwanted content: [2] https://bit.ly/3P1iuQC... Question answering over transcripts of speech: [3] https://bit.ly/3OYUGMW Question and answering over technical documents and augmenting NPC's with a backstory: [4] https://bit.ly/3OYON2l... https://bit.ly/45tn3sb August 16, 2023 at 03:01PM

Show HN: Prompt-Compose.js Use Axioms and Compositions to Build Modular Prompts https://bit.ly/3YBZDia

Show HN: Prompt-Compose.js Use Axioms and Compositions to Build Modular Prompts This JS library provides basic axioms for building and managing GPT prompts. It helps you build small and reusable prompt components and then let you compose them together to build larger ones. https://bit.ly/44eWDtg August 16, 2023 at 01:19PM

Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2 https://bit.ly/3OYhGvH

Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2 https://bit.ly/47CNYDY August 16, 2023 at 04:05PM

Show HN: SpacetimeDB – The database that replaces your server https://bit.ly/3DZ439a

Show HN: SpacetimeDB – The database that replaces your server We just released our database, SpacetimeDB, on GitHub under the BSL 1.1 license. It converts to a free software license after a few years. The point of the database is that you upload application logic into the database as a WebAssembly stored procedure, so instead of clients connecting to a webserver they connect directly to the database. The database itself does authentication and you write your own authorization logic just like you would inside a webserver. We’ve developed our game, BitCraft ( https://bit.ly/3EidCAt ) entirely in this way. All of the game state is stored and synchronized with clients via SpacetimeDB, including player positions and movement. We also plan to allow you to horizontally scale your applications in two ways: 1. By having multiple databases that can send messages to each other (i.e. the actor model) 2. By having distributed databases which partition data over multiple machines, similarly to CockroachDB, although this approach would cause a commensurate increase in latency in accessing data Curious to hear your thoughts! https://bit.ly/47zPOVN https://bit.ly/47CYE5t August 16, 2023 at 02:48PM

Show HN: Yadget Synthetic Data Generation for Testing https://bit.ly/3qrLHe3

Show HN: Yadget Synthetic Data Generation for Testing Yadget is an honest-to-goodness SaaS tool designed to generate Synthetic Data for testing. You can produce realistic, non-identifiable datasets to help you test and validate your products. Ideal for sw developers for data testing and validation processes. Right now the only differentiator is the number of free rows that it can develop but there is a roadmap IF people use it. Is this a good approach or a chicken and egg problem that we have set for ourselves? https://bit.ly/452qExz August 16, 2023 at 11:57AM

Show HN: Static_str_ops: &'static str and non-const operations in Rust https://bit.ly/3QHgRZh

Show HN: Static_str_ops: &'static str and non-const operations in Rust It is often asked by Rust programmer that how to create `&'static str` in Rust with non-const operations at runtime, e.g., returns the result of `format!()` as `&'static str`, rather than `String`. The crate static_str_ops addressed this issue, by allocating a hash set under the hood, and return the reference as the result. Along with this crate, a set of utilities are provided, including `static_format!`, `static_concat!`, and `staticize_once!` which can be used to initialize static strings with the `call_once` semantic. https://bit.ly/45xTCoH August 16, 2023 at 06:11AM

Show HN: Repo with a list of 80 decent companies hiring remotely in Europe https://bit.ly/3KFXFaw

Show HN: Repo with a list of 80 decent companies hiring remotely in Europe Tech-stack included https://bit.ly/3KJUiQa August 16, 2023 at 11:09AM

Show HN: Wildcams from every region in the world to spot your favorite animals https://bit.ly/3E4Gc7X

Show HN: Wildcams from every region in the world to spot your favorite animals https://bit.ly/45dz6dq August 16, 2023 at 10:16AM

Show HN: List of public sites blocking ChatGPT Bot https://bit.ly/45vp9b6

Show HN: List of public sites blocking ChatGPT Bot Following on from this post ( https://bit.ly/3OuDmhy ), I was intrigued to find which big sites would follow suit, so I started collating a list of them. Interestingly, it's also now being included in codebases by default (like Mastodon). https://bit.ly/3qAraE8 August 16, 2023 at 08:10AM

Tuesday 15 August 2023

Show HN: Portfolio/Resume website driven by GPT https://bit.ly/3seSUhZ

Show HN: Portfolio/Resume website driven by GPT Decided to take a left turn in building a portfolio site for myself. So I fed ChatGPT my resume, came up with a prompt, and now will let ChatGPT be my advocate for my resume site. Github for the page: https://bit.ly/3Yzm9YQ https://bit.ly/47wwHMm August 15, 2023 at 02:22PM

Show HN: Servicer, pm2 alternative built on rust and systemd https://bit.ly/44bKuFx

Show HN: Servicer, pm2 alternative built on rust and systemd Servicer is a CLI to create and manage services on systemd. I have used pm2 in production and find it easy to use. However a lot of its functionality is specific to node.js, and I would prefer not to run my rust server as a fork of a node process. Systemd on the other hand has most of the things I need, but I found it cumbersome to use. There are a bunch of different commands and configurations- the .service file, systemctl to view status, journald to view logs which make systemd more complex to setup. I had to google for the a template and commands every time. Servicer abstracts this setup behind an easy to use CLI, for instance you can use `ser create index.js --interpreter node --enable --start` to create a `.service` file, enable it on boot and start it. Servicer will also help if you wish to write your own custom `.service` files. Run `ser edit foo --editor vi` to create a service file in Vim. Servicer will provide a starting template so you don't need to google it. There are additional utilities like `ser which index.js` to view the path of the service and unit file. ``` Paths for index.js.ser.service: +--------------+-----------------------------------------------------------+ | name | path | +--------------+-----------------------------------------------------------+ | Service file | /etc/systemd/system/index.js.ser.service | +--------------+-----------------------------------------------------------+ | Unit file | /org/freedesktop/systemd1/unit/index_2ejs_2eser_2eservice | +--------------+-----------------------------------------------------------+ ``` Servicer is daemonless and does not run in the background. It simply sets up systemd and gets out of the way. There are no forked services, everything is natively set up on systemd. You don't need to worry about resource consumption or servicer going down which will cause your app to stop. Do give it a spin and review the codebase. The code is open source and MIT licensed- https://bit.ly/3sdFinj https://bit.ly/3OYXOst August 15, 2023 at 12:34PM

Monday 14 August 2023

Show HN: LLM Connected with REST APIs https://bit.ly/3OWekcw

Show HN: LLM Connected with REST APIs Hey, folks here is a peek into Jujutsu. We at Poozle are working with hundreds of APIs and it has been always frustrating to 1. Search the API in the documentation or ask ChatGPT 2. Then copy it to the postman and understand/test the API 3. Generate code to integrate into the codebase We thought how about having all of this at one place. We currently fine-tuned LLM on public REST APIs to reduce hallucination and then combined it with ChatGPT and Postman. I look forward to feedback, feature requests and discussions! https://bit.ly/3QEwzEB August 14, 2023 at 11:32PM

Show HN: Command palette-style Git client https://bit.ly/3QJUGSB

Show HN: Command palette-style Git client https://bit.ly/448QYVq August 14, 2023 at 11:01PM

Show HN: AV1 Broadcasting from OBS https://bit.ly/47vto8g

Show HN: AV1 Broadcasting from OBS https://bit.ly/3DWZkFc August 14, 2023 at 03:29PM

Show HN: Little Rat – Chrome extension monitors network calls of all extensions https://bit.ly/3DTI0AH

Show HN: Little Rat – Chrome extension monitors network calls of all extensions Hi HN I needed a way to monitor network calls made by chrome extensions so I made a small extension. You can install it by dropping the zip or crx into the extensions page. It'll be on the chrome store whenever/if it gets through the review. Hopefully it's useful to others. https://bit.ly/3DRGrn0 https://twitter.com/dnak0v https://bit.ly/3DRGrn0 August 14, 2023 at 12:49PM

Show HN: I made a “ChatGPT for your website” too https://bit.ly/47sUQn9

Show HN: I made a “ChatGPT for your website” too https://bit.ly/3YAiwSl August 14, 2023 at 02:02PM

Show HN: A website chatbot that also uses APIs https://bit.ly/3qmNnp7

Show HN: A website chatbot that also uses APIs Hi! "Another chatbot for your content" you may ask? Not really! Let me explain. I have realized that there's an untapped potential for ChatGPT plugins: why leave them locked up in the OpenAI store? Let's embed them on websites or share using links! Let's make chatbots ~ do stuff ~, not just talk about what they know. That's how Chatwith was born. It is a chat widget, it scrapes your website, knowledge page, notion etc - but more importantly, it also understands your API. It can interact with that API on your or your visitors' behalf. Some use cases & ideas: - Shopify bot - ask it for order status and invoice - Realtor - ask for budget, provide listings - Survey - ask questions, collect answers, submit to Typeform - Airline service - get your boarding pass - Mixpanel - talk to your analytics In other words: - Talk to APIs & hot data - ChatGPT plugin on every website - Your SaaS can be a chatbot - APIs made accessible (they were reserved for devs until now) - Create an API, use chat as the interface - skip the frontend I am trying to envision a future where website visitors are empowered to just say what they want from the business - instead of navigating endless dashboards and documentation. I'm looking for some feedback about my product! lmk Rafal https://bit.ly/3DWDvpg August 14, 2023 at 01:08PM

Show HN: A free course on how to write a good Midjourney/ChatGPT prompt https://bit.ly/45uifmv

Show HN: A free course on how to write a good Midjourney/ChatGPT prompt https://bit.ly/45nXLf1 August 14, 2023 at 10:37AM

Sunday 13 August 2023

Show HN: PokerWave – Retro PvP Card Games in Rust and Redis and VanillaJS https://bit.ly/3savQRu

Show HN: PokerWave – Retro PvP Card Games in Rust and Redis and VanillaJS Source code: https://bit.ly/47wTKa4 https://bit.ly/47x9l9k August 13, 2023 at 06:05PM

Show HN: NotYetNews – AI-Generated News from the Future https://bit.ly/3qm49ER

Show HN: NotYetNews – AI-Generated News from the Future https://bit.ly/3sdD1IM August 13, 2023 at 04:39PM

Show HN: Awayto v2 short demo; an actual all-in-one framework https://bit.ly/3DUG62U

Show HN: Awayto v2 short demo; an actual all-in-one framework Hey folks, just putting this up as a demo link for people to try out. It's a project I've been working on since January and in light of recent framework posts lately I figured I'd start talking about my own. The link is a demo site of Awayto v2 [1] (ignore the front page info that's all from version 1). Awayto [0] started out as a quick deploy app which grew to exist via AWS. I felt the need to make something that wasn't so closely tied to cloud infra, and Awayto v2 is that. Currently deployed on hetzner vms, using Tailscale for networking, there is a great deal of things going on. There is a local installation path planned, as long as you provide your own servers, etc, as it all just works on Tailscale anyway. I'm still working on docs, but the goal is to spit out _everything_ a dev might want to control in their stack. My current version of deploying to hetzner sets up 7 servers (2 ns, exit, build, app, db, svc). Git profile [2] for more info, tech stack info. This is just a short demo and will only be up a limited time. There's no email validation or anything, gibberish is welcome. You are not being tracked. I know I need how-to docs, video assists, and all that. Slow and steady. It's being hosted from a single warehouse in the Pacific Northwest, be kind. Caching is in play and not perfectly tuned so maybe wait a few minutes if something doesn't automatically show up. Any feedback is awesome. Cheers! [0] https://bit.ly/3DUG6zW [1] https://bit.ly/3KFz2em [2] https://bit.ly/448a9yw https://bit.ly/3DUG8b2 August 13, 2023 at 12:58PM

Show HN: Broken Bear, the AI teddy bear that loves your broken self https://bit.ly/47srg17

Show HN: Broken Bear, the AI teddy bear that loves your broken self I made a GPT-based AI Chatbot based on Carl Roger's philosophy of radical self-acceptance. Broken Bear is designed to be a kind, comforting, and quietly encouraging friend. https://bit.ly/3sbTGfK August 13, 2023 at 10:47AM

Show HN: Mixtape of 200 “futuristic” songs circa 1980 https://bit.ly/3KCLY4u

Show HN: Mixtape of 200 “futuristic” songs circa 1980 I'm posting this long mix of 200 "futuristic" music recordings, in chronological order (from the mid 1970's to the mid 1980's). Some are obvious (eg: "She Blinded Me With Science") while others are long forgotten (eg: G.G. Tonet's "Dedicated To Norbert Wiener" or Jyl's "Silicon Valley") --- Circa 1980 Mixtape https://bit.ly/3Yw1e8Y --- While the theme of the linked mix (ie: tech) probably interests some here, it is likely too fluffy for many others so apologies for that. This thing took me almost two years to finish, so in a moment of weakness I am going ahead and posting it here. There actually is a tech angle to why it took so long. After I gathered the 200 audio tracks I wanted, I wound up stymied for several months because trying to match the timbre and loudness of 200 songs overwhelmed me. During that time I began writing a program in my spare time to band-split all the files and match their perceived loudness. I got around half-way through that when OpenAI released GPT4. On a whim, I asked it to write a BASH script to perform the auto-EQ: a couple evenings of minor tweaks and it was done https://bit.ly/3L1hQjJ so I went ahead and completed the mix. The final mixing together of songs - I am not a DJ and have no experience beat-matching - was also done programmatically (wrote a program that takes start- and end- times of the regions to crossfade, and then ramps samplerate up or down for the two tracks. August 13, 2023 at 09:02AM

Saturday 12 August 2023

Show HN: I used AI to turn people into GigaChads https://bit.ly/3qBYtGC

Show HN: I used AI to turn people into GigaChads Hey folks! I want to share a project I've been working on during my free time over the past few months. It's a mobile app that uses AI to turn people into over 30 famous meme images: from GigaChad to DiCaprio. You can check out some of the results here: https://bit.ly/3YzRJ8I I was inspired by the Remix option in Midjourney. At the end of 2022 I saw an article how people using this feature combine two pictures and get some crazy results mixing people with animals and generating new memes. Later, to have a little fun, I decided to prank my friend using the Midjourney Remix with his photos. However, I wasn't satisfied with the results. So I built my own pipeline using Stable Diffusion + DreamBooth + some other components, and created a few images by mixing his face with memes. My friend had a good laugh when he saw them. I thought it would be a good idea to make the process easier to repeat so I built MeMemes app. I hope you all enjoy it and have some fun, and would love to hear your feedback! P.S: Due to high server cost I take small fee for generation. But today I will make it just 1$. https://bit.ly/3YzRJ8I August 13, 2023 at 05:12AM

Show HN: Run LLaMa2 on the Browser with Ggml.js https://bit.ly/3OAgsVU

Show HN: Run LLaMa2 on the Browser with Ggml.js You can now build serverless AI inference web application with ggml.js's LM backends. https://bit.ly/47xeazy August 12, 2023 at 08:52PM

Show HN: React Hooks in Python https://bit.ly/3sfkwTZ

Show HN: React Hooks in Python A React inspired way to code in Python. Python Hooks is a very opinionated project and it's not meant to be a replacement for any of the existing state management libraries. It was created as a coding exercise gone sideways. https://bit.ly/446dv59 August 12, 2023 at 04:49PM

Show HN: Hypersprawl – a metaverse with 4 spatial dimensions https://bit.ly/456N1C7

Show HN: Hypersprawl – a metaverse with 4 spatial dimensions Hi all, Years ago I was wondering what kind of problems superhuman AI would be able to solve that would be difficult for humans. I came up with problems requiring higher dimensional spatial awareness. Scratching my head a bit further, the humble me started thinking that actually there is no reason why our brains could not handle higher spatial dimensions, if the brain was just given appropriate feedback from our sensory system. Fast forward a lot of further head scratching, and here is a barely MVP of a VR environment for 4 spatial dimensions, with some navigation aids including acoustic sensory augmentation (sounds fancier than it is...) First I thought to have just the Hypershack where you can locally build 4d stuff on your browser, but then thought it would be cool to have also a 4d metaverse where you could share and see 4d things built by others - and there might be even a way to monetise this for me by renting real estate in there. So, that is Hypersprawl. To manage expectations, the performance is bad for now, I have limited the Hypersprawl to 10 4d objects per address. You can use Hypershack for free, also there are lots of free addresses in Hypersprawl, only if you want to get closer to the Black Sun (sorry Stephenson, I couldn't not copy that), you need to make a donation or subscription. You do not need to have a VR headset to have a look, browser is enough, but of course immersion suffers quite a lot. All feedback is more than welcome. Frankly, I do not expect this to be a major commercial success and actually I think this may be a bit too far in the fringes of geekiness to find anyone else interested, but I guess this community is one of the better places to try to prove me wrong. (So, have I been successful in getting any intuition in 4 spatial dimensions? So far not much luck on that, only that the 4d space is huge. Literally mind-bogglingly huge. I think my next direction is to spend some time figuring out the pedagogy on what objects/functionality I should have there to get the intuition. But do not expect anything to be quick with this one, and I am talking more likely about years than months.) Cheers, Teemu https://bit.ly/3OF8nQ6 August 12, 2023 at 03:50PM

Show HN: There are over a thousand possible finger arrangements for your hands https://bit.ly/3rZf3k7

Show HN: There are over a thousand possible finger arrangements for your hands https://bit.ly/445vLfg August 12, 2023 at 02:38PM

Show HN: Pho – Phonetic Alphabet Renderer in Rust https://bit.ly/3DR3uyj

Show HN: Pho – Phonetic Alphabet Renderer in Rust https://bit.ly/3qrwx8n August 12, 2023 at 10:11AM

Friday 11 August 2023

Show HN: Open-source proxy server for Llama2, GPT-4, Claude2 with Logging,Cache https://bit.ly/3OTxfVx

Show HN: Open-source proxy server for Llama2, GPT-4, Claude2 with Logging,Cache Hello hacker news, I’m the maintainer of liteLLM() - package to simplify input/output to OpenAI, Azure, Cohere, Anthropic, Hugging face API Endpoints: https://bit.ly/3sdfQ0U We’re open sourcing our implementation of liteLLM proxy: https://bit.ly/3OSDsRz... TLDR: It has one API endpoint /chat/completions and standardizes input/output for 50+ LLM models + handles logging, error tracking, caching, streaming What can liteLLM proxy do? - It’s a central place to manage all LLM provider integrations - Consistent Input/Output Format - Call all models using the OpenAI format: completion(model, messages) - Text responses will always be available at ['choices'][0]['message']['content'] - Error Handling Using Model Fallbacks (if GPT-4 fails, try llama2) - Logging - Log Requests, Responses and Errors to Supabase, Posthog, Mixpanel, Sentry, Helicone - Token Usage & Spend - Track Input + Completion tokens used + Spend/model - Caching - Implementation of Semantic Caching - Streaming & Async Support - Return generators to stream text responses You can deploy liteLLM to your own infrastructure using Railway, GCP, AWS, Azure Happy completion() ! https://bit.ly/3OUbxAP August 12, 2023 at 01:08AM

Show HN: Weaviate – Multi Tenancy Notebook https://bit.ly/45625jf

Show HN: Weaviate – Multi Tenancy Notebook https://bit.ly/3KBBMt0 August 11, 2023 at 11:50PM

Show HN: Pip Imports in Deno https://bit.ly/47pVFx4

Show HN: Pip Imports in Deno deno_python 0.3.1 adds support for importing python pip packages directly in JavaScript! Fun and useful, slightly cursed. https://bit.ly/3QBc5g2 August 11, 2023 at 10:30AM

Thursday 10 August 2023

Show HN: I made a tool that makes React faster automatically https://bit.ly/3OSnLKc

Show HN: I made a tool that makes React faster automatically In brief: I'm Aiden, 18, and have spent the past 2 years of high school working on Million.js, an open source React alternative with 11K stars on GitHub and hundreds of thousands of npm downloads. Recently, I released automatic mode, which detects slow React components and automatically optimizes the reconciliation phase. It's still in beta but chugging along. It's around 70% faster than React on the JS Framework Benchmark and you can see how I did it here: https://bit.ly/45feEsi Interested? Check it out here: https://bit.ly/45mjDqZ August 11, 2023 at 06:39AM

Show HN: Tetris, but the blocks are ARM instructions that execute in the browser https://bit.ly/3s8mXrF

Show HN: Tetris, but the blocks are ARM instructions that execute in the browser OFRAK Tetris is a project I started at work about two weeks ago. It's a web-based game that works on desktop and mobile. I made it for my company to bring to events like DEF CON, and to promote our binary analysis and patching framework called OFRAK. In the game, 32-bit, little-endian ARM assembly instructions fall, and you can modify the operands before executing them on a CPU emulator. There are two segments mapped – one for instructions, and one for data (though both have read, write, and execute permissions). Your score is a four byte signed integer stored at the virtual address pointed to by the R12 register, and the goal is to use the instructions that fall to make the score value in memory as high as possible. When it's game over, you can download your game as an ELF to relive the glory in GDB on your favorite ARM device. The CPU emulator is a version of Unicorn ( https://bit.ly/446wWer ) that has been cross-compiled to WebAssembly ( https://bit.ly/47p0N4z ), so everything on the page runs in the browser without the need for any complicated infrastructure on the back end. Since I've only been working on this for a short period of time leading up to its debut at DEF CON, there are still many more features I'd eventually like to implement. These include adding support for other ISAs besides ARM, adding an instruction reference manual, and lots of little cleanups, bug fixes, and adjustments. My highest score is 509,644,979, but my average is about 131,378. I look forward to feedback, bug reports, feature requests, and strategy discussions! https://bit.ly/47vrqoC August 11, 2023 at 12:56AM

Show HN: Q&A with AI Trained on Bankruptcy Law https://bit.ly/3DP14QC

Show HN: Q&A with AI Trained on Bankruptcy Law I crawled a #$%^ ton of bankruptcy case law and pointed a LLM at it to answer bankruptcy legal questions. I just tried it on the Supreme Court's request today in its order stopping the Purdue Pharma settlement[1], and it gives a decent answer. > The parties are directed to brief and argue the > following question: Whether the Bankruptcy Code authorizes a > court to approve, as part of a plan of reorganization under > Chapter 11 of the Bankruptcy Code, a release that extinguishes > claims held by nondebtors against nondebtor third parties, > without the claimants’ consent. ChatLaw's answer: The Bankruptcy Code does not explicitly authorize a court to approve, as part of a plan of reorganization under Chapter 11, a release that extinguishes claims held by non-debtors against non-debtor third parties, without the claimants’ consent. However, courts have interpreted certain provisions of the Bankruptcy Code to permit such non-consensual third-party releases under certain circumstances. The relevant provisions of the Bankruptcy Code include Section 105(a), which empowers the court to issue any order, process, or judgment that is necessary or appropriate to carry out the provisions of this title, and Section 1123(b)(6), which allows a plan to include any other appropriate provision not inconsistent with the applicable provisions of this title. In the case of In re: Mallinckrodt PLC, (District of Delaware, 02/08/2022), the court noted that while Section 524(e) of the Bankruptcy Code should be read to preclude non-debtor releases, releases are not the equivalent of a discharge. The court also noted that the Third Circuit has recognized that bankruptcy courts do have statutory and constitutional authority to approve a plan of reorganization that contains non-consensual third-party releases, albeit, only in extraordinary cases. In the case of In Re: 18-13374-mew Aegean Marine Petroleum Network Inc. (Southern District ofNew York, 2019-04-08), the court noted that some Circuit Courts of Appeal have held that bankruptcy courts lack the power to grant nonconsensual third-party releases of the kind that the Debtors seek here. However, other Courts of Appeal, including the Second Circuit Court of Appeals, have held that bankruptcy courts have the power to impose involuntary releases, but that such involuntary releases should be imposed only in rare cases. In the case of 22-110 In re: Purdue Pharma L.P. (Second Circuit Court of Appeals, 5/30/2023), the court concluded that two sections of the Bankruptcy Code, 11 U.S.C. 105(a), 1123(b)(6), jointly provide the statutory basis for the bankruptcy courts authority to approve a plan that includes nonconsensual releases of third-party claims against non-debtors. The court further held that the bankruptcy courts inclusion of the releases is equitable and appropriate under the specific factual circumstances of this case. In the same case, in a concurring opinion, Judge Richard C. Wesley agreed that a bankruptcy court has the authority to approve a Chapter 11 reorganization plan that includes nonconsensual nondebtor releases, based on the court's precedent in In re Drexel Burnham Lambert Grp., Inc., 960 F.2d 285, 293 (2d Cir. 1992). However, he expressed concerns about the lack of explicit statutory basis for such releases in the Bankruptcy Code. In conclusion, while the Bankruptcy Code does not explicitly authorize non-consensual third-party releases, courts have interpreted certain provisions of the Code to permit such releases under certain circumstances. The permissibility of such releases often depends on the specific facts and circumstances of the case, and courts have cautioned that such releases should be approved only in rare cases. [1] https://cnn.it/3DP15nE... https://bit.ly/3DP16Ie August 11, 2023 at 12:58AM

Show HN: ChatKey – Supercharge your productivity with ChatGPT and AutoHotkey https://bit.ly/47ppWMp

Show HN: ChatKey – Supercharge your productivity with ChatGPT and AutoHotkey https://bit.ly/3rDoNQQ August 10, 2023 at 05:11PM

Show HN: Open-Source Web App with User Interface for AutoML on Tabular Data https://bit.ly/47ppPjX

Show HN: Open-Source Web App with User Interface for AutoML on Tabular Data https://bit.ly/47oEGv4 August 10, 2023 at 05:09PM

Show HN: Netdata released v1.42 and it includes 800 integrations https://bit.ly/3OmSOfq

Show HN: Netdata released v1.42 and it includes 800 integrations https://bit.ly/3On8Mq4 August 10, 2023 at 10:00AM

Show HN: A Strategic Guessing Game https://bit.ly/47EJahp

Show HN: A Strategic Guessing Game https://bit.ly/3KBSOr7 August 10, 2023 at 08:10AM

Show HN: Applite – Clean Homebrew front end app for macOS built with SwiftUI https://bit.ly/3qrsGrX

Show HN: Applite – Clean Homebrew front end app for macOS built with SwiftUI https://bit.ly/3ORXA64 August 10, 2023 at 02:13PM

Show HN: Computer Socialism https://bit.ly/3Ox9AIU

Show HN: Computer Socialism https://bit.ly/3YsW7q8 August 10, 2023 at 11:13AM

Wednesday 9 August 2023

Show HN: Easiest way to convert PDF tables to Excel https://bit.ly/45hhXzL

Show HN: Easiest way to convert PDF tables to Excel We built a Windows app to convert PDF tables to Excel. You just have to take a screenshot of the table. Why try another app when there's so many PDF to Excel converters? It is: - Faster - More convenient - More accurate than other converters (including Excel's Power Query). Feel free to test it with complex tables (like the ones found in financial documents). https://bit.ly/46WVlFH August 10, 2023 at 01:35AM

Show HN: Traxoft – Easy Image Voting Shopify App https://bit.ly/3DPktko

Show HN: Traxoft – Easy Image Voting Shopify App https://bit.ly/3ONXaxA August 9, 2023 at 11:38AM

Show HN: I'm 17 and wrote this guide on how CPUs run programs https://bit.ly/45kfUdx

Show HN: I'm 17 and wrote this guide on how CPUs run programs https://bit.ly/3OPjyGX August 9, 2023 at 02:33PM

Show HN: Infracost (YC W21): Be proactive with your cloud costs https://bit.ly/45iAqeE

Show HN: Infracost (YC W21): Be proactive with your cloud costs Hi, we are Ali, Hassan, and Alistair, co-founders of Infracost (https://bit.ly/3q0dSel). Infracost helps engineers see the cost of each Terraform change before launching resources. When changes are made, it posts a comment with the cloud cost impact. For example, “you’ve added 2 instances and volumes, and change an instance type from medium to large, your bill will increase by 25% next month, from $1000 to $1250 per month”. We launched in February 2021 (https://bit.ly/3q0AHPl), and Infracost is now being actively used by over 3,000 companies. However, there is a shift happening in the cloud cost management space. New teams, called FinOps teams (a combination of "Finance" and "DevOps"), are being formed within companies to manage cloud costs. One of the first tasks assigned to these teams is to determine "who is using what" - that is, which teams, business units, products, etc. are spending the most on cloud. To accomplish this, they use tags. Tags are labels that all cloud resources should have and are key-value pairs. For example, a server could be tagged with: product=HackerNews; environment=production; team=blueTeam. So if resources are not tagged properly, then you can’t tell who is using what. However, FinOps teams face challenges because their tools are reactive. These tools begin by analyzing cloud bills and providing visibility of tags from there. This means that they are looking at resources that are already running in production and costing money. A customer recently shared, “I want all resources to be properly tagged. But if they are not, I would rather a resource not be tagged at all than be tagged incorrectly.” My "aha" moment! FinOps teams can define a tagging policy that can be validated in CI/CD before resources are launched. This is important because if code is shipped with the wrong tags, FinOps teams will have to fight for sprint time to fix them. Even if you shut down an untagged resource directly in the cloud, the next time Terraform runs, the resource will launch again with no tag. You need to fix the issue at its root. I’d love your feedback on our solution to the tagging problem. You define your tag key-value policy in our SaaS product, and Infracost checks all Terraform resources per change. If anything fails the policy, it posts a comment with the details of which resources need tags, and what the allowed values are. Once fixed, it will let the code be shipped to production. Try it out by going to https://bit.ly/3qnXOZw, setting up with the GitHub app or GitLab app, and defining your tagging policy. It will then scan your repository and inform you of any missing tags and their file and line number. You can use the free trial, but if you need more time, please message me and I’ll extend it for you. I would also love to hear how others ensure that the correct tag keys and values are applied to all resources, and whether this is done proactively or reactively. Additionally, I would be interested in hearing about any lessons learned in the process. Cheers August 9, 2023 at 02:01PM

Show HN: Social Bellow – AI-Powered Interactive Companion https://bit.ly/45jyjal

Show HN: Social Bellow – AI-Powered Interactive Companion Greetings HN, My name is Edgar and I've created Social Bellow, an AI chat companion. Before this I spent close to a decade working on games with Grumpyface Studios, working closely with Cartoon Network as well as managing my own business. I've built Social Bellow out of the need to manage prompts and eliminate the repetitive task of copying and pasting the same prompts. Storing prompts has the added advantage of providing Large Language Models (LLMs) with more context, thereby facilitating structured content responses. Moreover, I saw the necessity for a tool that could maintain the context window during conversations with the LLMs. Social Bellow was built using AWS Amplify, NextJS, and the help of Vercel to do the streaming. Figma has also helped tremendously in the creation of the project. Having a workflow of Figma, Amplify Studio, and Git continuous deployment has cut down on the time to publish a change. Social Bellow is free to use with OpenAI GPT-3.5 Turbo with a token allowance of 50,000 tokens a month. I've just launched this so you'd be one of the first to try it out. Thank you for the feedback and helping improve the application! https://bit.ly/3QES1cu August 9, 2023 at 09:10AM

Show HN: Minimal note-taking app https://bit.ly/3OPyQvx

Show HN: Minimal note-taking app No accounts, barely any UI chrome. Web-based note taking app with real-time collaboration. Visiting homepage generates a new note with a unique URL. https://bit.ly/45mlD2M August 9, 2023 at 08:39AM

Show HN: MagicQuit – closes apps when you don't use them anymore (free) https://bit.ly/3DMEc46

Show HN: MagicQuit – closes apps when you don't use them anymore (free) I often end up having 15+ applications open in my Dock. And, unfortunately, I tend to never close them. While Arc Browser does a great job for browser tabs, I didn’t find any fully satisfying solution for MacOS. One used way too much power and the other one would have taken quite some time to set it up. So instead I decided to develop an app which took x times more of my free time. MagicQuit is entirely free, open source, 100% offline and closes apps that you haven’t been using in the last 12 hours (customizable). Feature-wise I wanted to keep it as clean and simple as possible. It also uses nearly ~0% of cpu usage. Give it a try if you’re a Mac user and also having the same issue with many open applications: https://bit.ly/3KybkAp https://bit.ly/3KybkAp August 9, 2023 at 12:48PM

Show HN: Kvak.io – Online note-taking app https://bit.ly/3E7NTKZ

Show HN: Kvak.io – Online note-taking app Web-based note taking app with real-time colab. No accounts, barely any UI. Visiting the homepage generates a new note with a unique URL. https://bit.ly/45mRJLw August 9, 2023 at 08:55AM

Tuesday 8 August 2023

Show HN: The Population Project https://bit.ly/44Yd91L

Show HN: The Population Project Two years ago, I turned 50. After a successful career as an entrepreneur, a business angel and a novelist, I set out to start a philanthropic venture under the following constraints: - it had to be global. - it had to be beautiful (in my eyes, at least). - it had to be technology and stats driven. I decided I would try to list the full name and date of birth of all humans alive. While some may find the concept pointless, I immediately knew I had struck gold: - it was global and incredibly hard. - it had an almost artistic quality to it, like an ever-changing installation. - as a libertarian, I resent that states conduct censuses and then sit on the data. - One billion people in the world aren't officially registered. At least someone would acknowledge their existence. I created a non-profit called The Population Project. I would never make a dime off it, but at least my costs would be tax-deductible. I then started researching lists of names online. I quickly adopted two principles. First I would collect a minimal set of information : full name, birth date, and birth place. Second, I would only scrape public information, i.e. nothing behind a password. After a few months, I realized I needed help from more experienced developers. I chose to work on 4D, a platform I had used in the past to develop my company's information system. It was a tough choice: 4D is not a leading player in the back-end world, but I figured the growth of API tooling would make language choice less critical. The first iteration of our database was frustrating - way too slow to publish a website. I learned the power of incremental change, with each marginal improvement saving you a few percent of speed or space. I also got to implement concepts I had heard about but never implemented, such as mirroring, partitioning, or hash-indexing. Then I hired a team of six data processors in Madagascar who clean up and process the lists found online. Lots of Python and Excel macros in their day-to-day. I have instilled in them an obsession with quality. A bad record will sit in our base forever. After trying dozens of softwares, we've settled on Adobe Acrobat and Octoparse. The final piece was the website. I lucked out in finding a strong team in Romania. They build with Next.js and deploy on Vercel. I gave them Wikipedia as the model to aim for. We/they haven't been able to match Wikipedia's simplicity. Our pages are too heavy. But I find the site user-friendly, pleasing to the eye and reasonably fast. We can and we will do better. A word about privacy. Some people complain that because it publishes names and DOBs, the Population Project infringes on their privacy. We obviously don't see it that way. - All our info is public. That DOB you find on the site is probably in the voter list of your state, a list that anyone can request or plainfully download. - The info we publish is minimal. Basically, we say that you exist. No one will find anything about your race, religion, sexual preferences, job or income. - We have adopted Wikipedia's privacy policy. We do not record your IP, unless you create or edit a record. - We're using Matomo for our Analytics. Great stuff. It's not free but they do not use your data like GA. Why am I telling you all this? From the beginning, I've envisioned a three-step process: 1) Build the database and populate it with millions of Western profiles. 2) Launch the site, where anybody can create or edit records and share them with their family. 3) When we've reached critical mass (1B records?), start making deals with NGOs and governments, and venture into other alphabets. We have just completed step 1. Step 2 is daunting as hell. I have grown a business but I have never grown a website. While I am ready to spend a bit of money on PR or SEO, I am not delusional: to reach the level of success we have in mind, we need this thing to go (somewhat) viral. How do you do that? https://bit.ly/453p8LC August 7, 2023 at 04:46PM