BlogViral

Show HN: AI bot that automatically processes unstructured documents Hi HN! We’re excited to share what we’ve been working on—a bot that automates the tedious task of processing unstructured documents from emails and entering them into ERPs. After many iterations, we’ve achieved 99.8% accuracy in extracting and mapping data from invoices, POs, and other documents. One surprising takeaway from this journey: building the AI was only 10% of the challenge! The real work came from handling edge cases, integrating seamlessly with various ERPs, and creating a reliable pipeline for real-world documents with messy formats. We’d love your feedback, thoughts, or questions about how we built this, the challenges we faced, or anything else. Let us know what you think! Thanks for checking it out! https://ift.tt/auiZswU November 23, 2024 at 08:20AM

Show HN: Open-Source Pull Request AI Reviewer Hey HN, Over the last year, I’ve reviewed more than 1000 code changes. Most of the time was spent catching obvious mistakes rather than debating complex design decisions. If we estimate ~10 minutes per review, that’s 160+ hours spent reviewing code in just one year. So I thought: could I get some of that time back using LLMs? That's why I spent the last few weekends building Presubmit.ai, an open-source AI reviewer that runs as a Github Action right when you open a Pull Request. The results so far are promising: I estimate it can reduce the review time by 50%, which in my case would mean I save 80hours (~10 working days) per year. Unlike similar SaaS solutions, the goal is not to replace the human reviewer but to highlight obvious mistakes early, spot security vulnerabilities and give more context about the change. I like to think of it as a “pre-reviewer”. Some of its features are: * Line-by-line comments * PR summarization * Title gen

Show HN: Pull Request Reviewed by LLM This year I’ve reviewed more than 1000 code changes. Most of the time was spent catching obvious mistakes rather than debating complex design decisions. If we estimate ~10 minutes per review, that’s 160+ hours spent reviewing code in just one year. So I thought: could I get some of that time back using LLMs? That's why I spent the last few weekends building an LLM-based prereviewer that should take a first pass before the actual human reviewer. The results so far are promising: I estimate it can reduce the review time by 50%, which in my case would mean I save 80hours (~10 working days) per year. Linked above is an example of a PR where I'm testing the AI reviewer and it showcase how it can detect bugs, suggest best practices about token validity, generate summary and title, and even chat with me in review comments. The AI reviewer is a simple Github action that runs everytime I open or synchronize a pull request and you can see the source

Show HN: Shop on Amazon with Crypto Hey folks! I'm building an app to let anyone shop on Amazon with crypto. How it works: [1] Add "baggins.ai/" before any Amazon product URL [2] Fill in your shipping details [3] Pay with your preferred wallet (BTC, ETH, DOGE, USDC, and more) Features: - Supports 1-2 day Prime shipping - Uses Coinbase Commerce for secure transactions Here's an early version for y'all to test: https://www.baggins.ai/ Keen to get feedback on the UX and feature requests! My LI to show that it’s not a scam :) https://ift.tt/LYeyWg5 https://ift.tt/qQc6A39 November 22, 2024 at 11:29PM

Show HN: VS Code extensions that display CGM blood glucose levels in status bar As a Type 1 diabetic, I need to continuously monitor my blood glucose levels. I’ve implemented a couple of Visual Studio Code extensions that retrieve the latest blood glucose readings from your CGM and display them in your VS Code status bar. One VS code extension uses the Nightscout CGM to retrieve the blood glucose readings. It requires users to run the Nightscout application on a hosted server. A nice benefit of Nightscout application is that it works with all the major CGM devices. However, a slight drawback of this option is that it requires a hosted third party software (Nightscout) for proper functionality. I’ve also implemented a Visual Studio code extension for those (like myself) that use the Freestyle Libre CGM. This version connects directly to LibreLinkUp to retrieve the latest blood glucose readings and display them in your VS code status bar. This removes the dependency for the intermediary

Show HN: My Remote Teaching Station (Mk IV) The remote teaching station has been evolving for the last four years. The Mk IV is the most advanced and most attractive version so far. https://ift.tt/wgxiCEb November 21, 2024 at 11:37PM

Show HN: An AI that reliably builds full-stack apps by preventing LLM mistakes Hey HN! Previous CERN physicist turned hacker here. We've developed a way to make AI coding actually work by systematically identifying and fixing places where LLMs typically fail in full-stack development. Today we're launching as Lovable (previously gptengineer.app) since it's such a big change. The problem? AI writing code typically make small mistakes and then get stuck. Those who tried know the frustration. We fixed most of this by mapping out where LLMs fail in full-stack dev and engineering around those pitfalls with prompt chains. Thanks to this, in all comparisons I found with: v0, replit, bolt etc we are actually winning, often by a wide margin. What we have been working on since my last post ( https://ift.tt/1exYjmr ): > Handling larger codebases. We actually found that using small LLMs works much better than traditional RAG for this. > Infra work to enable instant preview (it sp

Show HN: Agentic Evaluators for Agentic Workflows (Starting with RAG) Hey all! Thought this group might find this interesting - new approach to evaluating RAG pipelines using 'agents as a judge'. We got excited by the findings in this paper ( https://ift.tt/U0FyOcq ), about agents producing evaluations closer to human-evaluators, especially for multi-step workflows. Our first use case was RAG pipelines, specifically evaluating if your agent MISSED pulling any important chunks from the source document. While many RAG evaluators determine if your model USED its chunk in the output, there's no visibility on if your model grabbed all the right chunks in the first place. We thought we'd test the 'agent as judge', with a new metric called 'potential sources missed', to help evaluate if your agents are missing any important chunks from the source of truth. Curious what you all think! https://ift.tt/7dVuqit November 20, 2024 at 11:57PM

Show HN: Cardo ‒ Open Source desktop podcast client Show HN: Cardo - Open Source Desktop Podcast Client Hi, I'm an amateur developer from Spain. I have released this desktop podcast client that works on Windows, Mac and Linux. It's a modest project, but it might be useful for you, it has syncing capabilities with Antennapod, Kasts, Repod or other clients. You can manage your subscriptions, queue episodes and even download them to listen to later. I look forward to hearing your thoughts. https://ift.tt/Gnwz6lD November 20, 2024 at 07:56PM

Show HN: Serverless code execution, but for AI agents https://sandboxed.ai November 20, 2024 at 06:36AM

Show HN: Archgw: open-source, intelligent proxy for AI agents, built on Envoy Hi HN! This is Adil, Salman, Co and Shuguang and we're excited to introduce archgw [1], an open source intelligent proxy for agents built on Envoy [2]. Arch moves the critical but crufty work around safety, observability, and routing of prompts outside business logic. Arch is a uniquely intelligent infrastructure primitive, engineered with purpose-built fast LLMs [3] for tasks like intent detection over multi-turn, parameter identification and extraction, triggering single/multiple function calls, and offers convenience features to auto dispatch LLM calls for summarization based on data from your APIs via system prompts configured in archgw. Today, the approach to build a smart production-ready agent is weaving together a large set of mono-functional opinionated libraries, adding extra layers like LLM-based preprocessing to determine things like relevance and safety of the user's prompt (e.g. applying

Show HN: Physically accurate black hole simulation using your iPhone camera https://ift.tt/UCZjoEI November 20, 2024 at 12:06AM

Show HN: Fireproof – local-first database with Git-like encrypted sync Hi, HN! As a cofounder of Couchbase, I pioneered mobile sync, and I’ve always wanted to bring the speed and reliability of local-first data to the web, incubating PouchDB among other efforts. I learned the constraints of real world financial applications at McKinsey & Company FinLab, and Merkle integrity research at Protocol Labs taught me smart contract data structures. As part of the JavaScript community (and early hosting provider for NPM) I’ve been waiting, and now with the availability of APIs like Passkeys and Origin Private Filesystem, I’m happy to say the browser is ready to support embedded databases. Front-ends are a lot easier to write when your database handles live sync for you, but the existing solutions rely on heavyweight cloud APIs instead of putting the smarts at the edge, where it belongs. I started from a different set of constraints, and arrived at a lightweight embedded database that uses a

Valencia Side-Running Bikeway Goes to SFMTA Board for Final Vote By Coming up with the final design required in-depth community outreach and conversations, like this feedback exercise conducted at a Valencia Street open house. On Nov. 19, we will present a final design for a side-running Valencia Street bikeway to the SFMTA Board of Directors. This follows ten months of sustained community outreach and design work. If approved, construction will begin in January 2025. This project aims to create a safer and more enjoyable experience for everyone traveling along the vibrant Valencia Street corridor between 15th and 23rd streets. You can share feedback either... Published November 18, 2024 at 07:00AM https://ift.tt/rd2QzlZ

Show HN: FastGraphRAG – Better RAG using good old PageRank Hey there HN! We’re Antonio, Luca, and Yuhang, and we’re excited to introduce Fast GraphRAG, an open-source RAG approach that leverages knowledge graphs and the 25 years old PageRank for better information retrieval and reasoning. Building a good RAG pipeline these days takes a lot of manual optimizations. Most engineers intuitively start from naive RAG: throw everything in a vector database and hope that semantic search is powerful enough. This can work for use cases where accuracy isn’t too important and hallucinations are tolerable, but it doesn’t work for more difficult queries that involve multi-hop reasoning or more advanced domain understanding. Also, it’s impossible to debug it. To address these limitations, many engineers find themselves adding extra layers like agent-based preprocessing, custom embeddings, reranking mechanisms, and hybrid search strategies. Much like the early days of machine learning when we manually

Show HN: EnkiTask – Simple Task Management for Freelancers, Pay Only for Tasks Hi HN, I’m excited to share EnkiTask, a simple project management tool we built for freelancers and indie hackers. We wanted something with: - No subscriptions or recurring payments (pay only for tasks). - Unlimited team members at no extra cost. - A clean, intuitive interface built with Agile/Scrum methodologies in mind. We started using it internally, and after positive feedback from friends, decided to make it public. Would love your thoughts! Check it out here: [ https://enkitask.com](https://enkitask.com) November 18, 2024 at 11:22PM

Show HN: Store and render ASCII diagrams in Obsidian Obsidian plug-in that allows you to create and store ASCII diagrams in your notes. It can be used to visualise diagrams, flowcharts, complex tables, Gantt charts and more in technical documentation, that will be rendered as a nice SVG graphics. https://ift.tt/xqpgBIF November 12, 2024 at 09:03AM

Show HN: Understanding the Bloch Sphere https://ift.tt/K0erMWL November 18, 2024 at 03:18AM

Show HN: Novus – local HTTPS proxy for a delightful developer experience https://ift.tt/9RhwQ7k November 17, 2024 at 10:52PM

Show HN: I made Picle (a.k.a. Catchphrase x Wordle x AI) Love to hear what you think! Thank you! https://picle.fi/ November 17, 2024 at 10:08PM

Show HN: I built an app for anyone to design their own kitchen https://ift.tt/j1Hwt6s November 17, 2024 at 06:19AM

Show HN: I built a(nother) house optimized for LAN parties https://lanparty.house/ November 16, 2024 at 10:52PM

Show HN Memory for AI Agents https://ift.tt/7WtXR9u November 16, 2024 at 10:03PM

Show HN: Ore – Lightweight, Generic and Simple DI Container for Go https://ift.tt/nYrBZ7p November 16, 2024 at 09:39PM

Show HN: Scooter – Interactive find and replace in the terminal https://ift.tt/hzV0RpK November 15, 2024 at 11:45PM

Show HN: Windsurf – Agentic IDE At Codeium, we've been building AI-powered extensions for a while (we first launched our VSCode extension with autocomplete a little over 2 years ago!), but we've always thought there would come a day where we would hit the limits of what could be achieved within existing IDEs, so we decided to build our own: Windsurf (yes, it's yet another VSCode fork :) We've stuffed a lot of cool features into Windsurf—a super fast autocomplete model, an inline diff generation experience that feels truly native, but we're most proud of Cascade, which is an evolution of the sidebar chat experience that many other extensions have. Cascade can perform deep reasoning on your existing codebase, access a vast array of tools that allow it to run terminal commands and find relevant files, and it's omniscient of all the actions that the user has taken independent of invoking the AI. (You can for example, start implementing a change manually and just ask

Show HN: The Billy Bass I put on the Internet This one is just for fun. A couple years back I put together this tool to help me make synced up open/close mouth animations. End goal was always to "put it on the internet" like so many other things I remember when I was a bit younger. You can't drop this into a livestream these days without getting banned because people can't play nice, so I made it to record and distribute videos privately. I only code like this as a hobby, so it is a bit rough (I am a hardware guy), but these days you can get pretty far without knowing a lot. Enjoy https://ift.tt/9AneXQG November 14, 2024 at 07:47PM

Show HN: Memoripy – AI Memory Layer with Short- & Long-Term Memory, Clustering Hey HN! I built Memoripy, a memory layer for AI that adds short-term, long-term, and semantic memory capabilities to enhance LLM applications. It helps AI systems retain and prioritize past interactions, adapt over time, and respond with greater context and personalization. Memoripy uses semantic clustering to retrieve relevant memories, along with adaptive memory decay and reinforcement, so interactions stay fresh and context-aware. It’s designed for easy integration with OpenAI, Ollama, and other platforms—giving your AI applications dynamic memory management with minimal setup. Would love to hear your thoughts and feedback! https://ift.tt/7eAQ9Sg November 15, 2024 at 03:42AM

Paying Your Fares Keeps Us Moving By It can happen to anyone. You are in a rush and need to get to an important appointment. Your phone’s battery runs out. Or your Clipper Card only has a dollar left in the account. You hop on the next bus and skip paying the fare. You cross your fingers that no one checks for your proof of payment. This individual example may seem harmless. Yet, when tens of thousands of riders every day do not pay their fare, it ends up costing Muni millions every year. Our partners at the San Francisco County Transportation Agency (SFCTA) recently wrote a piece describing the challenging fiscal situation... Published November 13, 2024 at 07:00AM https://ift.tt/cGsk60w

Show HN: Burner – A Low Cost Wallet to Gift Crypto Hi HN! I’m one of the creators of Burner, a low cost Ethereum hardware wallet designed for gifting. After creating various forms of crypto “cash” ( https://kong.cash/ , https://offline.cash/ ) we learned that gifting cryptocurrencies was consistently one of the biggest challenges for holders and enthusiasts. Burner looks and feels like a colorful gift card, but under the hood it incorporates a secure element chip. You can access its wallet with just an NFC tap, and it works entirely through our (soon to be) open source web app. There is a lot more to share, like USD II (created by https://www.bridge.xyz/ ), a stablecoin that we designed to work with Burner without gas, but for now we’re excited to push Burner out the door and start getting feedback from users. https://burner.pro/ November 14, 2024 at 12:01AM

Show HN: Nango Auth – Free OAuth for 250 APIs Nango Auth is a free, source-available implementation of (O)Auth for 250+ APIs. Auth with external APIs is surprisingly difficult. OAuth is a mess[0], many APIs require parameters other than an API key or access token, and platforms like Stripe or GitHub even create their own custom auth protocols. We first launched Nango Auth on HN 1.5 years ago[1] when it only supported 40 OAuth APIs. Since then, it has expanded beyond OAuth into an end-to-end solution for API authentication: - Supports 250+ APIs[2] and almost a dozen auth modes: OAuth 2.0, OAuth 1.0, API key, Basic auth, and a half-dozen custom formats - Pre-built UI to help users pick & connect the API (including guides to find their API key and other required parameters) - Automatic credentials validation on connect - Secure, encrypted credentials storage & automatic token refresh - Detects expired/broken access tokens - Very detailed logs for quick & easy debugging More th

Show HN: Konga Beat – A custom track editor for Donkey Konga 2 and 3 Howdy HN! For those who don't know, back in the early 2000s, Nintendo and Namco developed a series of music rhythm games for the GameCube featuring Donkey Kong called Donkey Konga: https://ift.tt/9X71OYT The Donkey Konga games borrowed heavily from Taiko no Tatsujin (another music rhythm game by Namco). However, instead of taiko drums, the player would use DK Bongos to jam along with music from different eras and genres. Long story short, I figured out how to add custom tracks to some of the Donkey Konga games (Donkey Konga 2 and 3) but found the entire process cumbersome, so I decided to make a dedicated editor. It was a lot of fun to make, and I hope others get some enjoyment out of it too! https://ift.tt/bBXh8WO November 13, 2024 at 11:39PM

Show HN: Visual inference exploration and experimentation playground https://ift.tt/QyK1bSP November 12, 2024 at 08:03AM

Muni Launches Official Merchandise Store By Jeanne Brophy We are thrilled to announce the launch of Muni's first-ever official merchandise store at The Muni Store. After years of planning and hard work, we're bringing Muni pride directly to our riders and fans. What's in store? The Muni Store (themunistore.com) is an online store only and features over 30 items that appeal to Muni enthusiasts: Comfortable hoodies and sweatshirts Stylish t-shirts and caps Practical mugs for your morning commute on transit Custom Muni puzzle and a "worm" shaped pillow The Classic collection features items with the... Published November 12, 2024 at 07:00AM https://ift.tt/Ht4w2jG

Show HN: Next.js GitHub Markdown Blog This project allows you to easily add a nice looking, mobile-friendly blog to your existing NextJS app without a lot of heavy dependencies or complex stuff to configure. You just set up a repo on GitHub with some markdown files with some metadata at the top, and it will automatically retrieve and convert the markdown to rich html/css blog posts that works well with SEO. I made it for my own webapp because I wanted something simple and easy and didn't want to deal with a complex library/system that does tons of stuff I don't care about. https://ift.tt/KtILqU9 November 13, 2024 at 12:10AM

Show HN: DocSend, but Made 10x Cheaper Hey HN, founder of Peony here. Most founders use DocSend to share investment or sales docs and have to pay $65 to $300 a month to get the security and analytics features. It pains me to see startups getting ripped off when the availability of technologies such as Clickhouse makes real time analytics almost a trivial feature to implement in 2024. We think it's time to end the carnage and democratize the technology. We set ourselves a high bar: we don't want to build another DocSend - we want it to be a far more superior product and also 10x cheaper. After a couple of months of work, I'm proud to share with you Peony - a first preview into what we believe will be the future of file sharing. In addition to the analytics and security features you'd expect coming from DocSend, we built Peony to be flexible and adaptable across all your file sharing needs and give you the ability to deeply personalize your file share per recipient. I'

Show HN: Flash Kitty – Archive of Adobe/Macromedia Flash Movies from Flash Kit After realizing a few months ago that the current flashkit owners didn't really back up any of the user submitted movies, and getting some Flash nostalgia, I created this working Flash Kit archive using data from the Wayback Machine/Internet Archive. It uses Raffle so you can watch the submitted movies in a modern browser without needing plugins. It's not curated so you'll find a variety of things, some things are really creative and can be used for inspiration. https://ift.tt/gAP5vRW November 12, 2024 at 12:41AM

Show HN: I built a Claude AI chat interface to bypass platform limits I got frustrated with Claude's official platform limitations - conversations disappearing, no customization options, and clunky file handling. So I built my own interface over a weekend! GitHub: https://ift.tt/rzDeWC2 What it does: - Saves all conversations locally (SQLite + Drizzle ORM) - Lets you customize Claude's personality per chat - Handles file attachments properly + caching input tokens - Dark/light mode - No conversation limits - Markdown & code syntax highlighting Tech stack is pretty simple: - Nuxt 3 for the frontend - Anthropic's SDK for Claude integration - @nuxt/ui for components - Local SQLite DB Happy to answer any questions! https://ift.tt/rzDeWC2 November 11, 2024 at 08:16PM

Show HN: Open-source tool to convert ComfyUI workflows into web apps and APIs We built an open-source solution to transform ComfyUI workflows into production-ready web applications with minimal configuration. The project consists of: - ViewComfy (open source) - A tool for wrapping ComfyUI workflows in clean, user-friendly interfaces: https://ift.tt/hZOgbD3 - Cloud deployment layer - Includes an automatic dependency resolver that handles model management and node installation. Deploy either as interactive web apps (using ViewComfy) or REST APIs: https://ift.tt/G8oprbm Key features: - Zero-config deployment of any ComfyUI workflow - Automatic model/dependency management - REST API generation - UI builder components You can get started by dropping a workflow here: https://ift.tt/G8oprbm https://ift.tt/9Bpz0PL November 11, 2024 at 03:01AM

Show HN: I made a tiny device for automatically recording digital pianos Hey HN! A few years ago, I left my cushy big tech job to make hardware. And made the device I always wanted - an automatic piano recorder! I usually play piano improvisationally, and manually hitting record never meshed well with that. But there are always moments I wish I recorded, and now they are! Hopefully it scratches a similar itch for some of you as well! A few of the tech details: * built on an esp32-s3 * custom injection molded enclosure * BLE comms, sd card storage, DS1302 RTC * android & ios apps with Flutter * Shadertoy vfx support for video sharing - Chip https://jamcorder.com/ November 8, 2024 at 06:41AM

Show HN: I made a minimalistic AI calendar creator to accelerate daily planning Hey Hacker News! To test implementing AI (and paywalls tbh) in software for the first time, I made this simple calendar creator (no mail address required) that lets a person create a calendar based on his needs and availability and export it to his calendar app, pdf or receive a daily newsletter with his daily tasks (and more). After wrestling with different models (f.e. with huggingface) and encountering different problems, I decided to use ChatGPT's models, tune them a little and see how the result works out. ChatGPT's low price enables me to give users the opportunity to create calendars for free and without a mail address required. Demo video: https://youtu.be/UeZmqXcU5fY?feature=shared The website/tool includes: - Creating your calendar based on a title, date range and a description - Editing and "polishing" the calendar until getting a desired result - Exporting the calendar to your

Show HN: httpclock. A useless way to tell the time with HTTP status codes… I made this a few months back as a fun little project and it has absolutely no utility whatsoever. The server returns the current time in the request's status code — i.e., as long as the time can be mapped to a valid HTTP status code (e.g., 4:04pm -> 404 Not found) the server returns that status code for the request. Example: https://ift.tt/OWc9pBg The httpclock.com domain detects timezone by IP and redirects to the respective subdomain such as pt.httpclock.com (but will fall back to UTC) A browser will show a blank page for most of the day given the number of valid status codes, but you can check other timezone subdomains, e.g. `curl -I https://ift.tt/UisASw5 ` Note: "Invalid" times will return 999 with no content. Anyway, I hope you enjoy this very useless clock. I plan to post the code on GitHub soon since I may as well. Thanks! https://httpclock.com November 10, 2024 at 10:05PM

Show HN: Akas: A Micropodcasting App App store: https://ift.tt/z13fBSY... Play store: https://ift.tt/8MEna9S... Site link: https://akashq.com Invitation code: BVN55L https://www.akashq.com/ November 10, 2024 at 01:45AM

Show HN: Arch GW – Distributed gateway for agents, engineered with small LLMs Hi HN My name is Salman and I work on Arch GW - the intelligent gateway designed to protect, observe, and personalize LLM applications with your APIs. https://ift.tt/ZmNwFrs Our team built Envoy Proxy at Lyft, and re-imagined it with the belief that: Prompts are nuanced and opaque user requests, which require the same capabilities as traditional HTTP requests including secure handling, intelligent routing, robust observability, and integration with backend (API) systems for personalization – all outside business logic. Engineered with purpose-built LLMs, Arch handles the critical but undifferentiated tasks related to the handling and processing of prompts, including detecting and rejecting jailbreak attempts, intelligently calling "backend" APIs to fulfill the user's request represented in a prompt, routing to and offering disaster recovery between upstream LLMs, and managing the observability o

Show HN: Svgg – Turn raw SVG into image link https://svgg.link November 9, 2024 at 10:24PM

Show HN: 0x4c – Information Collections https://0x4c.quest November 9, 2024 at 10:10PM

Show HN: HyperTAG, AI-Powered Telegram Bot That Summarizes URLs & YouTube Links https://ift.tt/PV2fDuC November 8, 2024 at 10:29PM

Show HN: Fixthisbug.de – AI Code Fixes with Local LLM for Privacy For fun (and learning) I've let an AI built FixThisBug.de, an AI-selfpowered code fixing tool that's different from typical AI coding assistants as it uses a local Ollama instance with the qwen2.5 model. Key Features: - AI build: build entirely with AI, over several iterations via v0 and cursor. - Local Processing: Uses qwen2.5 model through Ollama for code analysis and fixes - Dual Language: Full support for English and German interfaces - "Free Tier": Limited daily fixes for casual users - "Pro Access": Unlimited fixes for authenticated users (just for fun, its free :) ) - Privacy Compliant: GDPR-compliant & hosted in Germany Tech Stack: - Frontend: Next.js 15.0, React 19 - Backend: Supabase + Next.js API Routes - - AI: Local Ollama instance running qwen2.5 - Auth: Supabase Auth with HCaptcha - Infrastructure: German servers for EU compliance To add a little extra to the project: Unlike

Show HN: AIBest.Tools – Discover the Best AI Tools Discover the latest and the best AI tools of 2024 in AIBest.Tools and stay ahead of the curve https://aibest.tools November 8, 2024 at 09:04PM

Show HN: Mdsf, a Codeblock Formatter for Markdown https://ift.tt/UXoOmPD November 8, 2024 at 08:23PM

Show HN: ChatGPT for calorie tracking. Frictionless diet and exercise tracking Hi, I'm Steve and I've built this mobile app to solve my very long-standing problem of not consistently using any calorie tracking apps due to the poor UX (many clicks, too much friction). So, although I am not the best UI/UX designer, I have tried to remove friction at every corner with Journable. This applies to the 1. Tracking experience: Chat-based interface (think ChatGPT) to log food/exercise 2. Onboarding experience: No login screen, no measurements or goals, straight to the main chat window 3. Photo entries: Just take a picture of your plate and done That said, I'm not the best UI/UX designer so I would really appreciate any feedback on the app, and I welcome any and all comments & suggestions. Should I make it easier? Faster? Simpler? Does it need more color? Keen to hear it all! https://ift.tt/l5Q2ZpV November 8, 2024 at 01:22AM

Show HN: Intelligent Browser for Web Automation Powered by AI Hey HN this is Daniel, I'm excited to share Airtop with the community! Airtop enables AI agents to seamlessly browse and automate any website — even ones with complex authentication like MFA or OAuth. Whether you need to scrape, interact with dynamic content, or automate tasks across multiple browsers, Airtop's cloud-based infrastructure makes it scalable and accessible. Why Airtop? — AI-Driven Web Automation: Automate interactions with any site through natural language commands even if they include human-in-the-loop scenarios. — Authentication Ready: Airtop handles websites requiring authentication, allowing bots to perform complex tasks. — Scalability: Easily manage and deploy tasks, whether it's one browser or a thousand. — Compliance: Airtop ensures your data is handled with the highest security, availability, and privacy standards, giving you peace of mind while automating sensitive tasks. You can check it a

Show HN: BemiDB – Postgres read replica optimized for analytics https://ift.tt/yIPVpzn November 7, 2024 at 11:25PM

Show HN: GitQuill – free cross-platform GUI for Git, inspired by GitKraken https://ift.tt/TO0Lsym November 7, 2024 at 03:43AM

Show HN: Last CLI tool you will need https://ift.tt/RM2ZVzI November 7, 2024 at 02:08AM

Statewide ‘Daylighting Law’ Warnings Begin Nov. 11, 2024 By Madhu Unnikrishnan Parking this close to an intersection could soon get you a warning. Next year, you could face a fine. On Nov. 11, 2024, we will begin issuing written warnings for vehicles parked within 20 feet of any crosswalk in the direction of approaching traffic. For example, you could receive a warning if you park less than 20 feet in front of a stop sign. We’re doing this to comply with the statewide “Daylighting Law” (Assembly Bill 413). It went into effect at the beginning of 2024. Starting Jan. 1, 2025, we will begin issuing citations to comply with California law. Fines will start at $40. This law... Published November 06, 2024 at 07:00AM https://ift.tt/sj2mBi1

Show HN: Samsar One Version One is now live Hi all, 6 months ago I started building out an app which combines all the SoTA gen-ai models out there into one platform which anyone could use to create 2-4 min long videos starting from scratch, starting from an idea. I received a ton of feedback from HN community & others along the way. Today excited to announce version one of app.samsar.one, a platform which allows anyone to easily and consistently create long, coherent and consistent generative-ai videos while picking and choosing their model starting from merely an idea. https://app.samsar.one/ October 31, 2024 at 05:06PM

Show HN: NewsCatcher's Hyperlocal News API – Granular City-Level News Feeds We’ve launched NewsCatcher’s Hyperlocal News API to provide city-level news feeds for market analysis, localized apps, and data analytics. Why We Built It: Aggregating hyperlocal news is complex. Local news comes from diverse sources, many covering national topics, making it hard to isolate local events like transit updates, crime, extreme weather alerts, or infrastructure projects. Searching by location alone can lead to irrelevant results, especially with city names that overlap or match common words (e.g., Orange, Lake). What It Does: Our API provides precise, location-based news by processing 185K articles daily and tagging each with its associated_town down to the town level with 92% accuracy. Covering 31,000 U.S. locations, it uses advanced NLP to accurately associate location names, even when they’re common words. It enables you to: - Access near-real-time, location-focused news feeds - Filter by top

Show HN: I wrote an open-source browser alternative for Computer Use for any LLM Hey HN, I made Browser-Use, an open-source tool that lets (all Langchain supported) LLMs execute tasks directly in the browser just with function calling. It allows you to build agents that interact with web elements using natural language prompts. We created a layer that simplifies website interaction for LLMs by extracting xPaths and interactive elements like buttons and input fields (and other fancy things). This enables you to design custom web automation and scraping functions without manual inspection through DevTools. Hasn't this been done a lot of times? Good question, as a general SaaS tool yes, but I think a lot of people are going to try to make their own web automation agents from scratch, so the idea is to provide groundwork/library for the hard part so that not everyone has to repeat these steps: - parse html in a LLM friendly way (clickable items + screenshots) - provide a nice function

Show HN: A free multiviewer to watch major news events like elections Hey HN! I'm a Product Manager at the FT in the UK, and VidGrid is something I've been working on for years in my own time. It's just got a major update just in time for the election. The idea is a way to watch lots of different news streams at the same time, as if you're in a control room or news gallery for the very latest info. I tried to prioritise usability and speed. All streams are third-party sourced (from broadcaster's own links). You can now sign up for an account to save/favourite your own streams, and it has better keyboard and drag and drop support. I've also fixed a ton of bugs from the last version. Happy to answer questions about it, or about news media at this time of year in general! Enjoy, and have a good evening. https://vidgrid.tk.gg November 5, 2024 at 09:13PM

Show HN: HN Push – Web push notifications for top stories on Hacker News I created HN Push to help reduce the urge to refresh Hacker News constantly. Since I rely on HN for real-time tech news, I wanted an efficient way to stay informed without having to check the site. Receiving summaries with Apple Intelligence was an added bonus. The source code is available on GitHub[^1]. [^1]: https://ift.tt/41NYzhJ https://www.hnpush.com November 4, 2024 at 08:47PM

Show HN: Sesh – Simplified Server-Side Caching for Next.js https://ift.tt/tjd5u9X November 4, 2024 at 10:21PM

Show HN: Cmaxz – weather radar map viewer https://ift.tt/6HPpUMm November 4, 2024 at 09:12PM

Show HN: BladeEvader – a game you play by moving your real head https://ift.tt/GoBzDEb November 3, 2024 at 09:34PM

Show HN: Outcheckr- Webpage outbound link enumerator with threading Outcheckr enumerates all outbound links present in a webpage, now faster with multi-threading support. https://ift.tt/9OegYZ3 November 3, 2024 at 11:22PM

Show HN: I built a shadcn visual playground I'm excited to introduce Robust Design Systems – a tool to make creating and managing design systems easier than ever. With the visual component editor, you can customize shadcn component variants without touching any code. When you're done, simply export the code instantly! I'd love to hear your feedback and see how I can make it even better! https://ift.tt/otXpAex November 3, 2024 at 10:15PM

Show HN: Small site to look up HTTP status codes https://statuscode.xyz/ November 3, 2024 at 12:04AM

Show HN: Someday, Open-Source Calendly Alternative for Gmail / Google App Script Free and open-source. Simple alternative to cal.com / calendly, built on Google-App-Script for Gmail users. Built with modern technologies like React, TypeScript, Shadcn/UI, and Vite. https://ift.tt/osG4Q9i November 2, 2024 at 11:04PM

Show HN: OpenQuest, connect with people around a shared goal for a short time Hey everyone! I built a little side project called OpenQuest over the last three weeks, and I'm looking for some feedback to see if it's worth taking further. The idea is simple: it's a place to create a chat room where you can connect with people (a maximum of 8) who have the same goal as you, for a short time (7 days for now). Think of it as a way to stay motivated, hold each other accountable, or simply work together with new people on something specific. Some examples can be: - Following a programming course - Reading a book - Getting back to the gym - Cleaning up your home - Shopping for a mechanical keyboard For example, here's a room I created to get things going: https://ift.tt/wfGste4 Why did I build this? Mostly as a response to what the internet feels like these days. Social media is to me an overwhelmingly negative time waster, where it feels like we're uniting more around thin

Show HN: X.infer-Framework agnostic computer vision inference I spent the past 3 weeks building x.infer, a Python package that lets you run computer vision inference on a framework of choice. It currently supports models from transformers, Ultralytics, Timm, vLLM and Ollama. Combined, this covers over 1000+ computer vision models. You can easily add your own model. Repo - https://ift.tt/JkGDeU0 Colab quickstart - https://ift.tt/ISPsX0w... Why did I make this? It's mostly just for fun. I wanted to practice some design pattern principles I picked up from the past. The code is still messy though but it works. Also, I enjoy playing around with new vision models, but not so much learning about the framework it's written with. I'm working on this during my free time. Contributions/feedback are more than welcome! Hope this also helps you (especially newcomers) to experiment and play around with new vision models. https://ift.tt/JkGDeU0 November 2, 2024 at 10:41PM

Show HN: I created a minimalist pastebin clone using Go, Htmx, and PostgreSQL https://ift.tt/LezMTdQ November 1, 2024 at 09:26PM

Show HN: Exploring Russian Election Interference with Graphiti Hi HN, we're Jack and Daniel from Zep. We've built a visual exploration tool and AI assistant for analyzing Russian election interference in the run-up to next week's US elections. The Explorer uses Graphiti, Zep's open-source temporal Knowledge Graph library. Graphiti autonomously creates dynamic, temporally-aware knowledge graphs representing complex, evolving relationships between entities. To offer users a detailed view of Russian state operations and related topics, we populated the graph with over 50+ sources. These include US DOJ indictments, research by US and foreign governments, research by non-governmental organizations, and media articles. Using the graph, you can explore which US organizations and individuals are implicated in these efforts and learn how private entities (such as OpenAI, Meta, and others) have responded. Two operations stand out in this dataset: Doppelganger and Tenet Media. - D