The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Darwin – Automate Your GitHub Project with AI
Hey HN!
I've been working on a project called Darwin that I'm thrilled to share with you.<p>Darwin is essentially your GitHub agent powered by large language models (LLMs). It checks out your projects, understands them through natural language prompts, and automates tasks such as fixing issues, documenting code, reviewing pull requests, and more.<p>What drove me to create Darwin was a desire to harness the power of LLMs in a way that's seamlessly integrated with the tools I use daily. The motivation came from my curiosity about what could be possible when writing code that understands code.
Darwin stands out because it's designed for developers who want to leverage AI without needing deep expertise in LLMs or prompt engineering. It offers:<p>- hands-off approach to automate routine development tasks.<p>- Novel and creative ways of making LLMs work for you<p>- A unique API for each project, allowing for customized automation tools.<p>Currently, Darwin is in alpha. It's functional, with users able to connect their repositories, define tools, and run tasks. I'm especially interested in feedback at this stage — everything from output quality to user experience. Every project starts with a $5 free budget to try it out, and while payment isn't implemented yet, I'm keen to hear your thoughts.<p>The vision for Darwin is not just about automation but creating a more productive, creative, and enjoyable development experience. I believe we're just scratching the surface of what's possible with AI in software development, and I'm excited to see where we can take this.<p>For those interested, I'm looking for alpha testers and feedback. If you're curious about automating your GitHub workflow or want to push the limits of what AI can do for development, Darwin might be for you.
Check it out and let me know what you think!
Show HN: Free Certificate Monitoring via RSS
Show HN: Free Certificate Monitoring via RSS
Show HN: Free Certificate Monitoring via RSS
Show HN: R2R – Open-source framework for production-grade RAG
Hello HN, I'm Owen from SciPhi (<a href="https://www.sciphi.ai/" rel="nofollow">https://www.sciphi.ai/</a>), a startup working on simplifying˛Retrieval-Augmented Generation (RAG). Today we’re excited to share R2R (<a href="https://github.com/SciPhi-AI/R2R">https://github.com/SciPhi-AI/R2R</a>), an open-source framework that makes it simpler to develop and deploy production-grade RAG systems.<p>Just a quick reminder: RAG helps Large Language Models (LLMs) use current information and specific knowledge. For example, it allows a programming assistant to use your latest documents to answer questions. The idea is to gather all the relevant information ("retrieval") and present it to the LLM with a question ("augmentation"). This way, the LLM can provide answers (“generation”) as though it was trained directly on your data.<p>The R2R framework is a powerful tool for addressing key challenges in deploying RAG systems, avoiding the complex abstractions common in other projects. Through conversations with numerous developers, we discovered that many were independently developing similar solutions. R2R distinguishes itself by adopting a straightforward approach to streamline the setup, monitoring, and upgrading of RAG systems. Specifically, it focuses on reducing unnecessary complexity and enhancing the visibility and tracking of system performance.<p>The key parts of R2R include: an Ingestion Pipeline that transforms different data types (like json, txt, pdf, html) into 'Documents' ready for embedding. Next, the Embedding Pipeline takes text and turns it into vector embeddings through various processes (such as extracting text, transforming it, chunking, and embedding). Finally, the RAG Pipeline follows the steps of the embedding pipeline but adds an LLM provider to create text completions.<p>R2R is currently in use at several companies building applications from B2B lead generation to educational tools for consumers.<p>Our GitHub repo (<a href="https://github.com/SciPhi-AI/R2R">https://github.com/SciPhi-AI/R2R</a>) includes basic examples for application deployment and standalone use, demonstrating the framework's adaptability in a simple way.<p>We’d love for you to give R2R a try, and welcome your feedback and comments as we refine and develop it further!
Show HN: R2R – Open-source framework for production-grade RAG
Hello HN, I'm Owen from SciPhi (<a href="https://www.sciphi.ai/" rel="nofollow">https://www.sciphi.ai/</a>), a startup working on simplifying˛Retrieval-Augmented Generation (RAG). Today we’re excited to share R2R (<a href="https://github.com/SciPhi-AI/R2R">https://github.com/SciPhi-AI/R2R</a>), an open-source framework that makes it simpler to develop and deploy production-grade RAG systems.<p>Just a quick reminder: RAG helps Large Language Models (LLMs) use current information and specific knowledge. For example, it allows a programming assistant to use your latest documents to answer questions. The idea is to gather all the relevant information ("retrieval") and present it to the LLM with a question ("augmentation"). This way, the LLM can provide answers (“generation”) as though it was trained directly on your data.<p>The R2R framework is a powerful tool for addressing key challenges in deploying RAG systems, avoiding the complex abstractions common in other projects. Through conversations with numerous developers, we discovered that many were independently developing similar solutions. R2R distinguishes itself by adopting a straightforward approach to streamline the setup, monitoring, and upgrading of RAG systems. Specifically, it focuses on reducing unnecessary complexity and enhancing the visibility and tracking of system performance.<p>The key parts of R2R include: an Ingestion Pipeline that transforms different data types (like json, txt, pdf, html) into 'Documents' ready for embedding. Next, the Embedding Pipeline takes text and turns it into vector embeddings through various processes (such as extracting text, transforming it, chunking, and embedding). Finally, the RAG Pipeline follows the steps of the embedding pipeline but adds an LLM provider to create text completions.<p>R2R is currently in use at several companies building applications from B2B lead generation to educational tools for consumers.<p>Our GitHub repo (<a href="https://github.com/SciPhi-AI/R2R">https://github.com/SciPhi-AI/R2R</a>) includes basic examples for application deployment and standalone use, demonstrating the framework's adaptability in a simple way.<p>We’d love for you to give R2R a try, and welcome your feedback and comments as we refine and develop it further!
Show HN: R2R – Open-source framework for production-grade RAG
Hello HN, I'm Owen from SciPhi (<a href="https://www.sciphi.ai/" rel="nofollow">https://www.sciphi.ai/</a>), a startup working on simplifying˛Retrieval-Augmented Generation (RAG). Today we’re excited to share R2R (<a href="https://github.com/SciPhi-AI/R2R">https://github.com/SciPhi-AI/R2R</a>), an open-source framework that makes it simpler to develop and deploy production-grade RAG systems.<p>Just a quick reminder: RAG helps Large Language Models (LLMs) use current information and specific knowledge. For example, it allows a programming assistant to use your latest documents to answer questions. The idea is to gather all the relevant information ("retrieval") and present it to the LLM with a question ("augmentation"). This way, the LLM can provide answers (“generation”) as though it was trained directly on your data.<p>The R2R framework is a powerful tool for addressing key challenges in deploying RAG systems, avoiding the complex abstractions common in other projects. Through conversations with numerous developers, we discovered that many were independently developing similar solutions. R2R distinguishes itself by adopting a straightforward approach to streamline the setup, monitoring, and upgrading of RAG systems. Specifically, it focuses on reducing unnecessary complexity and enhancing the visibility and tracking of system performance.<p>The key parts of R2R include: an Ingestion Pipeline that transforms different data types (like json, txt, pdf, html) into 'Documents' ready for embedding. Next, the Embedding Pipeline takes text and turns it into vector embeddings through various processes (such as extracting text, transforming it, chunking, and embedding). Finally, the RAG Pipeline follows the steps of the embedding pipeline but adds an LLM provider to create text completions.<p>R2R is currently in use at several companies building applications from B2B lead generation to educational tools for consumers.<p>Our GitHub repo (<a href="https://github.com/SciPhi-AI/R2R">https://github.com/SciPhi-AI/R2R</a>) includes basic examples for application deployment and standalone use, demonstrating the framework's adaptability in a simple way.<p>We’d love for you to give R2R a try, and welcome your feedback and comments as we refine and develop it further!
Show HN: AboutIdeasNow – search /about, /ideas, /now pages of 7k+ personal sites
Hi HN!<p>It’s hard to find interesting people to work with on your ideas.<p>Our solution: index the /about, /ideas, /now pages of 1000s of personal websites. There are thousands of cool personal sites out there, with amazing ideas on them, but there’s nowhere to easily search through. So we built a simple site that indexes 7k+ personal sites [0]. We were inspired by Derek Sivers’ Now page movement [1] and other IndieWeb directories [2], but we figured that it would be more useful if we:<p>* Let you search directly across personal sites without having to visit them<p>* Take the content from 3 specific pages, /about, /now and /ideas, to structure everything<p>* Define /ideas pages as a space to articulate things you want to work on<p>We hope this’ll be a cool place for people to find others to collaborate with - would love your feedback. If you’d like your site to appear at the top, add it via the form and add a last updated date of today (any format). It’s completely open source (MIT) and open to contributions [3]!<p>Peter & Louis<p>[0] gathered from: 1) <a href="https://nownownow.com" rel="nofollow">https://nownownow.com</a> and similar sites 2) checking all HN posts since 2020 with more than 100 upvotes<p>[1] <a href="https://nownownow.com" rel="nofollow">https://nownownow.com</a><p>[2] <a href="https://personalsit.es" rel="nofollow">https://personalsit.es</a><p>[3] <a href="https://github.com/lindylearn/aboutideasnow">https://github.com/lindylearn/aboutideasnow</a>
Show HN: AboutIdeasNow – search /about, /ideas, /now pages of 7k+ personal sites
Hi HN!<p>It’s hard to find interesting people to work with on your ideas.<p>Our solution: index the /about, /ideas, /now pages of 1000s of personal websites. There are thousands of cool personal sites out there, with amazing ideas on them, but there’s nowhere to easily search through. So we built a simple site that indexes 7k+ personal sites [0]. We were inspired by Derek Sivers’ Now page movement [1] and other IndieWeb directories [2], but we figured that it would be more useful if we:<p>* Let you search directly across personal sites without having to visit them<p>* Take the content from 3 specific pages, /about, /now and /ideas, to structure everything<p>* Define /ideas pages as a space to articulate things you want to work on<p>We hope this’ll be a cool place for people to find others to collaborate with - would love your feedback. If you’d like your site to appear at the top, add it via the form and add a last updated date of today (any format). It’s completely open source (MIT) and open to contributions [3]!<p>Peter & Louis<p>[0] gathered from: 1) <a href="https://nownownow.com" rel="nofollow">https://nownownow.com</a> and similar sites 2) checking all HN posts since 2020 with more than 100 upvotes<p>[1] <a href="https://nownownow.com" rel="nofollow">https://nownownow.com</a><p>[2] <a href="https://personalsit.es" rel="nofollow">https://personalsit.es</a><p>[3] <a href="https://github.com/lindylearn/aboutideasnow">https://github.com/lindylearn/aboutideasnow</a>
Show HN: AboutIdeasNow – search /about, /ideas, /now pages of 7k+ personal sites
Hi HN!<p>It’s hard to find interesting people to work with on your ideas.<p>Our solution: index the /about, /ideas, /now pages of 1000s of personal websites. There are thousands of cool personal sites out there, with amazing ideas on them, but there’s nowhere to easily search through. So we built a simple site that indexes 7k+ personal sites [0]. We were inspired by Derek Sivers’ Now page movement [1] and other IndieWeb directories [2], but we figured that it would be more useful if we:<p>* Let you search directly across personal sites without having to visit them<p>* Take the content from 3 specific pages, /about, /now and /ideas, to structure everything<p>* Define /ideas pages as a space to articulate things you want to work on<p>We hope this’ll be a cool place for people to find others to collaborate with - would love your feedback. If you’d like your site to appear at the top, add it via the form and add a last updated date of today (any format). It’s completely open source (MIT) and open to contributions [3]!<p>Peter & Louis<p>[0] gathered from: 1) <a href="https://nownownow.com" rel="nofollow">https://nownownow.com</a> and similar sites 2) checking all HN posts since 2020 with more than 100 upvotes<p>[1] <a href="https://nownownow.com" rel="nofollow">https://nownownow.com</a><p>[2] <a href="https://personalsit.es" rel="nofollow">https://personalsit.es</a><p>[3] <a href="https://github.com/lindylearn/aboutideasnow">https://github.com/lindylearn/aboutideasnow</a>
Show HN: Psfiles – a CLI tool to monitor file system activity of a Linux process
Psfiles is a simple utility to view file system activity of Linux processes.<p>Features:<p>- start new process or attach to existing one and trace its file system activity,<p>- output results to standard output or save results to file,<p>- custom results sorting and filtering.
Show HN: This website is hosted on DNS
Hey HN!<p>I'm excited to share something I've been working on: a way to set up and launch websites directly through the domain control panel. It allows anyone with a domain name to create, publish, and edit basic websites directly from the domain control panel without any traditional hosting providers or coding knowledge. This narrows the gap for non-technical people looking to publish simple personal and small business websites.<p>This is also the first TWA (triweb application) on the triweb platform (<a href="https://triweb.com" rel="nofollow">https://triweb.com</a>) we are working on. Triweb currently has limited functionality, and this app is mostly just a showcase of how TWAs and triweb containers work. We have an exciting lineup of upcoming features and a unique, simple vision of the decentralized web without the overhyped web3 technologies. We hope that one day triweb will become a standard platform for local-first, browser-based decentralized web applications.
Show HN: Functional UI Kit – twin Figma and React component libraries
Hey Hackers! My name is Alex and I’ve been working on this project for the past 8 months with the support of Figma Creator Fund. I’d love to hear your thoughts from your experience working with designers & component libraries.<p>I started out in design and later got into coding, so I understand both sides really well. I did UX Design for 12 years at startups, at my own studio and at Wix, and then worked as a front-end dev at Wix for 2 more years.<p>I've noticed a common problem: most component libraries work great for devs but not so well for designers.<p>In my experience working with big teams, I've felt this frustration firsthand. Instead of focusing on making products, we end up arguing over small details and terms.<p>In Functional UI Kit, each comp has dedicated story in Storybook. Copy pasting from Dev Mode in Figma just works, Figma variables and CSS variables match, auto Layout is mirroring the same box model structure & the CSS architecture shields you from style collisions.<p>It leverages all the latest Figma features to the MAX. Including the latest: Annotations, and of course: Dark Mode.<p>I hope you try it and let me know what you think.
Show HN: Nekoweb – a retro static web hosting
Show HN: Nekoweb – a retro static web hosting
Show HN: Nekoweb – a retro static web hosting
Show HN: Nekoweb – a retro static web hosting
Show HN: Reverse-Engineering a Switch Lite with 1,917 wires
Hey Hackers. This is a project I solo-developed that turns completed PCB assemblies into an easy to use boardview with some accompanying boardscans. There are lots of easier and better ways of doing this, but this is an experimentation to do it as cheaply as possible, with the highest quality and lowest chance of errors. The technical details are in the link.<p>Most public boardviews are almost entirely the result of industrial espionage, other than a few encrypted subscription based software platforms that provide extensive access. The process output is released as donationware, as my main concern is that even released as a low-cost purchase, there is a very strong culture to share this type of information at no cost. I would like to have a more sophisticated suggested donation system adaptive to user country, but I wasn't able to find a good solution.<p>In terms of 'good startup ideas', I don't think this is one of them. The very high level of soldering skill required makes it difficult to scale, and the prevailing piracy culture makes it challenging to monetize. My main advantage is that costs are very low now that I have the entire thing working. Other than forge ahead at a loss and hope for the best, or to pivot hard leveraging the imaging technology, I'm not sure what other options I have. It feels too complicated and repetitive for shoft-form video content. If you have any feedback, questions, suggestions, etc., I'd love to hear them.
Show HN: Reverse-Engineering a Switch Lite with 1,917 wires
Hey Hackers. This is a project I solo-developed that turns completed PCB assemblies into an easy to use boardview with some accompanying boardscans. There are lots of easier and better ways of doing this, but this is an experimentation to do it as cheaply as possible, with the highest quality and lowest chance of errors. The technical details are in the link.<p>Most public boardviews are almost entirely the result of industrial espionage, other than a few encrypted subscription based software platforms that provide extensive access. The process output is released as donationware, as my main concern is that even released as a low-cost purchase, there is a very strong culture to share this type of information at no cost. I would like to have a more sophisticated suggested donation system adaptive to user country, but I wasn't able to find a good solution.<p>In terms of 'good startup ideas', I don't think this is one of them. The very high level of soldering skill required makes it difficult to scale, and the prevailing piracy culture makes it challenging to monetize. My main advantage is that costs are very low now that I have the entire thing working. Other than forge ahead at a loss and hope for the best, or to pivot hard leveraging the imaging technology, I'm not sure what other options I have. It feels too complicated and repetitive for shoft-form video content. If you have any feedback, questions, suggestions, etc., I'd love to hear them.
Show HN: Reverse-Engineering a Switch Lite with 1,917 wires
Hey Hackers. This is a project I solo-developed that turns completed PCB assemblies into an easy to use boardview with some accompanying boardscans. There are lots of easier and better ways of doing this, but this is an experimentation to do it as cheaply as possible, with the highest quality and lowest chance of errors. The technical details are in the link.<p>Most public boardviews are almost entirely the result of industrial espionage, other than a few encrypted subscription based software platforms that provide extensive access. The process output is released as donationware, as my main concern is that even released as a low-cost purchase, there is a very strong culture to share this type of information at no cost. I would like to have a more sophisticated suggested donation system adaptive to user country, but I wasn't able to find a good solution.<p>In terms of 'good startup ideas', I don't think this is one of them. The very high level of soldering skill required makes it difficult to scale, and the prevailing piracy culture makes it challenging to monetize. My main advantage is that costs are very low now that I have the entire thing working. Other than forge ahead at a loss and hope for the best, or to pivot hard leveraging the imaging technology, I'm not sure what other options I have. It feels too complicated and repetitive for shoft-form video content. If you have any feedback, questions, suggestions, etc., I'd love to hear them.