Show HN: News-briefing-generator – Local LLM-powered news digest https://ift.tt/JEdAGcF

Show HN: News-briefing-generator – Local LLM-powered news digest Hey HN, I created a tool to generate personalized news briefings from RSS/Atom feeds using local LLMs through Ollama. It currently works in two modes: fully automatic or with an interactive review where you can select which "main topics of the day" to include in your briefing. The result is a HTML document with summaries for each topic. https://ift.tt/AQhEc3P March 1, 2025 at 12:15AM

Show HN: Globstar – Open-source static analysis toolkit https://ift.tt/QSHLp29

Show HN: Globstar – Open-source static analysis toolkit Hey HN! We’re Jai and Sanket, co-founders of DeepSource (YC W20). We're open-sourcing Globstar ( https://ift.tt/YiQUcMe ), a static analysis toolkit that lets you easily write and run custom code quality and security checkers in YAML [1] or Go [2]. After 5+ years of building AST-based static analyzers that process millions of lines of code daily at DeepSource, we kept hearing a common request from customers: "How do we write custom checks specific to our codebase?" AppSec and DevOps teams have a lot of learned anti-patterns and security rules they want to enforce across their orgs, and being able to do that without being a static analysis expert, came up as an important want. We initially built an internal framework using tree-sitter [3] for our proprietary infrastructure-as-code analyzers, which enabled us to rapidly create new checkers. We realized that making the framework open-source could solve this problem for everyone. Our key insight was that writing checkers isn't the hard part anymore. Modern AI assistants like ChatGPT and Claude are excellent at generating tree-sitter queries with very high accuracy. We realized that the tree-sitters' gnarly s-expression syntax isn’t a problem anymore (since the AI will be doing all the generation anyway), and we can instead focus on building a fast, flexible, and reliable checker runtime around it. So instead of creating yet another DSL, we use tree-sitter's native query syntax. Yes, the expressions look more complex than simplified DSLs, but they give you direct access to your code's actual AST structure – which means your rules work exactly as you'd expect them to. When you need to debug a rule, you're working with the actual structure of your code, not an abstraction that might hide important details. We've also designed Globstar to have a gradual learning curve: The YAML interface works well for simple checkers, and the Go Interface can handle complex scenarios when you need features like cross-file analysis, scope resolution, data flow analysis, and context awareness. The Go API gives you direct access to tree-sitter bindings, so you can write arbitrarily complex checkers on day one. Key features: - Written in Go with native tree-sitter bindings, distributed as a single binary - MIT-licensed - Write all your checkers in a “.globstar” folder in your repo, in YAML or Go, and just run “globstar check” without any build steps - Multi-language support through tree-sitter (20+ languages today) We have a long way to go and a very exciting roadmap for Globstar, and we’d love to hear your feedback! [1] https://ift.tt/81FnBT0 [2] https://ift.tt/c4R3ysX [3] https://ift.tt/eqnMZpJ March 1, 2025 at 12:12AM

Show HN: SenseFeedback – AI-powered social media sentiment analysis https://ift.tt/IHrwSig

Show HN: SenseFeedback – AI-powered social media sentiment analysis https://ift.tt/1muF0B9 February 28, 2025 at 08:55PM

Show HN: Ranked Search for Semi-Structured Data https://ift.tt/sAt4V6E

Show HN: Ranked Search for Semi-Structured Data We’ve been working on a search problem that requires querying both text and numbers simultaneously. For example, in a dataset of clothing items with descriptions and prices, a search for “slim pants for $20” should prioritize skinny jeans for $25 over slim pants for $50 because they are semantically similar and the price is closer. I’ve found that standard embedding models struggle with numerical ordering, while text-to-SQL methods rely on exact matches and often filter out too many results. To solve this, we built a system designed specifically for structured datasets like CSVs or tables. Here’s a demo link where you can upload a small CSV to try out (no login required): https://ift.tt/eO7TVPl . Unlike most RAG approaches, we process each column independently, handling text with embeddings and numbers with custom scoring. When a user submits a query, we parse it into relevant fields—for instance, extracting “slim pants” as the description and “20” as the price. We then compute cosine similarity between the description embeddings and “slim pants” while also calculating the percent error between the user’s price input and the numerical field. These individual similarity scores are then combined across all columns to generate a final ranking. Right now, our system works best with well-structured data, so some preprocessing is often needed. We’re working on improving this by detecting and restructuring messy data automatically, such as pivoting columns or extracting attributes from large text fields. We’re also adding feedback mechanisms, like a thumbs up/down system, to refine future search results based on user input. I’d love to hear about your experiences with similar search challenges and would appreciate any feedback! https://ift.tt/eO7TVPl February 28, 2025 at 12:57AM

Show HN: Superglue – open source API connector that writes its own code https://ift.tt/Dt0caeZ

Show HN: Superglue – open source API connector that writes its own code Hi HN, we’re Stefan and Adina, and we’re building superglue ( https://superglue.cloud ). superglue allows you to connect to any API/data source and get the data you want in the format you need. It’s an open-source proxy server which sits between you and your target APIs. Thus, you can easily deploy it into your own infra. If you’re spending a lot of time writing code connecting to weird APIs, fumbling with custom fields in foreign language ERPs, mapping JSONs, extracting data from compressed CSVs sitting on FTP servers, and making sure your integrations don’t break when something unexpected comes through, superglue might be for you. Here's how it works: You define your desired data schema and provide basic instructions about an API endpoint (like "get all issues from Jira"). superglue then does the following: - Automatically generates the API configuration by analyzing API docs. - Handles pagination, authentication, and error retries. - Transforms response data into the exact schema you want using JSONata expressions. - Validates that all data coming through follows that schema, and fixes transformations when they break. We built this after noticing how much of our team's time was spent building and maintaining data integration code. Our approach is a bit different to other solutions out there because we (1) use LLMs to generate mapping code, so you can basically build your own universal API with the exact fields that you need, and (2) validate that what you get is what you’re supposed to get, with the ability to “self-heal” if anything goes wrong. You can run superglue yourself ( https://ift.tt/MfYbOzh - license is GPL), or you can use our hosted version ( https://ift.tt/gvKw0sH ) and our TS SDK (npm i @superglue/client). Here’s a quick demo: https://www.youtube.com/watch?v=A1gv6P-fas4 You can also try out Jira and Shopify demos on our website ( https://superglue.cloud ) Excited to share superglue with everyone here—it's early so you'll probably find bugs, but we'd love to get your thoughts and see if others find this approach useful! https://ift.tt/MfYbOzh February 28, 2025 at 12:20AM

Show HN: Instantly Translate Manga – TranslateManga https://ift.tt/X4ZvCHn

Show HN: Instantly Translate Manga – TranslateManga Since I was young, I've loved anime, and over the years, manga has brought me joy, given me courage, and sparked excitement in my heart. However, as I read more, I realized that many of these manga weren't translated at all. I also came across some AI-based translation tools, but the results often fell short. So, I decided to create a tool that allows manga fans to read and enjoy their favorite manga, no matter the language or whether a translation team is available. This product has just been launched, and there are certainly areas that can be improved. However, with time, I'm confident it will only get better. You're welcome to try it out and share your valuable feedback! https://ift.tt/kopm4QI February 24, 2025 at 09:39PM

Show HN: Open-O3:Exponentially Improve LLM Accuracy via Probabilistic Resampling https://ift.tt/UyoDIVj

Show HN: Open-O3:Exponentially Improve LLM Accuracy via Probabilistic Resampling https://ift.tt/60gFXmb February 26, 2025 at 09:35PM

Show HN: Lotad, an Open-Source DuckDB Differ for Data Exploration https://ift.tt/6Kb2hmd

Show HN: Lotad, an Open-Source DuckDB Differ for Data Exploration Lotad makes comparing DuckDB files effortless. Get started with a simple setup command that generates a config YAML file tailored to your needs. The tool creates a comprehensive DuckDB output file containing: High-level change summaries per table Detailed table deltas Complete schema difference analysis For tables with drift, Lotad generates dedicated comparison tables that preserve the original schema while adding an observed_in column to track data origins. Lotad is under active development, with support for additional database types on the roadmap. It's actively being worked on and I do have expanding the number of supported Databases on the roadmap. https://ift.tt/HjP1qXk February 26, 2025 at 10:53PM

Show HN: My new wiki for Silicon Graphics stuff https://ift.tt/7NUdyqK

Show HN: My new wiki for Silicon Graphics stuff I also run IRIXNet. I'm here to share my newest SGI-related project. https://ift.tt/H4wpXFm February 25, 2025 at 11:46PM

Show HN: Tach – Visualize and Untangle Your Python Codebase https://ift.tt/1ymeBuX

Show HN: Tach – Visualize and Untangle Your Python Codebase Hey everyone! We're Evan and Caelean, and we're the authors of Tach. Tach gives you the tools to build a modular monolith in Python: visibility into the state of your dependencies, as well as the tools to fix them. Since our last Show HN ( https://ift.tt/SbB1lvJ ) we've shipped support for layers, third party dependencies, visualizations, and more. Tach is: * Open source (MIT) and completely free * Fast (written in Rust ) * In use by teams at NVIDIA, PostHog, and more As your team and codebase grows, code gets tangled up. This hurts developer velocity, and increases cognitive load for engineers. One way Tach differs from existing systems that handle this problem (build systems, import linters, etc) is in it's ability to be incrementally adopted and its runtime speed. If you struggle with dependencies, onboarding new engineers, or a massive codebase, Tach is for you! We built it with developers in mind - with clean integrations into Git, CI/CD, and IDEs, and the performance for it to be effective in any form factor. https://ift.tt/oFtZA9k February 25, 2025 at 11:34PM

Show HN: I built an app to stop me doomscrolling by touching grass https://ift.tt/lTifvm4

Show HN: I built an app to stop me doomscrolling by touching grass i wanted to change the habit of reaching for my phone in the morning and doomscrolling away an hour so i built an app to help me. now i have to literally touch grass before accessing my most distracting apps the app is built in swiftui, uses the screen time apis provided by apple and google vision to recognise grass or not i'd love to get your thoughts on the concept. https://touchgrass.now/ February 24, 2025 at 07:15PM

Show HN: Bhumi–OSS Python Library w Rust Underhead for 2.5x Faster LLM Inference https://ift.tt/yafZ9iQ

Show HN: Bhumi–OSS Python Library w Rust Underhead for 2.5x Faster LLM Inference Read the full blogpost at https://ift.tt/EWdKRDz (click on reader to see the technical breakdown!) AI inference should be fast, but in practice it’s painfully slow. Inference bottlenecks slow down LLM-powered chatbots and AI workflows everywhere. I built Bhumi to fix that. Bhumi is a Python library designed for developers, yet its performance-critical core is implemented in Rust (via PyO3) for near-native speed. This hybrid approach delivers up to 2.5x faster response times across providers like OpenAI, Anthropic, and Gemini—without changing the underlying model. THE PROBLEM: SLOW AI INFERENCE Most LLM clients suffer from three main issues: 1. Batch Processing Overhead – Clients wait for the full response instead of streaming data as it’s ready. 2. Inefficient Buffers – Default buffer sizes aren’t tuned for AI-generated text. 3. Validation Bottlenecks – Tools like Pydantic slow down structured response handling. Bhumi tackles these challenges with a smarter architecture that blends Python’s ease of use with Rust’s raw speed. HOW BHUMI MAKES AI FASTER 1. Rust-Based Streaming: Python’s async is useful, but integrating Rust through PyO3 brings near-native performance. Streaming inference starts instantly, cutting response times by up to 2.5x. 2. Smarter Buffer Management: Quality-Diversity algorithms (like MAP-Elites) dynamically discover optimal buffer sizes, boosting throughput by roughly 40%. 3. Replacing Pydantic with Satya: Pydantic was a performance sink. I built Satya—a Rust-backed validation library—that accelerates structured outputs dramatically. PERFORMANCE BENCHMARKS: • OpenAI: 2.5x faster response times • Anthropic: 1.8x faster • Gemini: 1.6x faster • Minimal extra memory overhead Bhumi is provider-agnostic, allowing you to switch between OpenAI, Anthropic, Groq, and more with a simple config change. USING BHUMI (WITH TOOL USE & STRUCTURED OUTPUTS) Bhumi makes tool integration effortless. For example, here’s how you can register a weather tool in Python: import asyncio from bhumi.base_client import BaseLLMClient, LLMConfig async def get_weather(location: str) -> str: return f”The weather in {location} is 75°F” async def main(): config = LLMConfig(api_key=“sk-…”, model=“openai/gpt-4o-mini”) client = BaseLLMClient(config) client.register_tool(name=“get_weather”, func=get_weather) response = await client.completion([{“role”: “user”, “content”: “What’s the weather in SF?”}]) print(response[“text”]) asyncio.run(main()) WHAT’S NEXT? I’m actively working on: • Supporting More Providers & Models • Adaptive Streaming Optimizations • Advanced Structured Outputs & Tooling Bhumi is a Python-first library powered by a Rust underhead for performance. Check out Bhumi on GitHub at https://ift.tt/FVYpWjK or reach out at me@rachit.ai. https://bhumi.trilok.ai February 24, 2025 at 11:04PM

Show HN: OmniTools–A Self-Hosted Suite of Open Source Tools for Everyday Tasks https://ift.tt/81oH9A7

Show HN: OmniTools–A Self-Hosted Suite of Open Source Tools for Everyday Tasks It’s 2025, and somehow, there’s still no good self-hosted alternative to sites like ILoveIMG.com or OnlineTools.com... until now. OmniTools is here to fill that gap! It’s a free web-based, open-source self-hosted platform that brings together all your favorite online tools in one place—fully self-hosted and ad-free. Project: https://ift.tt/LJwFhIV Why Omni Tools? Completely FREE & Open-Source – No hidden fees, ever. Self-Hosted – Keep control of your data, no tracking, no nonsense. All Your Favorite Tools in One Place – Image, coding, file utilities and more! Beta Version – Just launched, and I need your feedback to make it even better! https://ift.tt/LJwFhIV February 23, 2025 at 10:28PM

Show HN: Mapping historical markers around the world https://ift.tt/XPpOTtZ

Show HN: Mapping historical markers around the world I saw the 'map of torii' post yesterday and thought y'all might like to see the small app I've been working on that uses HMDB.org data to map historical markers around the world. HMDB has been aggregating markers for over 15 years and back when I was living out of my van and traveling full-time I wanted to get notified whenever I passed one, so I built a mobile app around that. I think historical markers are underrated - as a physical marker they make history tangible. Rather than reading about history from a classroom, you get the opportunity to see and engage with it at the source. If you're already nearby, they are often worth the stop to learn more. Since releasing the iOS app a few years ago, I've been able to enhance the markers with summaries (which makes reading the content a lot more palatable), and converting them to audio, so you can listen to markers when you're driving. Yesterday I officially released the android app, with the same features as the iOS app. https://ift.tt/U03iW6f February 23, 2025 at 11:58PM

Show HN: SQL Premier League – Learn SQL with Sports Data https://ift.tt/vMzNtn3

Show HN: SQL Premier League – Learn SQL with Sports Data Hey HN, I built SQL Premier League – a site where you solve SQL challenges using real IPL cricket data. Instead of querying boring datasets (employees, sales, etc.), you write SQL queries to analyze real IPL matches—find top run scorers, best finishers, clutch bowlers, and more! The website is open-source as well : https://ift.tt/8JIYpAv Would love to hear your feedback! https://ift.tt/SwdfsUG February 23, 2025 at 10:39PM

Show HN: I Built a Free Appointment Scheduler for Small Businesses https://ift.tt/56d9Dfw

Show HN: I Built a Free Appointment Scheduler for Small Businesses https://adviplanner.com February 23, 2025 at 08:42PM

Show HN: Course on Building Full-Stack Chrome Extensions with React and Node.js https://ift.tt/qFvPaD9

Show HN: Course on Building Full-Stack Chrome Extensions with React and Node.js I've been working in the extension space on a variety of products for a number of years now and decided to put together a course on how everything I wish I knew when I first started out. It goes through building an entire "product", meaning UI, API, and extension, all communicating with each other. It covers a lot of topics I get asked about often as well such as extension-level authentication, injecting React apps into web pages via content scripts, and a bunch more. https://ift.tt/48ugYSx February 23, 2025 at 12:58AM

Show HN: Japanese City Name Generator – Using a Simple 3-Layer MLP https://ift.tt/brMmSxw

Show HN: Japanese City Name Generator – Using a Simple 3-Layer MLP I trained and deployed my first model: a Japanese city name generator using just a 3-layer MLP under the hood. It runs in the browser fully locally on the onnx runtime. Trained on <2,000 real Japanese city names, what's interesting is that on this simple task the simple MLP performed better than more complex models which tended to overfit and generate existing names. https://citygen.freemanjiang.com February 22, 2025 at 11:05PM

Show HN: Tradofire, a fun way to learn crypto trading risk-free https://ift.tt/AOiWrcs

Show HN: Tradofire, a fun way to learn crypto trading risk-free Hey HN, I have been building this for the last couple years and probably spent way too much time. First I wanted to make an automated trading strategy based on crypto coins breaking support and resistance lines but after writing a whole system and backtesting infra I realized it doesnt work :( So here it is now as an app where you can learn to trade crypto based on these signals. Some key features are 1. Real-Time Market Analysis: See when coins break support/resistance levels or suddenly spike. 2. Paper Trading with Leverage: Test your trading strategies without risking real money. 3. Performance and Leaderboards: See your paper trading performance and compare with others. I dont know honestly if this will ever make any money but just sharing and hoping some folks like it. If you like it please tell me what else I can add. Cheers Sumeru PS: The app is iOS only for now (Android can come soon if there is demand) https://ift.tt/EWJ4Mez February 22, 2025 at 02:53AM

Show HN: DSBG – A Static Site Generator That Fast-Tracks Your Digital Presence https://ift.tt/OG96brH

Show HN: DSBG – A Static Site Generator That Fast-Tracks Your Digital Presence The ethos behind it is to automate your digital presence as much as possible, while retaining control over the created content. To that end, the following features are available: Easy installation; Support for Markdown & HTML source files; Automatic tag generation from paths ; built-in tag filtering; Client-side fuzzy search over all content; Automatic RSS feed generation; Watch mode with automatic rebuild for continuous feedback; 3 different themes, with the ability to add your own via custom CSS; Automatic share buttons for major social networks; Easy to extend with analytics, comments, and more. https://ift.tt/yVJXsOv February 22, 2025 at 01:39AM

Show HN: Txeo – A Modern C++ Wrapper for TensorFlow https://ift.tt/Sqv9kLc

Show HN: Txeo – A Modern C++ Wrapper for TensorFlow Txeo is a lightweight and intuitive C++ wrapper for TensorFlow, designed to simplify TensorFlow C++ development while preserving high performance and flexibility. Built entirely with Modern C++, Txeo allows developers to use TensorFlow with the ease of a high-level API, eliminating the complexity of its low-level C++ interface. https://ift.tt/TVndDIO February 21, 2025 at 11:40PM

Show HN: I presented a novel efficient streaming algorithm https://ift.tt/reISaVQ

Show HN: I presented a novel efficient streaming algorithm This paper has been accepted to KDD2025. https://ift.tt/gbK84C1 February 21, 2025 at 11:37PM

Show HN: I made a free compliance audit tool for websites to avoid fines https://ift.tt/tgXheBn

Show HN: I made a free compliance audit tool for websites to avoid fines Hey HN. I'm Zack, and spent a week building this side project called PACT because I couldn't find anything like it out there for free. Of course, I made it free and no signup required. It audits your website to surface any privacy or compliance issues. I used a pre-made data scraper to surface the compliance issues, then used Claude to present the results and offer suggestions to fix. LMK what you think. Cheers! https://ai-pact.com/ February 21, 2025 at 03:42AM

Show HN: Benchmarking VLMs vs. Traditional OCR https://ift.tt/0UWRuGL

Show HN: Benchmarking VLMs vs. Traditional OCR Vision models have been gaining popularity as a replacement for traditional OCR. Especially with Gemini 2.0 becoming cost competitive with the cloud platforms. We've been continuously evaluating different models since we released the Zerox package last year ( https://ift.tt/CcgtQPH ). And we wanted to put some numbers behind it. So we’re open sourcing our internal OCR benchmark + evaluation datasets. Full writeup + data explorer here: https://ift.tt/86qw9lG Github: https://ift.tt/EsdCmWL Huggingface: https://ift.tt/9uimhaP Couple notes on the methodology: 1. We are using JSON accuracy as our primary metric. The end goal is to evaluate how well each OCR provider can prepare the data for LLM ingestion. 2. This methodology differs from a lot of OCR benchmarks, because it doesn't rely on text similarity. We believe text similarity measurements are heavily biased towards the exact layout of the ground truth text, and penalize correct OCR that has slight layout differences. 3. Every document goes Image => OCR => Predicted JSON. And we compare the predicted JSON against the annotated ground truth JSON. The VLMs are capable of Image => JSON directly, we are primarily trying to measure OCR accuracy here. Planning to release a separate report on direct JSON accuracy next week. This is a continuous work in progress! There are at least 10 additional providers we plan to add to the list. The next big roadmap items are: - Comparing OCR vs. direct extraction. Early results here show a slight accuracy improvement, but it’s highly variable on page length. - A multilingual comparison. Right now the evaluation data is english only. - A breakdown of the data by type (best model for handwriting, tables, charts, photos, etc.) https://ift.tt/86qw9lG February 21, 2025 at 01:49AM

Show HN: WinCse – Integrating AWS S3 with Windows Explorer https://ift.tt/fPBg8Te

Show HN: WinCse – Integrating AWS S3 with Windows Explorer WinCse is an application that integrates AWS S3 buckets with Windows Explorer. Utilizing WinFsp and the AWS SDK, WinCse allows you to treat S3 buckets as part of your local file system, making file management simpler. The application is currently in development, with plans for additional features and improvements. https://ift.tt/LOjdAua February 21, 2025 at 12:53AM

Show HN: Bounty Prompt – AI-Powered Open Source Burp Suite Extension https://ift.tt/XNgPG1j

Show HN: Bounty Prompt – AI-Powered Open Source Burp Suite Extension Bounty Prompt is a Open Source Burp Suite extension developed by Bounty Security that leverages advanced AI technology integrated via Burp AI. It enables users to generate intelligent security testing prompts by analyzing selected HTTP requests and responses from various sources within Burp Suite. The extension supports a wide range of HTTP tags, allowing you to automatically include specific parts of HTTP traffic (such as headers, parameters, bodies, and cookies) in your prompts, streamlining both automated and manual penetration testing workflows. https://ift.tt/z5juBO9 February 20, 2025 at 08:21PM

Show HN: A new fork of OpenDeepResearcher with DeepSeek R1 https://ift.tt/BZXrwKz

Show HN: A new fork of OpenDeepResearcher with DeepSeek R1 https://www.youtube.com/watch?v=aEOu9P4_2cU February 20, 2025 at 02:45AM

Show HN: Mastra – Open-source JS agent framework, by the creators of Gatsby https://ift.tt/KOwZLzq

Show HN: Mastra – Open-source JS agent framework, by the creators of Gatsby Hi HN, we’re Sam, Shane, and Abhi, and we’re building Mastra ( https://mastra.ai ), an open-source JavaScript SDK for building agents on top of Vercel’s AI SDK. You can start a Mastra project with `npm create mastra` and create workflow graphs that can suspend/resume, build a RAG pipeline and write evals, give agents memory, create multi-agent workflows, and view it all in a local playground. Previously, we built Gatsby, the open-source React web framework. Later, we worked on an AI-powered CRM but it felt like we were having to roll all the AI bits (agentic workflows, evals, RAG) ourselves. We also noticed our friends building AI applications suffering from long iteration cycles: they were getting stuck debugging prompts, figuring out why their agents called (or didn’t call) tools, and writing lots of custom memory retrieval logic. At some point we just looked at each other and were like, why aren't we trying to make this part easier, and decided to work on Mastra. Demo video: https://www.youtube.com/watch?v=8o_Ejbcw5s8 One thing we heard from folks is that seeing input/output of every step, of every run of every workflow, is very useful. So we took XState and built a workflow graph primitive on top with OTel tracing. We wrote the APIs to make control flow explicit: `.step()` for branching, `.then()` for chaining, and `.after()` for merging. We also added .`.suspend()/.resume()` for human-in-the-loop. We abstracted the main RAG verbs like `.chunk()`, `embed()`, `.upsert(),’ `.query()`, and `rerank()` across document types and vector DBs. We shipped an eval runner with evals like completeness and relevance, plus the ability to write your own. Then we read the MemGPT paper and implemented agent memory on top of AI SDK with a `lastMessages` key, `topK` retrieval, and a `messageRange` for surrounding context (think `grep -C`). But we still weren’t sure whether our agents were behaving as expected, so we built a local dev playground that lets you curl agents/workflows, chat with agents, view evals and traces across runs, and iterate on prompts with an assistant. The playground uses a local storage layer powered by libsql (thanks Turso team!) and runs on localhost with `npm run dev` (no Docker). Mastra agents originally ran inside a Next.js app. But we noticed that AI teams’ development was increasingly decoupled from the rest of their organization, so we built Mastra so that you can also run it as a standalone endpoint or service. Some things people have been building so far: one user automates support for an iOS app he owns with tens of thousands of paying users. Another bundled Mastra inside an Electron app that ingests aerospace PDFs and outputs CAD diagrams. Another is building WhatsApp bots that let you chat with objects like your house. We did (for now) adopt an Elastic v2 license. The agent space is pretty new, and we wanted to let users do whatever they want with Mastra but prevent, eg, AWS from grabbing it. If you want to get started: - On npm: npm create mastra@latest - Github repo: https://ift.tt/7uawi5s - Demo video: https://www.youtube.com/watch?v=8o_Ejbcw5s8 - Our website homepage: https://mastra.ai (includes some nice diagrams and code samples on agents, RAG, and links to examples) - And our docs: https://mastra.ai/docs Excited to share Mastra with everyone here – let us know what you think! https://ift.tt/7uawi5s February 19, 2025 at 10:25PM

Show HN: OpenAstra – Chat based open-source alternative to Postman https://ift.tt/a0R8Yyz

Show HN: OpenAstra – Chat based open-source alternative to Postman Hi HN, I'm excited to finally launch this project. While existing tools like Postman excel at API discovery and testing, they often require us to navigate complex interfaces, manually construct requests, etc. That's why I created OpenAstra. The core idea is to combine the visual richness of traditional API tools with the simplicity of a chat interface. Think of it as "Postman meets ChatGPT" - allowing us to interact with APIs through natural conversation while retaining core essential features of traditional API tools. If you want to test an endpoint or understand what it does? Just ask. The project is still in its early stages, and there's much more to build. I'd love to hear what features you'd find most valuable, and of course, pull requests are always welcome! https://ift.tt/msIpeUy February 19, 2025 at 10:59PM

Show HN: The One File I Created for Every Programming Language (10+ Years) https://ift.tt/tA3rJql

Show HN: The One File I Created for Every Programming Language (10+ Years) Throughout my career, while exploring different programming languages, I realized that having a quick reference was essential for refreshing my memory on the fly. So I developed a habit: for every new language I learned, I’d build a reference file (like python_reference.py) that documented everything from basic syntax to advanced features. Now, a decade later, these files have become my go-to resource. They’ve helped me study for interviews, revisit old projects after years, and now, in the AI era where generating code in unfamiliar languages is more common than ever, I think they’re more relevant than ever. A concise, straight to the point reference can be the difference between "it works" and "I actually understand why it works." I believe these references will be especially helpful for developers looking to pick up a new language quickly, without having to go through extensive courses or tutorials. I've updated most of the references, added some new ones, and made them open source. I've also put together a website where you can find them all: https://ift.tt/z4y8SDC Github Repo: https://ift.tt/sWC7yRE I’d love to hear your thoughts, and feel free to contribute if you have ideas or improvements! <3 https://referencecollection.com/ February 19, 2025 at 09:13PM

Show HN: A GPU-accelerated binary vector index https://ift.tt/oWp8De4

Show HN: A GPU-accelerated binary vector index This is a vector index I built that supports insertion and k-nearest neighbors (k-NN) querying, optimized for GPUs. It operates entirely in CUDA and can process queries on half a billion vectors in under 200 milliseconds. The codebase is structured as a standalone library with an HTTP API for remote access. It’s intended for high-performance search tasks—think similarity search, AI model retrieval, or reinforcement learning replay buffers. The codebase is located at https://ift.tt/o7dITBE . https://ift.tt/B81XI95 February 17, 2025 at 07:45AM

Show HN: Hacker News with AI-generated summaries https://ift.tt/pQMAKtC

Show HN: Hacker News with AI-generated summaries I built this clone of Hacker News to get a quick summary of articles before deciding to read them. Summaries are cached in localStorage. Not useful for links to social media sites. https://ift.tt/Sai6cns February 19, 2025 at 12:29AM

Show HN: I Built a FAANG Job Board – Only Jobs Scraped in the Last 24h https://ift.tt/uRgYeGr

Show HN: I Built a FAANG Job Board – Only Jobs Scraped in the Last 24h https://ift.tt/1qQS0Yf February 18, 2025 at 11:37PM

Show HN: Mind Map Wizard – Generate Infinite Mind Maps with AI, for Free (FOSS) https://ift.tt/XbROSt3

Show HN: Mind Map Wizard – Generate Infinite Mind Maps with AI, for Free (FOSS) Hi everyone, I want to share my newest project, Mind Map Wizard - a Text to Mind Map AI that transforms your text input into a detailed mind map in seconds. Just type in your topic and go. No account required! I want to get a solid overview of any possible topic in seconds. You don't need an account and there's no paid option. Features: - Simplicity: Only the essentials. Editing, sharing, downloading and creation history. All mind maps are stored locally in your browser. - Focus: Without any ads and an intuitive design, you can fully concentrate on your topics without distractions. -Local first: Data is stored locally, ensuring fast navigation and enhanced privacy. Check out this mind map I generated about Switzerland: https://ift.tt/sA0YNRp I’d love to hear your thoughts on how to improve Mind Map Wizard. Thanks for your support! GitHub link: https://ift.tt/VlPEWU9 https://ift.tt/l71DeQ0 February 18, 2025 at 12:23AM

Show HN: Ovadare – resolving AI agent conflicts in multi-agent platforms https://ift.tt/J1UdZtB

Show HN: Ovadare – resolving AI agent conflicts in multi-agent platforms https://ift.tt/sXnYcDd February 17, 2025 at 11:39PM

Show HN: XSLT and graphical outline viewer for your sitemap.xml https://ift.tt/oCwOYej

Show HN: XSLT and graphical outline viewer for your sitemap.xml You generated a sitemap.xml for Google with a list of every page on your website. Why not let humans look at it too? I was experimenting with Material UI and wanted to use it in a real project, so I made a graphical outline viewer and the necessary XSLT files so you can easily integrate it: save a file and add 1 line to the xml. Obviously, it works best if you have a nice hierarchical URL structure. The graphical viewer: https://ift.tt/KaR5MAf Integration instructions: https://ift.tt/wjPCqtO Demo: https://ift.tt/SQ8YXzv Source & credits: https://ift.tt/POHYc8a... https://ift.tt/wjPCqtO February 17, 2025 at 10:59PM

Show HN: Tools for Math Research https://ift.tt/z8u6NWV

Show HN: Tools for Math Research https://sugaku.net/ February 15, 2025 at 07:15AM

Show HN: B2B SaaS Go-to-Market Checklist https://ift.tt/G7xlM5R

Show HN: B2B SaaS Go-to-Market Checklist https://ift.tt/5VuhG21 February 17, 2025 at 05:40AM

Show HN: Air Traffic Control Radio and Chill Music for Focus https://ift.tt/BTLnJbI

Show HN: Air Traffic Control Radio and Chill Music for Focus https://ift.tt/RLCkhj2 February 17, 2025 at 04:36AM

Show HN: Hackyournews.com v2 https://ift.tt/YgmzhwX

Show HN: Hackyournews.com v2 A year and a half after I published https://ift.tt/EmRDdFJ , I've rewritten it to be neater and added support for more news sources. HackYourNews.com v1 had a great response on HN [1] and consistently sees ~2k weekly unique visitors. There were many long-standing requests that I wanted to fulfill (thanks for your patience!): a proper dark mode, correct rendering on mobile devices, and more cogent summaries. This rewrite is the result. gpt-4o-mini reduces the cost of summarization to an absurd degree, so it's now sustainable to keep this free service going! Someday, I hope to use the Batch API [2] to drive down costs even further. Enjoy. [1] https://ift.tt/9nU4QZj [2] https://ift.tt/fv7K4Ge February 16, 2025 at 07:46AM

Show HN: I developed a no code web scraper for effortless data extraction https://ift.tt/GmZiAQC

Show HN: I developed a no code web scraper for effortless data extraction https://ift.tt/cPKunBM February 17, 2025 at 01:04AM

Show HN: The news in the last 30, 14, 7, 3, or 1 days https://ift.tt/D0pCKVa

Show HN: The news in the last 30, 14, 7, 3, or 1 days I made this for when I come back from vacation and want to catch up on news. It's a bit of a simplistic LLM transformation on headlines and URLs that I store from RSS feeds. So it bugs out sometimes. But I think it might be useful to me. You can check out some of the prompts in the "debug" links. What do you think? https://ift.tt/oGImqwJ February 16, 2025 at 12:54PM

Show HN: Tech Brief – AI enhanced news reading https://ift.tt/X5Q0N7E

Show HN: Tech Brief – AI enhanced news reading I built this because I wanted it, and I now use it every day. It's a simple news site that gathers and summarises tech content and discussions, across multiple sources, providing tight, easily digestable summaries along with some simple tooling to support reading workflows. 1) Hourly updated homepage with the latest tech news across the web. 2) A simple < 3 min "News of the Hour", every hour, audio clip. 3) Summaries of HackerNews and Product Hunt, incl. comments and sentiment (more to come). 3) GitHub login with AI summaries of any releases made to your starred repos. 4) Read/Unread article status. 5) Simple swipe interface and keyboard support. 6) Simple Bookmark/Readling List, and Favourite tags (logged in) No Tracking. Fast. Mobile Friendly. Easy sharing. https://tech.brief.page/ February 16, 2025 at 07:28AM

Show HN: Blunderchess.net – blunder for your opponent every five moves https://ift.tt/kzjrUg1

Show HN: Blunderchess.net – blunder for your opponent every five moves blunderchess.net is an open source, peer-to-peer chess app where every five moves, players each get to make one blunder-move for their opponent https://ift.tt/rz6L8Qy February 16, 2025 at 07:22AM

Show HN: Edit Any Record on ATProto with History https://ift.tt/QDXb0RN

Show HN: Edit Any Record on ATProto with History https://ift.tt/xEnRIsL February 16, 2025 at 03:54AM

Show HN: I got frustrated with CRMs, so I'm building my own for startups https://ift.tt/nNDl6UG

Show HN: I got frustrated with CRMs, so I'm building my own for startups After trying a bunch of CRMs for my startup, I kept running into the same issues—overpriced plans that scale aggressively or bloated features that just slow me down. I wanted something simple, affordable, and actually built for startups, so I decided to build it myself: Leadchee.com. Fixed pricing, no nonsense. Curious—how do you all handle CRMs? Do you stick with the big players, go for niche tools, or build your own? Would love to hear your thoughts! https://leadchee.com February 14, 2025 at 10:55PM

Show HN: Live webcam metal pin toy simulation powered by WebGPU depth estimation https://ift.tt/vVJ37KG

Show HN: Live webcam metal pin toy simulation powered by WebGPU depth estimation https://ift.tt/tQWIuqR February 15, 2025 at 01:03AM

Show HN: A Valentine's Day experience for people who aren't celebrating https://ift.tt/n39aP4T

Show HN: A Valentine's Day experience for people who aren't celebrating Hey HN, I built justanotherday.lol today as a quick, fun project for people who aren't really into Valentine's Day. Just a lighthearted take on what some of us might be doing instead—scrolling Instagram, working late, or convincing ourselves that saving money is self-care. No signups, no fluff — just a simple site I put together in Next.js + Framer Motion in a bit of a hurry. Hope you find it fun. Let me know what you think! https://ift.tt/jeTWsDR February 14, 2025 at 11:06PM

Show HN: SQL Noir – Learn SQL by solving crimes https://ift.tt/Jwz5sBP

Show HN: SQL Noir – Learn SQL by solving crimes I built SQL Noir, an interactive detective game that challenges you to solve mysteries using real SQL queries. It’s fully open source, designed to give you a practical and immersive way to learn SQL while engaging with a narrative-driven mystery. https://www.sqlnoir.com February 14, 2025 at 04:49AM

Show HN: Dev SSO IdP, a mock single sign-on provider as a development aide https://ift.tt/b7ygBWP

Show HN: Dev SSO IdP, a mock single sign-on provider as a development aide Hi HN! This project grew out of my want for the development of my web UIs to not get hung up on integration with OpenID Connect single sign-on. SSO was only available in our stage and prod environments. Getting this integration laid down and tested fast, without having to jury-rig something in stage, would've been huge. And so I decided to build a solution myself. Hence, Dev SSO IdP. The vision for it is to mock all the features of an OIDC SSO server that would be pertinent to the development of web apps. To try it out: 1) Create a file called `.production.env` and paste in it the following 2 lines to start with: DEVSSOIDP_PERCENT_ENCODED_REDIRECT_URIS=http%3A%2F%2Flocalhost%3A5173 DEVSSOIDP_CLIENT_IDS=my_cool_app 2a) (with Node) Clone the repo with `git clone https://ift.tt/0eklFob `, then overwrite the project's `.production.env` with yours, then in the project's folder run `npm install`, then `npm start` 2b) (with Docker) Run `docker run -p 3000:3000 --rm --env-file .production.env bmcase/devssoidp:1.0.0` You can then see it at (and have your app redirect to) http://localhost:3000/authorize?response_type=code&client_id... You can add or change environment variables in `.production.env` in the likely case that its defaults don't apply to you. The GitHub readme goes into more detail on all of this. They say "be flexible in what you accept and strict in what you output". But Dev SSO IdP is intentionally strict in what it accepts so that I could catch issues faster. It raises an alarm in dev so you don't later get one in prod. This version I am comfortable designating v1.0.0. It has all the features needed for the OIDC code flow. I'd appreciate any advice, and in particular am interested in: * Would this actually be useful in your projects? Is there anything else it would need? * Do you use the OIDC implicit flow? I've never had reason to, and I understand it's regarded as a bad practice. But I worry I may be in a bubble and so I want to know if there's in fact a lot of folks out there who use the implicit flow. Aside, I'm open to work, and would be interested in bringing my full stack skills to your team (or the team of someone you want to do a favor for), in the Austin TX area or remotely. I'm happy to hear from you by email (ben@benswords.com) or LinkedIn ( https://ift.tt/mAjzB8J ). https://ift.tt/r2IzOdS February 14, 2025 at 03:23AM

Show HN: Add tool calling to any LLM https://ift.tt/hBWj7JU

Show HN: Add tool calling to any LLM https://ift.tt/TbyUQSf February 14, 2025 at 12:01AM

Show HN: Google, but Respects Your Privacy https://ift.tt/aWVQGKk

Show HN: Google, but Respects Your Privacy Ever feel like your searches are being watched or profiled? With Nool.quest , you can search anything online without the worry of your data being tracked or sold. It's a search engine that respects your privacy, giving you the freedom to explore the web on your terms. No ads, no surveillance, just results that matter to you. Enjoy the internet without compromising your freedom. https://nool.quest February 13, 2025 at 09:52PM

Show HN: Sort lines semantically using llm-sort https://ift.tt/9lTuvXO

Show HN: Sort lines semantically using llm-sort This is a small plugin I made for Simon Willison's llm utility. You can do things like: cat names.txt | llm sort -q "Which one of these names is best for a pet seagull?" cat books.txt | llm sort -q "Which book is more related to basic vs. advanced CS topics?" I see a lot of potential marrying LLMs with classic UNIX interfaces. https://ift.tt/zWpUDP5 February 11, 2025 at 10:25AM

Show HN: Game Bub – open-source FPGA retro emulation handheld https://ift.tt/gfvabmy

Show HN: Game Bub – open-source FPGA retro emulation handheld Hey HN, Over the past ~1.5 years, I built an open-source FPGA retro emulation handheld that can play Game Boy, Game Boy Color, and Game Boy Advance cartridges. To my knowledge, there isn't an existing open-source FPGA emulator that can play physical cartridges like this. One of my main goals was to do all of the pieces myself, and be able to understand every component of it, so I designed my own PCB, wrote the firmware, wrote a Game Boy and Game Boy Advance emulator for the FPGA (using the Chisel HDL), and designed a 3D-printed case. I detailed the design and development process in the linked post. It's quite long, but there are a lot of pictures and videos. Code and design files available on GitHub: https://ift.tt/0vefZrn , and an overview of the architecture: https://ift.tt/WdXEwQq... https://ift.tt/FfqICEh February 13, 2025 at 12:11AM

Show HN: CubeBistro – A Robotic Restaurant in a Cube https://ift.tt/QrVd17h

Show HN: CubeBistro – A Robotic Restaurant in a Cube Imagine a restaurant that fits in your office, city block, or even your home. Cubeistro is a fully automated, robotic restaurant inside a compact, futuristic cube. With ingredients delivered directly from farmers in cartridge-like boxes, we eliminate the need for traditional supply chains, reducing waste and maximizing efficiency. Orders are placed via an app or touchscreen, and food is delivered in color-coded lock boxes, keeping items warm or cold. No staff, no waste, just fresh food, and a new way to dine. Is anyone curious how this works? https://cubebistro.com/ February 12, 2025 at 10:57PM

Show HN: HypeBridge – Your Dedicated AI-Agent Driven Influencer Marketing Agency https://ift.tt/GO0uKT5

Show HN: HypeBridge – Your Dedicated AI-Agent Driven Influencer Marketing Agency https://ift.tt/5HyupgO February 12, 2025 at 04:02AM

Show HN: I open-sourced machine translation models for 12 rare languages https://ift.tt/tzN9cj5

Show HN: I open-sourced machine translation models for 12 rare languages You can test translation quality here https://ift.tt/PIpTvj0 https://ift.tt/nrFv32T February 12, 2025 at 04:07AM

Show HN: Community Detection on Bluesky https://ift.tt/SnNphIt

Show HN: Community Detection on Bluesky We ran the Leuven community detection algorithm on popular users on Bluesky (where the graph has edges determined by Jaccard similarity of a users' followers). We identified 118 communities and based on the names and descriptions of the top 10-20 users had LLMs generate title and descriptions for them. There are communities like "Feline enthusiasts", "Web Professionals", a bunch of NSFW ones and quite many communities are many different flavors of progressive/liberal activists. https://ift.tt/4dC5fhO February 12, 2025 at 03:39AM

Show HN: Colada for Claude https://ift.tt/uFadZzA

Show HN: Colada for Claude I actually enjoy Claude.ai's interface and artifacts implementation. I didn't want to lift and shift over to another LLM tool. So, to get past the daily limits, I decided to build a simple Chrome extension which continues conversations using your own Anthropic API key (or using our managed key). In short: - Get past Claude.ai conversation limits - Bring your own Anthropic API key - Optionally use our managed unlimited API key - Preserve conversation context - Bring project knowledge context into your extended convos - Reference web search results anytime by asking "Search the web" Let me know what you think. Open to any and all feedback. https://usecolada.com February 12, 2025 at 12:08AM

Show HN: WhisperCat – An Audio Recorder and Transcription Tool https://ift.tt/25uCTU0

Show HN: WhisperCat – An Audio Recorder and Transcription Tool Hi HN, I wanted to share my first open-source project with you all: WhisperCat . WhisperCat is a small desktop application for recording audio and transcribing it using OpenAI's Whisper API. I built this because I needed something simple and reliable for my own transcription workflows, and now I'm hoping it might be useful to others as well. It's still pretty early stage, but it works well for basic audio recording and transcription tasks. What It Does: Lets you record audio with your preferred microphone. Transcribes audio files automatically via Whisper (OpenAI's transcription API). Supports global hotkeys for recording (e.g., CTRL + R or a custom sequence like triple ALT). Runs in the background (system tray) when minimized. Has a basic microphone testing feature to help you pick the right device. Shows desktop notifications for events (e.g., when recording starts or errors happen). Platforms: WhisperCat is available for Windows and Linux , and there’s also an experimental macOS build you can try if you’re feeling adventurous: Experimental macOS Build You can download the latest release here: https://ift.tt/HupyIl5 Feedback is welcome! https://ift.tt/ls7euIC February 11, 2025 at 02:41AM

Show HN: Arelo – A simple, flexible file watcher for auto-restarting commands https://ift.tt/6YylIrq

Show HN: Arelo – A simple, flexible file watcher for auto-restarting commands arelo is a lightweight, language-agnostic file watcher that automatically runs a command when files change. It requires no configuration files; everything is controlled via simple command-line options. Easy to use: arelo -p '**/*.go' -- go run . Flexible file watching: Supports fsnotify (real-time), polling (for environments like WSL2), and fine-grained control with extended globbing (** and {js,ts,json}). Cross-platform and lightweight: Runs on Windows, macOS, and Linux without extra dependencies. Installation: - go install github.com/makiuchi-d/arelo@latest - Or download a prebuilt binary from GitHub Releases: https://ift.tt/JdXwLNW https://ift.tt/iqQn2al February 10, 2025 at 11:19PM

Show HN: AI Chat – unified chat sessions across OpenAI, Gemini, DeepSeek (go) https://ift.tt/k5eN0iW

Show HN: AI Chat – unified chat sessions across OpenAI, Gemini, DeepSeek (go) A simple Go package for unified AI chat management across OpenRouter, OpenAI, Google GenAI, and more, with support for tool calling and S3-compatible user sessions https://ift.tt/sVzcX70 February 10, 2025 at 11:53PM

Show HN: Locksmith – detect locks taken by Postgres migrations https://ift.tt/hzXo1Bm

Show HN: Locksmith – detect locks taken by Postgres migrations https://ift.tt/AbvT1id February 10, 2025 at 03:56AM

Show HN: Curatrs – Scheduled Programming for Podcasts https://ift.tt/qFUucDt

Show HN: Curatrs – Scheduled Programming for Podcasts Like many of us, I got tired of scrolling endlessly through podcast apps trying to find the right show for my commute. So I built Curatrs (curatrs.com) - it brings radio-style scheduled programming to podcast discovery. Instead of endless scrolling, you get podcasts programmed for specific times and durations. Currently in early MVP, built with Vite/Supabase, focused on making discovery more intentional and time-based. Would appreciate any feedback, especially from regular podcast listeners https://ift.tt/BzO75o9 February 10, 2025 at 02:53AM

Show HN: Neovim Plugin for iOS and macOS Development https://ift.tt/dvGrjZs

Show HN: Neovim Plugin for iOS and macOS Development Over two years ago, I began exploring whether it was possible to shift my iOS development to Neovim. It took me over six months to resolve all issues and figure out how to connect everything, creating an environment with all the features required for development. After that, I decided to develop my own plugin to enable others to do the same. Since then, I have been developing apps for iOS and macOS using Neovim, for both my professional work and personal projects with no issues. This change has significantly boosted my productivity, and I no longer have to deal with Xcode's flaws. I can accomplish 95% of my work without needing to open Xcode. Before that, it seemed impossible to develop for Apple platforms outside of Xcode. I'm proud that I was stubborn enough to make it work after all those failures along the way. Neovim is an amazing project <3. https://github.com/wojciech-kulik/xcodebuild.nvim February 9, 2025 at 07:46PM

Show HN: Lambda Core – Minimal Lambda Calculus in Every Language https://ift.tt/xsCn2h0

Show HN: Lambda Core – Minimal Lambda Calculus in Every Language Lambda Core is a collaborative project to implement the basics of lambda calculus (just booleans and church numerals) in every programming language! We now have 18 languages implemented. If your favorite language isn’t already in the repo, please add it! The instructions are simple, and it's a fun way to explore how different languages handle higher-order functions. Check out the GitHub link for details. I'd love your feedback and hope you'll join in! https://ift.tt/kx7Ee3j February 9, 2025 at 03:53AM

Show HN: I trained a custom LLM to create Apple Shortcuts https://ift.tt/xmu7Ywy

Show HN: I trained a custom LLM to create Apple Shortcuts Hi! This is a version 2.0 2x Context window 7-8x Faster Less hallucinations :) https://ift.tt/sMPJruo February 9, 2025 at 12:35AM

Show HN: FlashSpace – fast, open-source, macOS Spaces replacement https://ift.tt/cAh0xsB

Show HN: FlashSpace – fast, open-source, macOS Spaces replacement I've recently launched a new open-source project aimed at enhancing the experience of switching between Spaces/workspaces on macOS. The built-in Spaces feature is often slow and unfriendly. This project is designed to boost your productivity :). Enjoy! https://ift.tt/kxUGBg9 February 9, 2025 at 12:19AM

Show HN: A website that heatmaps your city based on your housing preferences https://ift.tt/06WI4mM

Show HN: A website that heatmaps your city based on your housing preferences For the past few months, I've been working on a website that answers two different questions: - Where in my city have the best travel times to all the things and people I care about? - Given a listing, how far is it from all the things and people I care about? Personally this was fueled by my own frustrations when I was apartment hunting in NYC. I was frustrating to have to juggle so many Google Maps tabs when I was evaluating a listing, and it was also annoying to not have full confidence that I was even searching in the right places. I wanted to be close to work, a Trader Joe's, and a major park. Given that public transportation networks can sometimes make close things hard to get to and far things easy to get to, it's not always obvious whether a neighborhood actually even fits my criteria or not! The overarching goal of theretowhere.com is to allow you to make more informed moving decisions while also making things more convenient than they are today. https://ibb.co/pBsX2HjN It can generate detailed travel time breakdowns for individual listings and addresses, making it easier to determine whether a listing is worth applying for without juggling Google Maps tabs. This is great for questions like “How far is this apartment from my friends, work and dancing gyms?” https://ibb.co/mVBjwPrJ It also has the powerful ability to heatmap a city based on which parts of it are close or not to the people and places you care about. This is great for questions like “Where in the city would I be reasonably close to work, friends and a woodworking studio?” https://ibb.co/vCynPSRK You can add these heatmaps to sites like Zillow and Streeteasy to make things super convenient (this was very fun to make). The main thing that's on my mind is whether this is useful or not. Like, is this something you would actually use? I also have other ideas I'd like to eventually intergrate into this (crime heatmaps, noise heatmaps, etc) https://ift.tt/KqVj0fi February 8, 2025 at 01:23AM

Show HN: A configuration management system for minimal *Nix environments https://ift.tt/uLykADC

Show HN: A configuration management system for minimal *Nix environments I built this thing to scratch my itch for a simpler alternative to Ansible and similar for basic jobs like setting up a dev env, building containers, and provisioning small fleets of servers. Grateful for feedback on the approach! A couple of friends and I have found it useful for day-to-day automation tasks and I'm wondering if there's enough utility in its ability to target minimal environments like Alpine containers or IoT devices to warrant fleshing out a proper 1.0 release. https://ift.tt/bAYj2K1 February 8, 2025 at 12:46AM

Show HN: Upsonic: An AI agent framework with client-server architecture https://ift.tt/1suSCpM

Show HN: Upsonic: An AI agent framework with client-server architecture Three months ago, we started developing an open source agent framework. We previously tried existing frameworks in our enterprise product but faced challenges in certain areas. Problems we experienced: * We risked our stateless architecture when we wanted to add an agented feature to our existing system. Current frameworks lack server-client architecture, requiring significant effort to maintain statelessness when adding an agent framework to your application. * Scaling problem - needed to write Docker configurations as existing frameworks lack official Docker support. Each agent in my application required a separate container (e.g., Twitter page analysis, website scraping, automatic documentation writing, etc.), necessitating individual agent deployment and health checks monitoring. * Needed LLM calls for simple tasks - both fast and cost-effective solutions. With increased model capabilities, the framework should offer this option. I could handle LLM calls myself, but structured outputs required extra work within task structure. Due to these problems, we decided to build a dockerized agent framework with server-client architecture. Though server-client architecture slowed development, we observe many benefits for users. We're developing a task-centric approach as we expect agents to complete simple tasks and assist with work. As tool support is crucial for completing tasks, we built a structure officially supporting MCP servers. Client-server architecture proved beneficial for MCP server stability. Finally, we prioritized simplicity in the framework, developing a structure where outputs are more easily coded with object responses. We'd be very happy if you could check our repo. I'd love to hear any questions you may have., https://ift.tt/OdaukGU February 7, 2025 at 11:02PM

Show HN: Embedding WebAssembly in QR Codes https://ift.tt/48vYtQJ

Show HN: Embedding WebAssembly in QR Codes https://ift.tt/0hIFsOm February 6, 2025 at 09:43PM

Show HN: Watch fascism unfold in realtime – an AI-powered tracker https://ift.tt/tlyUQNi

Show HN: Watch fascism unfold in realtime – an AI-powered tracker Hi HN, Wanted to share a project I made over the weekend - a real-time fascism tracker. The site fetches recent news from trusted sources, filters it for keywords related to fascism and the current US administration, and then sends it to GPT-4o for classification according to the 14 characteristics of fascism described by Dr. Lawrence Britt. With the rapid pace of news in the US, especially post-election, it’s hard to keep up. I built this site so you can quickly see important topics and draw parallels with similar historical events. Would love to hear your thoughts. - Ryan https://ift.tt/KNJcqh8 February 7, 2025 at 12:02AM

Show HN: A Minimalist Coffee Bean Rating System Built with Go and Htmx https://ift.tt/eD0PCnz

Show HN: A Minimalist Coffee Bean Rating System Built with Go and Htmx Hey HN! After years of experiencing hit-or-miss coffee bean purchases, I built a simple solution to crowdsource coffee bean ratings. The problem is straightforward: buying new coffee beans is a gamble, and with rising prices, a bad bag is both disappointing and costly. The solution is a no-frills web app built with Go, HTMX, and Tailwind CSS. No accounts required, no JavaScript frameworks, just a simple 5-star rating system for coffee beans. Technical Stack: - Backend: Go - Frontend: HTMX + Tailwind CSS - No user accounts (intentionally) - Progressive web app I deliberately chose HTMX over a JavaScript framework to keep things minimal and fast. The entire app is server-rendered with sprinkles of interactivity where needed. You can try it at RoastQuest.com and let me know what you think and how I can make it better. This is my first time using HTMX in production - happy to discuss the experience and trade-offs. https://roastquest.com February 6, 2025 at 10:49PM

Show HN: How good is your color vision? Find out in my new game https://ift.tt/d3MvJzI

Show HN: How good is your color vision? Find out in my new game https://ift.tt/64cu35m February 2, 2025 at 07:03AM

Show HN: Grammarly-like extension for any language https://ift.tt/xsqEWHR

Show HN: Grammarly-like extension for any language https://ift.tt/XMiIbW1 February 6, 2025 at 01:41AM

Show HN: Sveltos – Event-Driven Tool for Kubernetes Add-Ons and App Deployment https://ift.tt/4KZDE2V

Show HN: Sveltos – Event-Driven Tool for Kubernetes Add-Ons and App Deployment Hi HN, Managing Kubernetes add-ons, policies, and configurations across multiple clusters can feel like herding cats. That’s where Sveltos comes in—a lightweight, open-source tool to make managing fleets of Kubernetes clusters simple, scalable, and secure. What Can Sveltos Do? 1. Centralized Management – Deploy apps, add-ons, and policies from a single control plane, instead of setting up GitOps tooling on every cluster. A lightweight agent on each managed cluster keeps things efficient. 2. Security: Best of Push & Pull GitOps – Unlike traditional GitOps, which either requires exposing your clusters to external Git credentials (push) or setting up agents on each cluster (pull), Sveltos combines centralized GitOps management with secure pull-based configurations and push-based deployments—keeping credentials in a single, secure location. 3. Dynamic & Event-Driven Cluster Management – Just apply labels to a cluster, and Sveltos will automatically determine what apps, policies, and add-ons should be installed. You can even trigger actions based on real-time events, such as AI-driven insights or infrastructure changes. And from yesterday's release, Sveltos integrates with NATS to listen for any CloudEvents and dynamically respond by deploying resources. 4. Lightweight & Kubernetes-Native – Sveltos is built using Kubernetes-native concepts (CRDs, controllers) and runs with minimal resource overhead. Proactive Monitoring – Ensures clusters stay in their desired state, reapplying configurations as needed. How Are People Using Sveltos? 1. Database as a Service (DBaaS): Consistently deploy and manage database instances fleet-wide. 2. Fleet-Wide Add-On Management: Automate the deployment of tools like monitoring, logging, and security to all clusters at scale. 3. NATS Management: Deploy and monitor NATS clusters for message streaming. 4. API Gateway & Service Deployment: Automate workflows for exposing services with tools like Kong. 5. Custom Workflows: Whether enforcing fleet-wide security policies or orchestrating CI/CD pipelines, Sveltos adapts to your needs. One of the Ways Sveltos Works: 1. Label your clusters using Kubernetes label selectors. 2. Use YAML to define add-ons and policies to apply. 3. Let Sveltos dynamically configure clusters as they match the criteria. Watch Sveltos in Action: - An intro video to Sveltos from one of our happy users: https://www.youtube.com/watch?v=bsWEo79w09c&t=7s - Click-Through Demo of the UI: https://ift.tt/Sm5GNcB Star us on GitHub, it helps us grow and reach more people! https://ift.tt/7PiI35J Join the Community. We’d love your feedback and contributions! - Full Repo: https://ift.tt/DGzkq0e - Website: https://ift.tt/C1Xzxhw - LinkeIn: https://ift.tt/ySnjO2P - X: https://ift.tt/UBw65gy - Email: support@projectsveltos.io - Slack: https://ift.tt/LdB56ny... Thanks for reading, and we’d love to hear your thoughts! https://ift.tt/C1Xzxhw February 5, 2025 at 11:27PM

Show HN: I made a tool to help you save and execute commands in a directory https://ift.tt/znt7YE0

Show HN: I made a tool to help you save and execute commands in a directory Hi HN! A lot of times I end up with sets of commands I want to run in a project directory: building packages, running ansible to deploy things, cleaning up files, etc. Makefiles always felt rather overkill for this and I like having just a YAML file with the name, description, and commands that are available and for a menu to display with that information. This is that program. I had originally written it many years ago in Perl. I have been learning Go and this seemed like a great project to port. I hope you find it useful, thanks for reading! https://ift.tt/EigUjA8 February 5, 2025 at 11:05PM

Show HN: Haystack Code Reviewer – Perform code reviews on a canvas https://ift.tt/j26k8Ms

Show HN: Haystack Code Reviewer – Perform code reviews on a canvas Hi HN! We’re building Haystack Code Reviewer, a tool that lays out code diffs for a GitHub pull request on an interactive canvas. Instead of scrolling through diffs line-by-line, you can view all changes in a more connected, visual format – similar to viewing a call graph. We hope this will make it easier and less cognitively taxing to understand how different changes across files work together. For a quick overview, check out our short demo video: https://www.youtube.com/watch?v=QeOz70x0WPE . If you would like to give it a spin, head over to https://ift.tt/5xrfp6O , click the “Review pull request button” in the top toolbar, and load any pull request via URL or pick a pull request from a dropdown. We built Haystack Code Reviewer because we found pull requests difficult to review in a pure textual format — especially when hopping between multiple files or trying to break down complex changes. Oftentimes, pull request authors would have to specifically structure their commits so that code reviews would be easier to tackle, which is a time-consuming and error-prone process. Our goal is to make any pull request easy to understand at a glance, and reduce the effort needed from both reviewers and authors to craft a good code review. Haystack Code Reviewer works on private repositories! We have authentication to ensure that someone cannot open the server for your pull request without having access to that pull request on GitHub. For additional security, we plan to build self-hosting soon. Please contact us if you’re interested in this. Alternatively, a completely local option would be to download desktop Haystack and then navigate to your pull request from there. This is great for trying out the feature without exposing any data on the cloud! In the near future, we plan to: 1. Introduce step-by-step navigation to guide reviewers through each part of the changeset 2. Allow for self-hosting We’d love to hear your thoughts, suggestions, and any feedback on our approach or potential features! https://ift.tt/iWsPKqF February 5, 2025 at 12:02AM

Show HN: Mandarin Word Segmenter with Translation https://ift.tt/1AbaVo8

Show HN: Mandarin Word Segmenter with Translation I've built mandoBot, a web app that segments and translates Mandarin Chinese text. This is a Django API (using Django-Ninja and PostgreSQL) and a NextJS front-end (with Typescript and Chakra). For a sample of what this app does, head to https://ift.tt/3JVxP7L . This is my presentation of the first chapter of a classic story from the Republican era of Chinese fiction, Diary of a Madman by Lu Xun. Other chapters are located in the "Reading Room" section of the app. This app exists because reading Mandarin is very hard for learners (like me), since Mandarin text does not separate words using spaces in the same way Western languages do. But extensive reading is the most effective way to learn vocabulary and grammar. Thus, learning Mandarin by reading requires first memorizing hundreds or thousands of words, before you can even know where one word ends and the next word begins. I'm solving this problem by allowing users to input Mandarin text, which is then computationally segmented and machine translated by my server, which also adds dictionary definitions for each word and character. The hard part is the segmentation: it turns out that "Chinese Word Segmentation"[0] is the central problem in Chinese Natural Language Processing; no current solutions reach 100% accuracy, whether they're from Stanford[1], Academia Sinica[2], or Tsing Hua University[3]. This includes every LLM currently available. I could talk about this for hours, but the bottom line is that this app is a way to develop my full-stack skills; the backend should be fast, accurate, secure, well-tested, and well-documented, and the front-end should be pretty, secure, well-tested, responsive, and accessible. I am the sole developer, and I'm open to any comments and suggestions: roberto.loja+hn@gmail.com Thanks HN! [0] https://ift.tt/qeMR2b3 [1] https://ift.tt/gtH0iE6 [2] https://ift.tt/9zmBKFf [3] https://ift.tt/jVMBFpe https://ift.tt/GQom1ZL February 5, 2025 at 12:56AM

Show HN: Open-source schema based Change-Data-Capture utility for Postgres https://ift.tt/hetLKJ9

Show HN: Open-source schema based Change-Data-Capture utility for Postgres I am currently working on a Node.js utility for a schema-based approach on CDC for Postgres. It is a lightweight utility that you can plug on top of your existing WAL events service (eg. Debezium, WAL-listener...) and allows you to define schemas to listen to. Instead of listening to raw individual table-level events, you can aggregate those events into high-level schema events automatically. Conceptually, it is like having WAL events but on an SQL view, any modification to a table the view is based on would trigger a high-level event on the view itself. This has many real-world applications including: - Syncing your single source of truth (Postrges) to another store (eg. Elastic / Algolia...) - Have a reliable event-driven architecture where you can change the underlying data model while keeping the contract identical I was highly inspired by pgsync but wanted to build a lightweight, generic version of the idea that is not tied to any specific tech outside of Postgres. I am looking for early feedback on the idea to understand the traction and the direction I should give the project. https://ift.tt/ZCJxIXy February 4, 2025 at 04:06PM

Show HN: AI text editor with suggested edits in diff view https://ift.tt/N03CwEk

Show HN: AI text editor with suggested edits in diff view https://www.potext.com February 4, 2025 at 01:11AM

Show HN: Surf.new – An open-source alternative to OpenAI Operator https://ift.tt/xXFygZw

Show HN: Surf.new – An open-source alternative to OpenAI Operator https://surf.new February 3, 2025 at 10:28PM

Show HN: I Built a Platform to Buy and Sell GitHub Repositories https://ift.tt/2dOoj5A

Show HN: I Built a Platform to Buy and Sell GitHub Repositories Hey HN, I built a platform that allows developers to buy and sell GitHub repositories using private forking. The idea is to help indie developers, open-source maintainers, and teams monetize their work while ensuring buyers get fully functional projects with minimal hassle. Many developers create great projects but lack the time or resources to maintain them. Instead of letting them fade away, why not sell them to someone who wants to continue the work? Here is how it works: - Sellers list theis GitHub repos in the platform - Buyers purchase repos - Buyers automatically added as collaborators and can fork the repo Check it out here: https://gittrader.com https://ift.tt/eFbq9SV February 3, 2025 at 07:37AM

Show HN: Random Art Generator in Haskell https://ift.tt/9Z16gCd

Show HN: Random Art Generator in Haskell https://ift.tt/NG6YRrD February 3, 2025 at 03:41AM

Show HN: Chrome extension to run DeepSeek, LLMs and Whisper locally in browser https://ift.tt/pWlGk1j

Show HN: Chrome extension to run DeepSeek, LLMs and Whisper locally in browser Hi all, I open sourced my toy project that runs Generative AI models LOCALLY in the side panel of a Chrome extension. The Chrome extension uses Transformers.js to run models in browser under the hood. I've integrated and tested these models so far. \1. LLM: Llama 3, Phi 3.5, Qwen 2.5, SmolLM2 \2. Reasoning: DeepSeek R1 \3. Multimodal LLM: Janus \4. Speech-to-Text: Whisper On an M1 MacBook, DeepSeek R1 1.5B runs at ~30 tokens/sec If you're interested in, you can download the extension from chrome web store or clone my github repository. \1. chrome web store: https://ift.tt/GDwoBWA... \2. github: https://ift.tt/tcXhBRd \3. demo: https://www.youtube.com/watch?v=MSCDdFG5Lls It's my first react project. Feedback is always welcome! https://ift.tt/tcXhBRd February 3, 2025 at 12:49AM

Show HN: Groundhog AI Spring API https://ift.tt/rVCIy83

Show HN: Groundhog AI Spring API For anyone building weather-related AI apps, I am releasing an exciting iteration on last year’s model. My Groundhog API is trained on 130 years of data and makes use of 82 separate data sources. Similar to DeepSeek, it is completely open source and free to use. The primary use case is to make inferences about whether spring will come early or not, using a Mixture of Exports (MoE) approach, but surely others can be found if you are creative. Other use cases: - All predicting groundhogs - Where they all live - Whether they are “real” groundhogs or imposters Excited to see what people do with it! https://ift.tt/ZLPy0cf February 3, 2025 at 12:29AM

Show HN: I built a full mulimodal LLM by merging multiple models into one https://ift.tt/QEDrUla

Show HN: I built a full mulimodal LLM by merging multiple models into one https://ift.tt/wQBp2iF February 2, 2025 at 02:14PM

Show HN: ESP32 RC Cars https://ift.tt/A8gtTy6

Show HN: ESP32 RC Cars This is a projected I started that blends both the fun of playing a split screen multiplayer driving game and controlling real rc cars. The cars can also be controlled via bluetooth gamepads and is meant to be easily hackable. https://ift.tt/oOHEVgW February 2, 2025 at 01:51AM

Show HN: I hacked LLMs to work like scikit-learn https://ift.tt/nV7Th4K

Show HN: I hacked LLMs to work like scikit-learn Working with LLMs in existing pipelines can often be bloated, complex, and slow. That's why I created FlashLearn , a streamlined library that mirrors the user experience of scikit-learn. It follows a pipeline-like structure allowing you to "fit" (learn) skills from sample data or instructions, and "predict" (apply) these skills to new data, returning structured results. High-Level Concept Flow: Your Data --> Load Skill / Learn Skill --> Create Tasks --> Run Tasks --> Structured Results --> Downstream Steps Installation: pip install flashlearn Learning a New "Skill" from Sample Data Just like a fit/predict pattern in scikit-learn, you can quickly "learn" a custom skill from minimal (or no!) data. Here's an example where we create a skill to evaluate the likelihood of purchasing a product based on user comments: from flashlearn.skills.learn_skill import LearnSkill from flashlearn.client import OpenAI # Instantiate your pipeline "estimator" or "transformer", similar to a scikit-learn model learner = LearnSkill(model_name="gpt-4o-mini", client=OpenAI()) data = [ {"comment_text": "I love this product, it's everything I wanted!"}, {"comment_text": "Not impressed... wouldn't consider buying this."}, # ... ] # Provide instructions and sample data for the new skill skill = learner.learn_skill( data, task=( "Evaluate how likely the user is to buy my product based on the sentiment in their comment, " "return an integer 1-100 on key 'likely_to_buy', " "and a short explanation on key 'reason'." ), ) # Save skill to use in pipelines skill.save("evaluate_buy_comments_skill.json") Input Is a List of Dictionaries Simply wrap each record into a dictionary, much like feature dictionaries in typical ML workflows: user_inputs = [ {"comment_text": "I love this product, it's everything I wanted!"}, {"comment_text": "Not impressed... wouldn't consider buying this."}, # ... ] Run in 3 Lines of Code - Concurrency Built-in up to 1000 calls/min # Suppose we previously saved a learned skill to "evaluate_buy_comments_skill.json". skill = GeneralSkill.load_skill("evaluate_buy_comments_skill.json") tasks = skill.create_tasks(user_inputs) results = skill.run_tasks_in_parallel(tasks) print(results) Get Structured Results Here's an example of structured outputs mapped to indexes of your original list: { "0": { "likely_to_buy": 90, "reason": "Comment shows strong enthusiasm and positive sentiment." }, "1": { "likely_to_buy": 25, "reason": "Expressed disappointment and reluctance to purchase." } } Pass on to the Next Steps You can use each record’s output for downstream tasks such as storing results in a database or filtering high-likelihood leads: # Suppose 'flash_results' is the dictionary with structured LLM outputs for idx, result in flash_results.items(): desired_score = result["likely_to_buy"] reason_text = result["reason"] # Now do something with the score and reason, e.g., store in DB or pass to next step print(f"Comment #{idx} => Score: {desired_score}, Reason: {reason_text}") https://ift.tt/SDhMLFU February 1, 2025 at 11:39PM

Show HN: I re-designed interface for HN https://ift.tt/eCauHOm

Show HN: I re-designed interface for HN Any suggestions are appreciated, stack utilizes Gluestack UI ,Expo, React Native, and Cloudflare Pages. There is a known bug via touch scroll ability on Android, external keyboard's spacebar or mouse works correctly though, currently. If you know about a solution, let me know. Please note, this is just a prototype, it still has a lot of features to be included. I'd like to learn more about how people use HN and how Hacked could help, where other HN clients failed. https://ift.tt/wHjikuT February 2, 2025 at 12:11AM