Show HN: PipZap – Zapping the mess out of the Python dependencies https://ift.tt/xLI8pJO

Show HN: PipZap – Zapping the mess out of the Python dependencies https://ift.tt/oJ8Dms6 March 31, 2025 at 04:35AM

Show HN: A string Enum generator for Go lang https://ift.tt/KE5po0B

Show HN: A string Enum generator for Go lang https://ift.tt/CiBK0hz March 31, 2025 at 05:15AM

Show HN: Chip-8 emulator written in JavaScript https://ift.tt/PvhQi73

Show HN: Chip-8 emulator written in JavaScript https://ift.tt/HYOLT38 March 31, 2025 at 01:14AM

Show HN: I built a tool to add noise texture to your images https://ift.tt/JcDWlt5

Show HN: I built a tool to add noise texture to your images I'm excited to introduce Noise Tools – a simple yet powerful tool that lets you effortlessly add noise textures to your images. Whether you're a designer, artist, or just experimenting with aesthetics, Noise Tools helps you enhance your visuals with just a few clicks. Why I built this? I often found myself needing high-quality noise textures for design projects but struggled to find a quick and easy solution. So, I built Noise Tools to make the process easy for everyone! Features: Generate noise textures instantly Adjust intensity & styles No downloads or complicated settings Would love to hear your thoughts! Try it out and let me know what you think. Check it out here: noisetools.vercel.app https://ift.tt/nVTA7b8 March 27, 2025 at 01:12PM

Show HN: Job Application Bot by Ollama AI https://ift.tt/qCgDTp7

Show HN: Job Application Bot by Ollama AI JobHuntr.fyi is a macOS desktop app that uses Ollama-powered AI to apply for jobs on LinkedIn—automatically, 24/7. No OpenAI API key required. https://ift.tt/TBsbknX March 30, 2025 at 01:13AM

Show HN: I implemented Snake in a tmux config file https://ift.tt/ZPD1pgR

Show HN: I implemented Snake in a tmux config file https://ift.tt/qDeirC6 March 26, 2025 at 01:37PM

Show HN: zxc – terminal TLS intercepting proxy in Rust with tmux and Vim as UI https://ift.tt/nqFibjZ

Show HN: zxc – terminal TLS intercepting proxy in Rust with tmux and Vim as UI - Disk based storage. - Custom http/1.1 parser to send malformed requests. - http/1.1 and websocket support. Proxy: https://ift.tt/5Mh6sCI Vim: https://ift.tt/X7gDkEG https://ift.tt/5Mh6sCI March 29, 2025 at 12:31AM

Show HN: A FlashAttention backwards-over-backwards pass https://ift.tt/fPo4M5u

Show HN: A FlashAttention backwards-over-backwards pass https://ift.tt/oH0hgGB March 29, 2025 at 12:43AM

Show HN: Context7 – LLM Code Snippets from Docs in Minutes https://ift.tt/lXSZIGW

Show HN: Context7 – LLM Code Snippets from Docs in Minutes https://context7.com/ March 28, 2025 at 11:00PM

Show HN: My tiny web shell on my local PC https://ift.tt/SGAN3OH

Show HN: My tiny web shell on my local PC https://ift.tt/jBEqOTP March 28, 2025 at 01:34AM

Show HN: Xorq – open-source Python-first Pandas-style pipelines https://ift.tt/KyjU2oG

Show HN: Xorq – open-source Python-first Pandas-style pipelines Hi HN, Dan, Hussain and Daniel here… After years of struggling with data pipelines that worked in notebooks but failed in production, we decided to do something about it. We created xorq to eliminate the constant headaches of SQL/pandas impedance mismatch, runtime debugging, wasteful recomputations and unreliable research-to-production deployments that plague traditional pandas-style pipeline workflows. xorq is built on Ibis and DataFusion. We’d love your feedback and contributions. xorq is [Apache 2.0 licensed]( https://ift.tt/a0VdRWf ) to encourage open collaboration. Repo : https://ift.tt/IXgftwG Docs : https://docs.xorq.dev Roadmap Issues : https://ift.tt/IXgftwG You can get started `pip install xorq`. Or, if you use nix, you can simply run `nix run github:xorq-labs/xorq` and drop into an IPython shell. Demo video: https://youtu.be/jUk8vrR6bCw Here are some vignettes to look into next: 1. MCP Server + Flight + XGBoost: https://ift.tt/GbPU4w0 2. 1 DuckDB + 2 Writers + 1 Reader: https://ift.tt/kK496jt 3. OpenAI UDF: https://ift.tt/PXEh24v Some features to note: - Ibis-based multi-engine expression system: effortless engine-to-engine streaming - Cache expressions with `.cache` operator - Portable DataFusion-backed UDF engine with first class support for pandas dataframes - Serialize Expressions to and from YAML - Easily build Flight end-points by composing UDFs thanks for checking this out, and we’re here to answer any questions! https://ift.tt/eN6h3J7 March 27, 2025 at 10:57PM

Show HN: A difficult game to test your logic https://ift.tt/yMpnmoQ

Show HN: A difficult game to test your logic https://ift.tt/YxUtkMs March 24, 2025 at 07:17PM

Show HN: Taildrops – Free Tailwind CSS 4 code snippets https://ift.tt/ndt8fm9

Show HN: Taildrops – Free Tailwind CSS 4 code snippets Free Tailwind CSS 4 Components — and this is just the beginning! I’ve been sharing a bunch of free Tailwind CSS components on X, but honestly, they just keep getting buried in the timeline. It’s super frustrating when something you put effort into disappears so quickly. That’s why I decided to put everything on a website. Now you can easily find all the components I’ve shared in one place, and I’ll keep adding any new ones I create. It feels good to have a space where they won’t get lost. Check them out if you’re interested — I’d love to hear what you think! https://taildrops.com/ March 27, 2025 at 02:59AM

Show HN: I made an open source Kubernetes MCP Server to talk with K8s in English https://ift.tt/Sxmq597

Show HN: I made an open source Kubernetes MCP Server to talk with K8s in English A Model Context Protocol (MCP) server for Kubernetes that enables AI assistants like Claude, Cursor, and others to interact with Kubernetes clusters through natural language. ## Features ### Core Kubernetes Operations - [x] Connect to a Kubernetes cluster - [x] List and manage pods, services, deployments, and nodes - [x] Create, delete, and describe pods and other resources - [x] Get pod logs and Kubernetes events - [x] Support for Helm v3 operations (installation, upgrades, uninstallation) - [x] kubectl explain and api-resources support - [x] Choose namespace for next commands (memory persistence) - [x] Port forward to pods - [x] Scale deployments and statefulsets - [x] Execute commands in containers - [x] Manage ConfigMaps and Secrets - [x] Rollback deployments to previous versions - [x] Ingress and NetworkPolicy management - [x] Context switching between clusters ### Natural Language Processing - [x] Process natural language queries for kubectl operations - [x] Context-aware commands with memory of previous operations - [x] Human-friendly explanations of Kubernetes concepts - [x] Intelligent command construction from intent - [x] Fallback to kubectl when specialized tools aren't available - [x] Mock data support for offline/testing scenarios - [x] Namespace-aware query handling ### Monitoring - [x] Cluster health monitoring - [x] Resource utilization tracking - [x] Pod status and health checks - [x] Event monitoring and alerting - [x] Node capacity and allocation analysis - [x] Historical performance tracking - [x] Resource usage statistics via kubectl top - [x] Container readiness and liveness tracking ### Security - [x] RBAC validation and verification - [x] Security context auditing - [x] Secure connections to Kubernetes API - [x] Credentials management - [x] Network policy assessment - [x] Container security scanning - [x] Security best practices enforcement - [x] Role and ClusterRole management - [x] ServiceAccount creation and binding - [x] PodSecurityPolicy analysis - [x] RBAC permissions auditing - [x] Security context validation ### Diagnostics - [x] Cluster diagnostics and troubleshooting - [x] Configuration validation - [x] Error analysis and recovery suggestions - [x] Connection status monitoring - [x] Log analysis and pattern detection - [x] Resource constraint identification - [x] Pod health check diagnostics - [x] Common error pattern identification - [x] Resource validation for misconfigurations - [x] Detailed liveness and readiness probe validation ### Advanced Features - [x] Multiple transport protocols support (stdio, SSE) - [x] Integration with multiple AI assistants - [x] Extensible tool framework - [x] Custom resource definition support - [x] Cross-namespace operations - [x] Batch operations on multiple resources - [x] Intelligent resource relationship mapping - [x] Error explanation with recovery suggestions - [x] Volume management and identification Note: This repo is still in development, use with caution in production. https://ift.tt/Ve0MXY3 March 27, 2025 at 01:07AM

Show HN: Prompteus – Visual workflow builder for shipping better AI features https://ift.tt/V6AjlvK

Show HN: Prompteus – Visual workflow builder for shipping better AI features We built Prompteus to help devs build and manage AI features without the mess — no more prompt spaghetti or scattered "hardcoded" AI API calls. Design workflows visually, deploy as APIs, and get built-in caching, logging, rate limits, and model orchestration (OpenAI, Anthropic, Mistral, etc.). It’s like Zapier for LLMs — but dev-friendly. Free up to 50k requests/month. https://prompteus.com March 26, 2025 at 11:20PM

Show HN: I built a chatbot that lets you talk to any GitHub repository https://ift.tt/awFLV21

Show HN: I built a chatbot that lets you talk to any GitHub repository https://ift.tt/8pb0HDj March 26, 2025 at 12:43AM

Show HN: Generate docs from your public repos https://ift.tt/axoyuqN

Show HN: Generate docs from your public repos Hello HN, I’m Andrew from docs.dev ( https://docs.dev/ ), an AI powered docs assistant. With docs.dev you can generate your docs directly from your codebase, existing docs and other context sources. We don’t believe AI will replace technical writers—our goal is to make it easier for teams to get a solid first draft that they can review, edit, and improve. Think of it as a head start, not a finished product. More info on what we’ve built below but we wanted to release a quick, 1 minute, generate docs from your codebase tool. Try it out here: https://ift.tt/bLv5wO2 . We built this page, so folks could generate some docs easily and quickly on some of their open source projects. It is still new so let us know if there are bugs but feel free to give it a try! It should work on any moderately sized public repo on GitHub. Why build another docs tool? We believe there are many great tools out there to help teams host their docs and make them look great, but that there aren’t enough tools to help teams manage the content that goes into them. We found that often there’s a disconnect between the devs shipping code and the teams managing the docs, often leading to delays in getting new features out the door or outdated docs. We kept hearing that the only thing worse than no docs is incorrect docs. So, we built tools to help you manage docs directly from your codebase—no special platforms or vendor lock-in required. With docs.dev you can not only generate first drafts of new docs, but also audit your existing docs in bulk, analyze them for effectiveness, and keep everything up to date as the product changes. docs.dev can: Work with any markdown-powered framework Generate clean markdown files synced with your GitHub repo Support existing markdown docs, your codebase, and even Slack threads as context More info at docs.dev ( https://docs.dev/ ) and on our docs page ( https://learn.docs.dev/ ) We’d love for you to check us out and welcome any feedback, criticism, suggestions, questions, or ideas! Thanks so much for reading! https://ift.tt/bLv5wO2 March 25, 2025 at 08:35PM

Show HN: Fingernotes – handwritten notes which become their own preview image https://ift.tt/4w8iOQ2

Show HN: Fingernotes – handwritten notes which become their own preview image Hi HN, I've lurked here for ages and decided to come out of the shadows for my latest side project which reached the point where it’s sort of fun to use and hopefully not totally embarrassing to share. Hacking fingernotes.com together over a couple of weeks was a creative outlet when work got stressful. I think of it as digital sticky notes. The goal was to make notes with a personal touch that are easy to write and share. I also wanted them to appear as their own link preview image on supported platforms. That way when you send the link to a note, the person sees the message without following the link. Let me know what you think! I drew inspiration from Apple's quick notes: low latency made scribbling a pleasure, and sending notes to friends felt warm and original compared to a typical exchange. It was also intriguing to see my handwriting printed in a message chat. In a time of rising artificial generation, spreading my clumsy handwriting feels like an act of rebellion. But I dislike the light background in Apple notes, which I don't think you can change when sharing. More importantly, no one sent a note back. With fingernotes the low-friction interaction is meant to make creating notes simple. I also find the image previews aesthetically more pleasing. For implementation, fingernotes are publicly accessible links to collections of strokes that have been persisted to a Cloudflare D1 database and rendered in SVG. Like pen on a sticky note, each stroke is immutable but anyone can add to a note if they have the link. You can't undo strokes, so if you mess up your note just throw it out and start a new one. Having append-only collections avoids handling order of operations when multiple people edit the same note. Hosting it as a Cloudflare worker made it easy to get up and running. There's some latency in Safari on iOS which is absent on desktop. It's noticeable compared to Apple notes and I'm afraid it's a limitation of the browser. https://ift.tt/pe5hb9H March 23, 2025 at 12:02PM

Show HN: X DMs suck so we built a better one https://ift.tt/obs2Cqz

Show HN: X DMs suck so we built a better one https://tweetdm.com/crm March 24, 2025 at 11:52PM

Show HN: XYMake – Turn Your Posts into LLM-Ready Data https://ift.tt/XE38jlC

Show HN: XYMake – Turn Your Posts into LLM-Ready Data I just built XYMake ( https://xymake.com ), a tool that lets you convert any X (Twitter) thread into clean markdown, making your conversations accessible for LLMs, MCPs, or any API. ## What it does: - Transforms any X thread URL into markdown by simply changing "x.com" to "xymake.com" in the URL - OAuth2 login to "free your data" and make your threads available - Auto-generates OG images with token counts and participant info for easy sharing - Serves different content types based on whether the request is from a crawler, browser, or agent ## Why I built it: I believe people should have the right to own and use their own data. While X/Twitter uses our content to train Grok, we should be able to leverage our own conversations for similar purposes. I built this as a proof of concept in one day (what started as a 30-minute experiment turned into a 10-hour flow state). It's built entirely on Cloudflare Workers and uses some interesting techniques to serve different content types to different consumers. ## Technical highlights: - Request identification to serve HTML+OG images to crawlers while providing raw markdown to agents - Preloading OG image generation using ctx.waitUntil for near-instant loading when shared - Optimized OG image rendering across platforms using workers-og Try it out with any X thread - just replace "x.com" with "xymake.com"! Example: https://ift.tt/JTme2Pp Feedback welcome! This is just the beginning of what's possible when we reclaim our conversational data. https://xymake.com March 25, 2025 at 12:32AM

Show HN: Prefix any URL with `pure.md/` to get unblocked Markdown https://ift.tt/MzJn6iV

Show HN: Prefix any URL with `pure.md/` to get unblocked Markdown https://pure.md March 24, 2025 at 10:06PM

Show HN: Tascli, a simple CLI task and record manager https://ift.tt/7gT1d3s

Show HN: Tascli, a simple CLI task and record manager https://ift.tt/vlB3jAf March 25, 2025 at 12:02AM

Show HN: Formal Verification for Machine Learning Models Using Lean 4 https://ift.tt/ejzlbia

Show HN: Formal Verification for Machine Learning Models Using Lean 4 https://ift.tt/QLpRlth March 24, 2025 at 12:15AM

Show HN: NPM-Audit-to-Report https://ift.tt/N3vnBJk

Show HN: NPM-Audit-to-Report https://ift.tt/dwMNnCu March 23, 2025 at 04:34PM

Show HN: DAPS – Prime-Adaptive Search for Discontinuous Optimization Problems https://ift.tt/cXQBSFG

Show HN: DAPS – Prime-Adaptive Search for Discontinuous Optimization Problems I've been working on a global optimization algorithm that uses prime number-based adaptive grid search. It dynamically adjusts resolution by increasing or decreasing prime numbers as "resolution knobs" — allowing it to handle discontinuities, sharp valleys, and chaotic landscapes better than naive grid search. The repo includes Python and PyTorch-compatible versions, benchmarks against grid search, and a research paper. Would love feedback from optimization, ML, or numerical analysis folks. Curious if anyone sees potential applications or improvements. GitHub: https://ift.tt/ykSGO0Y Paper: https://ift.tt/2max4Mt.... https://ift.tt/ykSGO0Y March 23, 2025 at 11:19AM

Show HN: I build a tool that will tell you what to respond in negotations https://ift.tt/08mPQDN

Show HN: I build a tool that will tell you what to respond in negotations After reading the book Getting to Yes, I really want some tool to help me negotiate more efficiently without having to memorize everything principle. You start by putting in interests of each party, then you can explore different functions: how to respond to the other party, explore objective criteria out there or brainstorm more negotiation options. Still working on it! Leave me feedback if you have any suggestions! https://ift.tt/G4uzdP6 March 23, 2025 at 03:31AM

Show HN: I Made a Language to Be JavaScript's Nanny https://ift.tt/OoW7Qql

Show HN: I Made a Language to Be JavaScript's Nanny I'm working on a language called Chicory. It's yet-another compiles to JS(X) language. I'd value any feedback. See also https://ift.tt/XNZfliQ https://ift.tt/1QoZFmy March 23, 2025 at 01:39AM

Show HN: GoCard – A file-based spaced repetition system built in Go https://ift.tt/IeDU2Xg

Show HN: GoCard – A file-based spaced repetition system built in Go Hi HN! I'm excited to share GoCard, a terminal-based spaced repetition system I built that uses plain Markdown files as its data source. I've always been frustrated with existing spaced repetition tools that lock my knowledge into proprietary formats or require constant internet access. As a developer who lives in terminals and text editors, I wanted something that: 1. Stores cards as plain text files I can edit with any editor 2. Works seamlessly with Git for versioning and sync 3. Runs in a terminal without distractions 4. Has first-class support for code snippets and programming concepts GoCard implements the SM-2 algorithm (the same one used by Anki) but instead of a database, it uses a simple directory structure where: - Each card is a Markdown file with YAML frontmatter - Directories represent decks and subdecks - Everything is editable with standard tools *Key features:* - Distraction-free terminal UI built with BubbleTea - Real-time file watching (edit cards in your editor while reviewing) - Code syntax highlighting for 50+ languages - Vim/Emacs keybindings for efficient navigation - Hierarchical deck organization via directories - Cross-platform (Linux, macOS, Windows) What sets GoCard apart from other SRS tools is its developer-centric approach. Create cards with your favorite editor, organize them with your file manager, version them with Git, and review them in a clean terminal interface. I built this because I wanted a knowledge management system that worked with my developer workflow rather than against it. Making everything file-based means I can apply all my existing text-processing skills and tools. The project is v0.1.0, implemented in Go, and available at: https://ift.tt/BlvT6zj I'd especially appreciate feedback on the UX design and any suggestions for making it more intuitive for terminal users. Has anyone else built similar file-based knowledge tools? What patterns worked well for you? https://ift.tt/BlvT6zj March 23, 2025 at 02:35AM

Show HN: Hyperbrowser MCP Server – Connect AI agents to the web through browsers https://ift.tt/cavY5hi

Show HN: Hyperbrowser MCP Server – Connect AI agents to the web through browsers Hi HN! Excited to share our MCP Server at Hyperbrowser - something we’ve been working on for a few days. We think it’s a pretty neat way to connect LLMs and IDEs like Cursor / Windsurf to the internet. Our MCP server exposes seven tools for data collection and browsing: 1. `scrape_webpage` - Extract formatted (markdown, screenshot etc) content from any webpage 2. `crawl_webpages` - Navigate through multiple linked pages and extract LLM-friendly formatted content 3. `extract_structured_data` - Convert messy HTML into structured JSON 4. `search_with_bing` - Query the web and get results with Bing search 5. `browser_use_agent` - Fast, lightweight browser automation with the Browser Use agent 6. `openai_computer_use_agent` - General-purpose automation using OpenAI’s CUA model 7. `claude_computer_use_agent` - Complex browser tasks using Claude computer use You can connect the server to Cursor, Windsurf, Claude desktop, and any other MCP clients with this command `npx -y hyperbrowser-mcp` and a Hyperbrowser API key. We're running this on our cloud browser infrastructure that we've been developing for the past few months – it handles captchas, proxies, and stealth browsing automatically. Some fun things you can do with it: (1) deep research with claude desktop, (2) summarizing the latest HN posts, (3) creating full applications from short gists in Cursor, (3) automating code review in cursor, (4) generating llms.txt for any website with windsurf, (5) ordering sushi from windsurf (admittedly, this is just for fun - probably not actually going to do this myself). We're building this server in the open and would love feedback from anyone building agents or working with web automation. If you find bugs or have feature requests, please let us know! One big issue with MCPs in general is that the installation UX sucks and auth credentials have to be hardcoded. We don’t have a solution to this right now but Anthropic seems to be working on something here so excited for that to come out. Love to hear any other complaints / thoughts you have about the server itself, Hyperbrowser, or the installation experience. You can check us out at https://hyperbrowser.ai or check out the source code at https://ift.tt/3APZL6J https://ift.tt/3APZL6J March 20, 2025 at 10:31PM

Show HN: Reaching inbox zero has never been more fun https://ift.tt/4pijzYU

Show HN: Reaching inbox zero has never been more fun The average person receives around 120+ emails per day. This makes it almost impossible to stay on top of your emails. This is where InboxSwipe comes in. InboxSwipe is the easiest and most fun way to clean up your Gmail inbox. We present all your emails in a tinder style card view where you can swipe away to take several actions on your email (deleting, unsubscribing, marking as read, etc.) You can choose from 10+ actions and assign it to any swipe gesture you want. We also have AI powered reply feature so that you can respond and discard emails with just a click of a button. Try it out and let me know what you think. https://ift.tt/EPRB95S March 21, 2025 at 11:22PM

Show HN: GizmoSQL – Run DuckDB as a Server with Arrow Flight SQL https://ift.tt/Ptcl47v

Show HN: GizmoSQL – Run DuckDB as a Server with Arrow Flight SQL Hi, I'm Philip Moore - the founder of GizmoData, and creator of GizmoSQL - an Apache Arrow Flight SQL Server - with DuckDB (or SQLite) back-end execution engines. GizmoSQL is a composable SQL server with Arrow Flight SQL, DuckDB, and SQLite - with the intention of making it easy to run DuckDB (or SQLite) as a server - usable by multiple people from a client (remote) computer. It also adds security (authentication) and encryption of traffic with TLS. To run GizmoSQL - see the steps in the README.md - where you can see how easy it is to run the server as well as how to connect via ADBC and JDBC from a remote client - such as DBeaver, Python, etc. The easiest way to run GizmoSQL is via Docker - but there are downloads for Linux and macOS for both x86-64 and arm64 platforms (download links in the README). Why?: As you may know, DuckDB and SQLite are embedded systems - they don't enable client connectivity, and they aren't really designed for concurrency. I've built GizmoSQL to work around that - because I believe the DuckDB engine is very powerful, and I feel like a lot of customers overpay and run distributed compute (i.e. Spark) when they don't really need to. Making it easy to have remote connectivity to DuckDB can make it easier to migrate SQL workloads from Spark or other expensive commercial platforms to this engine - with a much simpler architecture/infrastructure. It is my intention to make GizmoSQL a commercial product - licensed for production use by organizations, but free for developers to code with - evaluate, and test. A little bit of backstory: * I built the initial version of this while working for a former employer - it wasn't their core focus, so they open-sourced that early version. After I left there, I forked the product and have improved it substantially - to support concurrency of both reads and writes, improving security, as well as keeping it up to date with the latest versions of Apache Arrow and DuckDB. * This project evolved from a prototype created by the brilliant Tom Drabas. * It feels a little weird trying to make a commercial product based upon DuckDB, but MotherDuck started it :P - and I've contributed (albeit very little) to the DuckDB and Apache Arrow projects in the form of a couple of PRs. I'm really excited about this project - I have run benchmarks of this product against commercial platforms such as Snowflake and Databricks SQL - and it holds its own running the 22-query TPC-H SF1TB benchmark, especially on cost. See the graph at: https://ift.tt/7Yb1Tyx Getting started: Github README: https://ift.tt/RJLBZ3E... DockerHub: https://ift.tt/ygeYBPs GizmoSQL homepage: https://ift.tt/7Yb1Tyx Phil's Github profile: https://ift.tt/b1rAzoD Thanks for your time and feedback in advance. https://ift.tt/vbU1exo March 21, 2025 at 12:45AM

Show HN: Nicely designed editor for mockups and screenshots https://ift.tt/1uj75Pq

Show HN: Nicely designed editor for mockups and screenshots https://postspark.app March 21, 2025 at 12:14AM

Show HN: SpongeCake – open-source SDK for OpenAI computer use agents https://ift.tt/z8YwCGj

Show HN: SpongeCake – open-source SDK for OpenAI computer use agents Hey HN! Wanted to quickly put this together after seeing OpenAI launched their new computer use agent We were excited to get our hands on it, but quickly realized there was still quite a bit of set-up required to actually spin up a VM and have the model do things. So we wanted to put together an easy way to deploy these OpenAI computer use VMs in an SDK format and open source it Hopefully this tooling is helpful to other folks building AI agents! Here’s a link to the repo ( https://ift.tt/pXdc59F ) - please try it out and give us a star. If you have any feedback, add it as a comment to this post! Or if you simply just love spongecake, show support for the delicious treat https://ift.tt/pXdc59F March 20, 2025 at 10:16PM

Show HN: Codemcp – Claude Code for Claude Pro subscribers – ditch API bills https://ift.tt/ABrR5kh

Show HN: Codemcp – Claude Code for Claude Pro subscribers – ditch API bills Hi all! I normally work on the PyTorch project but I've been on baby leave for the past month, so I've been playing around with AI as a user rather than a framework implementor. I really liked the agent experience with Claude Code, but I couldn't really justify spending so many dollars on API costs for random side projects. I already pay for a Claude Pro subscription though, and it turns out you can simulate many of Claude Code's features with an MCP. If you have a Pro subscription, check this out! I think it really captures the Claude Code experience quite well, without forcing you to pay for API tokens. https://ift.tt/pRfhSMl March 13, 2025 at 11:59PM

Show HN: I built an extension to book Airbnbs directly https://ift.tt/rkvwedz

Show HN: I built an extension to book Airbnbs directly Hi Hackers, My wife and I have been slow traveling around the world for last 3 years, and our top travel hack that has saved us most amount of money is to book directly with Airbnb host. We usually rent for a month so savings in fees are easily ~$300 - $500 on each stay, i.e. about 15-20%. Not every host offers it we respect that, but there are so many hosts out there that would rather have you book directly via their website and we as guests want the same. The problem is these hosts can’t promote or say that on Airbnb. This inspired me to build OpenBnB.org, where I’ve started collecting direct booking websites of hosts. So far, I have around 1,500 hosts representing 150,000 listings – most of them in USA. The idea is to give guests more options to book, and hosts another channel to distribute their listings. The first solution is a browser extension that makes it really easy to find the direct booking website of hosts when you’re browsing Airbnb. It just a one-time easy install with no sign ups. It: 1) highlights all the directly-bookable listings on the search page, 2) lets you search listings only from hosts with direct booking option and then of course 3) gives you the direct booking link on the listing page. What I like about this solution is it doesn’t require guests to go to a different website; they can just browse Airbnb (largest inventory of short-term rentals) as usual and get more options to book when available. Other than savings, I think there is something about the direct relationship with hosts and guests, without any intermediaries. The cool think is I estimate about 20-33% of Airbnbs can be booked directly! That means I’ve only collected around 6 to 9% of all directly-bookable listings around the world. I’ve seen some other chrome extensions do something similar, but none of them highlight these listings nor let you search listings only with hosts that offer direct booking. What do you think? Try it out and let me know if this is useful. I’m also planning to spin up a website that only has listings from these hosts, kind of like a meta-search engine for vacation rental websites. https://ift.tt/rGqe0PO March 20, 2025 at 01:37AM

Show HN: We built an agentic image editor that preserves the original structure https://ift.tt/oPR4ESC

Show HN: We built an agentic image editor that preserves the original structure Hi everyone, I’ve been experimenting with app where you can edit images in your camera roll simply by tweaking your photo’s metadata (changing location/time) and our agent will contextually regenerate the photo in that place & time in one shot. There's no prompting involved. One of the hardest problems we’ve seen with these ai image editing/creation tools is that they struggle with preserving the subjects of the original image (faces, genders, number of people, bodies, animals, etc), and I think we’ve gotten a step closer to making it feel more realistic. The gallery has some examples that people have been regenerating. https://ift.tt/7AdIWBh Here’s a demo: https://ift.tt/tgaewYk Feel free to dm me on Twitter: https://twitter.com/sakofchit if you’d like to try out the TestFlight in the meantime Would love to know what y'all think! https://ift.tt/7AdIWBh March 19, 2025 at 11:14PM

Show HN: I Made an Escape Room Themed Prompt Injection Challenge https://ift.tt/U6dxCBq

Show HN: I Made an Escape Room Themed Prompt Injection Challenge We launched an escape room-themed AI Escape Room challenge with prizes of up to $10,000 where you need to convince the escape room supervisor LLM chatbot to give you the key using prompt injection techniques. Hope you like it :) https://ift.tt/93JbQpD March 19, 2025 at 01:12AM

Show HN: I Created a Fork of Ghost CMS with an AI Editor and Native ECommerce https://ift.tt/85dmDxF

Show HN: I Created a Fork of Ghost CMS with an AI Editor and Native ECommerce After many months of hard work and innovation, we've built a platform that takes Ghost CMS to the next level. Cartanza integrates native AI-powered content and image creation and native eCommerce functionality directly into the blogging experience. This means you can now: - Generate high-quality blog content and images with AI—no more copy-pasting between tools. - Seamlessly embed eCommerce capabilities, linking products and collections directly into your blog posts. - Manage subscriptions, merchandise, and content marketing all in one place. To see Cartanza in action, check out our demo video on YouTube ( https://youtu.be/CQQDqKjOM-Y ). In the video, I walk you through our platform's key features and show how easy it is to get started with our innovative solution. We're excited to invite bloggers, content creators, and eCommerce enthusiasts to explore Cartanza. Join us as we redefine the blogging experience—where creativity meets commerce, powered by cutting-edge AI. https://cartanza.com/ March 19, 2025 at 12:27AM

Show HN: Cascii – A portable ASCII diagram builder written in vanilla JavaScript https://ift.tt/v4P95fr

Show HN: Cascii – A portable ASCII diagram builder written in vanilla JavaScript 3 months ago I wanted to draw an ASCII diagram to include in some documentation at work. I found the few tools online to be insufficient, and was suprised there wasn't a more complete tool to get the job done. Since, I've built Cascii from scratch in vanilla Javascript (I'm not an FE dev, it might be obvious...). I hope it works alright. Please check out the live version at https://cascii.app , report problems, make diagrams to improve your code's documentation. Hope you enjoy using it. https://ift.tt/mPtkY4Q March 16, 2025 at 03:32PM

Show HN: OpenTimes – Free travel times between U.S. Census geographies https://ift.tt/Tk1BSjR

Show HN: OpenTimes – Free travel times between U.S. Census geographies Hi HN! Today I'm launching OpenTimes, a free database of roughly 150 billion pre-computed, point-to-point travel times between United States Census geographies. In addition to letting you visualize travel isochrones on the homepage, OpenTimes also lets you download massive amounts of travel time data for free and with no limits. The primary goal here is to enable research and fill a gap I noticed in the open-source spatial ecosystem. Researchers (social scientists, economists, etc.) use large travel time matrices to quantify things like access to healthcare, but they often end up paying Google or Esri for the necessary data. By pre-calculating times between commonly-used research geographies (i.e. Census) and then making those times easily accessible via SQL, I hope to make large-scale accessibility research cheaper and simpler. Some technical bits that may be of interest to HN folks: - The entire OpenTimes backend is just static Parquet files on R2. There's no RDBMS or running service. The whole thing costs about $10/month to host and is free to serve. - All travel times were calculated by pre-building the inputs (OSM, OSRM networks) and then distributing the compute over hundreds of GitHub Actions jobs. - The query/SQL layer uses a setup I haven't seen before: a single DuckDB database file with views that point to static Parquet files via HTTP. Finally, the driving times are optimistic since they don't (yet) account for traffic. This is something I hope to work on in the near future. Enjoy! https://opentimes.org March 18, 2025 at 02:10AM

Show HN: A static scanner for LLM app code https://ift.tt/tLQuNJo

Show HN: A static scanner for LLM app code https://ift.tt/fBEAJLG March 17, 2025 at 11:19PM

Show HN: Cppmatch – Rust-Like Pattern Matching and Error Handling for C++ https://ift.tt/Ij2qmMV

Show HN: Cppmatch – Rust-Like Pattern Matching and Error Handling for C++ I've created cppmatch, a lightweight, header-only C++ library that brings Rust-inspired pattern matching and error handling to C++. It tries to imitate the functionality of the questionmark (?) operator in C++ by using a macro that uses the gcc extension https://ift.tt/4KglVTR This allows to create exceptionless code with non-intrusive error-as-value that unlike Exceptions, makes it clear which kinds of error a function can generate and forces you to handle (or ignore) them. The ? operator translates to *expect* To handle the errors I introduce *match* which allows to easily visit the contents of the result or any std::variant (you can use it to imitate rust enums) You can view an example of this project used in a "real way" in compiler-explorer: Simplified error types to just be a string: https://ift.tt/p2AcZEC Multiple structs as error types: https://ift.tt/NlGfV9p Feel free to give feedback or contribute to the project! https://ift.tt/8XDB7ox March 16, 2025 at 10:37PM

Show HN: Cross-platform native UI library for all OS https://ift.tt/DbX0dfV

Show HN: Cross-platform native UI library for all OS https://ift.tt/JfzrLxt March 16, 2025 at 11:19PM

Show HN: Nash, I made a standalone note with single HTML file https://ift.tt/gOQkZGn

Show HN: Nash, I made a standalone note with single HTML file Hello HN, I hope it will posted as well. I made a note in single html file. This does not require a separate membership or installation of the software, and if you download and modify an empty file, you can modify and read it at any time, regardless of online or offline. It can be shared through messengers such as Telegram, so it is also suitable to share contents with long articles and images. It is also possible to host and blog because it is static html file content. https://ift.tt/dQjla9n March 14, 2025 at 07:21AM

Show HN: Kill SaaS with Open Source https://ift.tt/qETm5w7

Show HN: Kill SaaS with Open Source KillSaaS is my answer to subscription software in the AI era. I'm building this because I believe small teams can use modern AI tools to create free alternatives to giants like Figma and DocuSign in weeks, not years. We're creating a platform where developers vote on which SaaS to replace, then build it together as open source. wdyt? https://ift.tt/E7L5KoC March 16, 2025 at 02:50AM

Show HN: Basic Memory – Build a knowledge graph from Claude conversations https://ift.tt/aZD1r7v

Show HN: Basic Memory – Build a knowledge graph from Claude conversations Basic Memory is an open-source tool that enables Claude to build and navigate a persistent knowledge graph based on your conversations. It solves the problem of lost context in AI interactions by storing knowledge in standard Markdown files on your computer. I built this because I found myself constantly repeating information to LLMs and wanted a system where my knowledge grew naturally through conversations while maintaining complete control over my data. Demo video: https://ift.tt/Yey7Shb Key features: - Continue conversations exactly where you left off without repetition - All knowledge stays in local Markdown files you can edit anytime - Works with Claude Desktop via the Model Context Protocol - Seamless integration with Obsidian for visualization and editing - Fully open source (AGPL) The system works by creating structure from simple markdown patterns: - Observations with categories: `- [category] fact #tag` - Relations between documents: `- relation_type [[WikiLink]]` or plain `[[Wikilinks]]` - These patterns emerge naturally during conversations When you chat with Claude, you can simply say "Let's continue our conversation about X" and it will build context from your knowledge base, without needing to upload files every time. GitHub: https://ift.tt/u0e5yjL Docs: https://ift.tt/Ikt6KzD Website: https://ift.tt/ldejx9T Requires Claude Desktop or other MCP host and Python 3.12+ I'd love feedback from the HN community, particularly from those interested in knowledge management or AI applications. https://ift.tt/u0e5yjL March 15, 2025 at 11:49PM

Show HN: Psyllium, a Ruby Gem to make Fibers behave more like Threads https://ift.tt/ajOquAK

Show HN: Psyllium, a Ruby Gem to make Fibers behave more like Threads Hi everyone! I created this small Ruby Gem to add some convenient methods to the Fiber class to make it easier to use in the same way a Thread object can be used. This was born out of my frustration that the current implementation of the Fiber class makes it difficult to retrieve the final value of a block passed to a Fiber, especially when creating a fiber via the `schedule` class method. I appreciate any feedback anyone has. https://ift.tt/w6Nc8kn March 15, 2025 at 12:09AM

Show HN: OCR Benchmark Focusing on Automation https://ift.tt/Zx5EkKJ

Show HN: OCR Benchmark Focusing on Automation OCR/Document extraction field has seen lot of action recently with releases like Mixtral OCR, Andrew Ng's agentic document processing etc. Also there are several benchmarks for OCR, however all testing for something slightly different which make good comparison of models very hard. To give an example, some models like mixtral-ocr only try to convert a document to markdown format. You have to use another LLM on top of it to get the final result. Some VLM’s directly give structured information like key fields from documents like invoices, but you have to either add business rules on top of it or use some LLM as a judge kind of system to get sense of which output needs to be manually reviewed or can be taken as correct output. No benchmark attempts to measure the actual rate of automation you can achieve. We have tried to solve this problem with a benchmark that is only applicable for documents/usecases where you are looking for automation and its trying to measure that end to end automation level of different models or systems. We have collected a dataset that represents documents like invoices etc which are applicable in processes where automation is needed vs are more copilot in nature where you would need to chat with document. Also have annotated these documents and published the dataset and repo so it can be extended. Here is writeup: https://ift.tt/ApUyYfn Dataset: https://ift.tt/DarCqpy Github: https://ift.tt/pCVYAHG Looking for suggestions on how this benchmark can be improved further. https://ift.tt/ApUyYfn March 13, 2025 at 02:19AM

Show HN: Pi Labs – AI scoring and optimization tools for software engineers https://ift.tt/9NOlJpB

Show HN: Pi Labs – AI scoring and optimization tools for software engineers Hey HN, after years building some of the core AI and NLU systems in Google Search, we decided to leave and build outside. Our goal was to put the advanced ML and DS techniques we’ve been using in the hands of all software engineers, so that everyone can build AI and Search apps at the same level of performance and sophistication as the big labs. This was a hard technical challenge but we were very inspired by the MVC architecture for Web development. The intuition there was that when a data model changes, its view would get auto-updated. We built a similar architecture for AI. On one side is a scoring system, which encapsulates in a set of metrics what’s good about the AI application. On the other side is a set of optimizers that “compile” against this scorer - prompt optimization, data filtering, synthetic data generation, supervised learning, RL, etc. The scoring system can be calibrated using developer, user or rater feedback, and once it’s updated, all the optimizers get recompiled against it. The result is a setup that makes it easy to incrementally improve the quality of your AI in a tight feedback loop: You update your scorers, they auto-update your optimizers, your app gets better, you see that improvement in interpretable scores, and then you repeat, progressing from simpler to more advanced optimizers and from off-the-shelf to calibrated scorers. We would love your feedback on this approach. https://build.withpi.ai has a set of playgrounds to help you quickly build a scorer and multiple optimizers. No sign in required. https://code.withpi.ai has the API reference and Notebook links. Finally, we have a Loom demo [1]. More technical details Scorers: Our scoring system has three key differences from the common LLM-as-a-judge pattern. First, rather than a single label or metric from an LLM judge, our scoring system is represented as a tunable tree of metrics, with 20+ dimensions which get combined into a final (non-linear) weighted score. The tree structure makes scores easily interpretable (just look at the breakdown by dimension), extensible (just add/remove a dimension), and adjustable (just re-tune the weights). Training the scoring system with labeled/preference data adjusts the weights. You can automate this process with user feedback signals, resulting in a tight feedback loop. Second, our scoring system handles natural language dimensions (great for free-form, qualitative questions requiring NLU) alongside quantitative dimensions (like computations over dates or doc length, which can be provided in Python) in the same tree. When calibrating with your labeled or preference data, the scorer learns how to balance these. Third, for natural language scoring, we use specialized smaller encoder models rather than autoregressive models. Encoders are a natural fit for scoring as they are faster and cheaper to run, easier to fine-tune, and more suitable architecturally (bi-directional attention with regression or classification head) than similar sized decoder models. For example, we can score 20+ dimensions in sub-100ms, making it possible to use scoring everywhere from evaluation to agent orchestration to reward modeling. Optimizers: We took the most salient ML techniques and reformulated them as optimizers against our scoring system e.g. for DSPy, the scoring system acts as its validator. For GRPO, the scoring system acts as its reward model. We’re keen to hear the community’s feedback on which techniques to add next. Overall stack: Playgrounds next.js and Vercel. AI: Runpod and GCP for training GPUs, TRL for training algos, ModernBert & Llama as base models. GCP and Azure for 4o and Anthropic calls. We’d love your feedback and perspectives: Our team will be around to answer questions and discuss. If there’s a lot of interest, happy to host a live session! - Achint, co-founder of Pi Labs [1] https://ift.tt/aKhcI8k https://ift.tt/M5CKJju March 14, 2025 at 07:07PM

Show HN: Bypass DEI Censorship https://ift.tt/f1wjuWM

Show HN: Bypass DEI Censorship https://ift.tt/18anFhM March 14, 2025 at 02:53AM

Show HN: Cross platform binary to launch native binary using Cosmopolitan Libc https://ift.tt/NvsOQSY

Show HN: Cross platform binary to launch native binary using Cosmopolitan Libc https://ift.tt/8OvNun0 March 14, 2025 at 12:23AM

Show HN: Bubbles, a vanilla JavaScript web game https://ift.tt/y45uabs

Show HN: Bubbles, a vanilla JavaScript web game Hey everybody, you might remember my older game, Lander! It made a big splash on Hacker News about 2 years ago. I'm still enjoying writing games with no dependencies. I've been working on Bubbles for about 6 months and would love to see your scores. If you like it, you can build your own levels with my builder tool: https://ift.tt/kzPmjsT and share the levels here or via Github. https://ift.tt/12nRyOi March 13, 2025 at 11:18PM

Show HN: Simple Turn Servers for WebRTC – 5GB Free, $0.20/GB After https://ift.tt/RWgoHxp

Show HN: Simple Turn Servers for WebRTC – 5GB Free, $0.20/GB After https://turnwebrtc.com/ March 13, 2025 at 04:27AM

Show HN: WanderHome – A smart pet tag designed for cats https://ift.tt/Nr96pgO

Show HN: WanderHome – A smart pet tag designed for cats https://wanderho.me March 13, 2025 at 03:41AM

Show HN: CatCompass – An app for tracking stray cats https://ift.tt/Oq5moQC

Show HN: CatCompass – An app for tracking stray cats https://catcompass.com March 13, 2025 at 03:40AM

Show HN: Time Portal – Get dropped into history, guess where you landed https://ift.tt/dhgbrcw

Show HN: Time Portal – Get dropped into history, guess where you landed Hi HN! I love imagining the past, so I made Time Portal, a game where you are dropped into a historical event and see AI video footage from that moment. You have to guess where you are in time and on the map. It’s like GeoGuessr (and heavily inspired by it!) but for historical events. The videos are all created with AI. It’s a pipeline of Flux (images), Kling (video), and mmaudio (audio). The videos aren’t always historically accurate to the last detail. They might incorporate elements of folklore or have details from popular beliefs about the way things looked rather than the latest academic research on how they looked. I’m thinking a lot about how to make the game more interactive. One thing that makes Geoguessr so fun for me is that you can move infinitely and always find more details to help you pinpoint the location. I want Time Portal to have a similar quality. I have a few ideas to try soon that will hopefully make the game more interactive and infinite. https://ift.tt/bdfhS4V March 13, 2025 at 01:53AM

Show HN: Daylight – track sunrise / sunset times in your terminal https://ift.tt/lsqA7cR

Show HN: Daylight – track sunrise / sunset times in your terminal https://ift.tt/HPzqlaA March 9, 2025 at 05:51PM

Show HN: AI-powered root cause analysis with the Five Whys method https://ift.tt/UOToqA2

Show HN: AI-powered root cause analysis with the Five Whys method https://ift.tt/6i75mYt March 12, 2025 at 07:16AM

Show HN: We built a Plug-in Home Battery for the 99.7% of us without Powerwalls https://ift.tt/r35SWa6

Show HN: We built a Plug-in Home Battery for the 99.7% of us without Powerwalls Hi HN! I’m Cole Ashman, founder of Pila Energy. I’ve spent my career working on home energy systems—first as an engineer on Tesla’s Powerwall, where I focused on the Backup Gateway, Solar Inverter, and metering systems. More recently, I led Product at SPAN, where we built the Smart Electrical Panel and integrated with most major home solar, EV, and battery systems. Pila ( https://pila.energy/ ) is a home battery that plugs into a standard wall outlet, provides smart backup power, energy shifting, and grid services. It’s more than a power bank—it’s a distributed energy system that can scale across multiple rooms, entire buildings, and work together in real time as a coordinated system. We built Pila to be local first with an open API to allow developers to build use cases on top of our hardware (Home Assistant, etc). Big batteries like Tesla Powerwall and Enphase are great if you own a home and can afford a $10K+ electrical project, but they require permanent installation, electricians, and panel upgrades—which makes them inaccessible for renters, apartments, and cost-conscious homeowners. Over 50% of the cost of installing a Powerwall isn’t even the battery itself—it’s soft costs: labor, permitting, etc. We wanted to create an entry point for more people to access energy security at home. How does it work? Plug Pila into any 120V wall outlet, and power passes through to connected devices and appliances. The inverter, LFP battery, BMS, grid disconnection, controller, and wireless connectivity are all built in. (details at https://ift.tt/bNsv7PG ) When an outage happens, the onboard inverter detects the power loss within 20ms and automatically disconnects from the grid (islanding). Whether you’re home or away, backup kicks in instantly. A built-in cellular radio ensures you get a notification even if your home WiFi is out. Pila is 1.6kWh. That will backup a standard fridge for over a day. One key challenge we faced with a distributed architecture was coordination between batteries, for things like solar-following and managing real-time draw from your utility connection. Unlike large garage systems, where you can run a wired CAN bus, our batteries are spread across the home. We’re solving this with a sub-GHz wireless mesh network—self-healing, coordinator-less, and designed to make setup and expansion as simple as plugging in another unit. Long-term, we’d love to open up this protocol to provide a more reliable communication layer for energy products in noisy built environments—reducing reliance on consumer Wi-Fi. We want to deliver the value you’d expect from a whole-home battery like Powerwall, in a plug-in format. That means going beyond a basic lead acid UPS with real home energy management, useful insights about power use, power larger loads like sump pumps, and even deliver grid services. Most portable batteries are missing the functionality that makes a home battery useful: no bidirectional power, no integration with solar or smart home systems, and no ability to manage home energy dynamically. They tend to be boxy, ruggedized, meant to be moved around, not seamlessly integrated into your living space. On top of that, many use e-mobility battery chemistries, which are great for delivering high power on demand but wear out faster when cycled daily for home energy use. As a renter myself, I started Pila because these awesome energy products aren’t accessible enough. And frankly, generators are loud, expensive, and a pain to deal with. Even many Powerwall owners I’ve talked to say they really care about keeping the fridge, WiFi, and a sump pump running—so why does energy resilience have to be so complicated and expensive? As the grid struggles to keep up with demand, we believe modular, renter-friendly batteries can make home energy resilience more accessible. What's been your experience with home batteries? What recent power outages have you had, and how were you affected? https://pilaenergy.com March 11, 2025 at 09:18PM

Show HN: A Multiplayer Chatbot https://ift.tt/9bCwTRP

Show HN: A Multiplayer Chatbot Imagine if ChatGPT thought you should meet someone it recently spoke with. I built this simple demo that keeps messages from other users in context, so it can suggest connections and stuff. You can modify the system prompt to decide what the whole point of this is. I’m looking for ideas! https://ift.tt/BXSrEYh March 11, 2025 at 11:08PM

Show HN: Chrome Extension for ChatGPT to organize conversations into folders https://ift.tt/mbySFQp

Show HN: Chrome Extension for ChatGPT to organize conversations into folders Hi HN, I'm Alex, a full-stack developer from Toronto, Canada. I recently built a Chrome extension that organizes ChatGPT conversations into folders, allowing users to sort and save important information for easy reference. The idea for this extension came from a friend who highlighted the lack of good (and affordable) ChatGPT organizers. Many existing tools were either low-quality or overpriced, so I decided to create one that was both reliable and accessible. I built the extension using plain JavaScript and developed a backend with Express to handle Google authentication. For storage, I used MongoDB, enabling all users with an account to save their folder structures and conversation data. Initially, I planned to charge $5 per month to cover costs since originally this extension was intended as a portfolio project addressing a real-world problem. However, just as I finished the main functionality and was about to implement payments, ChatGPT announced an official feature similar to one my extension was providing. Rather than continue competing in a market with an "official" solution, I decided to stop development. But I didn't want my work to go to waste, so I chose to release it for free, motivated by a desire to share it with the community. I made some changes to eliminate the backend. Now the extension stores all folder structures and content locally in Chrome storage. Luckily, I had some old code to reuse for this. The extension is now live on the Chrome Web Store. This project introduced me to a lot of new challenges with technologies I hadn’t used before, but I’m grateful for the experience and the skills I gained along the way. I hope you find it useful! Links to the extension and its website: https://ift.tt/4nkDmLX... https://ift.tt/TxpQd7S If you have any questions or suggestions, feel free to reach out in the comments or via email at georgepozdman@gmail.com. https://ift.tt/TxpQd7S March 11, 2025 at 04:41AM

Riding the Rails: San Francisco Cable Car Stamps

Riding the Rails: San Francisco Cable Car Stamps
By Kelley Trahan

Evening shot of a cable car on Powell Street with passengers, February 29, 1968 San Francisco's iconic cable cars aren't just a beloved tourist attraction. They are a symbol of the city's unique history and ingenuity. And they’ve appeared on two United States postage stamps. Let's take a journey through the history of these tributes and see how they came to be. The first ride: the 1971 cable car stamp The first cable car stamp was released in 1971. It was an 8-cent historic preservation stamp honoring the San Francisco cable cars. It showed the cable car's charm and was a small tribute to the...

Published March 10, 2025 at 05:30AM
https://ift.tt/Nwhu1qx

Show HN: I built a Figma plugin for quick data calculations https://ift.tt/tWdDjkA

Show HN: I built a Figma plugin for quick data calculations I lead design on a B2B SaaS product. It's quite data-heavy in places. Using placeholder content in data tables, checkout summaries and dashboards is a big no-no for us. It might seem like using random numbers saves time at first, but sooner or later there's documentation to write and plenty of clarifications to be made. It throws off customers during interviews – "hey, that's not really my sales target!". It confuses stakeholders at review time– "what's this data point supposed to be?" I built a Figma calculator plugin for my team so that they spend less time doing mental maths. It calculates sums, differences averages and percentages, and makes it easy to use real-looking data in designs. https://ift.tt/H1mRWyv March 10, 2025 at 07:11PM

Show HN: I built a free SVG Web site https://ift.tt/wEtsrZ9

Show HN: I built a free SVG Web site This has been an experiment to see if I could create everything using scripts and AI. If AI couldn't do it I'd get it to create the code such as API calls and so on. This websvg.com site was completely created using these AI tools. Including the DNS being applied, the Cloudflare Pages were automatically set up and the the web site was a Svelte 5 application generated by v0.dev and Cursor. Every image was generated in Midjourney and converted to SVG. I have now taken all of these scripts and can create a similar landing or directory site in less than a minute, provided I have the data. Anyway it's been fun. https://websvg.com/ March 10, 2025 at 01:50AM

Show HN: Buildless CJS+ESM+TS+Importmaps for the Browser https://ift.tt/KvXzOam

Show HN: Buildless CJS+ESM+TS+Importmaps for the Browser https://ift.tt/B4Q5Jh2 March 10, 2025 at 12:42AM

Show HN: A No-Nonsense Discord Timestamp Generator https://ift.tt/AeLw6yt

Show HN: A No-Nonsense Discord Timestamp Generator Looking for some tips on improvements, am I missing a feature or could I improve the UX somehow? Thanks! https://ift.tt/SCc1Z2I March 10, 2025 at 01:14AM

Show HN: Evolving Agents Framework https://ift.tt/J8rWf9s

Show HN: Evolving Agents Framework Hey HN, I've been working on an open-source framework for creating AI agents that evolve, communicate, and collaborate to solve complex tasks. The Evolving Agents Framework allows agents to: Reuse, evolve, or create new agents dynamically based on semantic similarity Communicate and delegate tasks to other specialized agents Continuously improve by learning from past executions Define workflows in YAML, making it easy to orchestrate agent interactions Search for relevant tools and agents using OpenAI embeddings Support multiple AI frameworks (BeeAI, etc.) Current Status & Roadmap This is still a draft and a proof of concept (POC). Right now, I’m focused on validating it in real-world scenarios to refine and improve it. Next week, I'm adding a new feature to make it useful for distributed multi-agent systems. This will allow agents to work across different environments, improving scalability and coordination. Why? Most agent-based AI frameworks today require manual orchestration. This project takes a different approach by allowing agents to decide and adapt based on the task at hand. Instead of always creating new agents, it determines if existing ones can be reused or evolved. Example Use Case: Let’s say you need an invoice analysis agent. Instead of manually configuring one, our framework: Checks if a similar agent exists (e.g., a document analyzer) Decides whether to reuse, evolve, or create a new agent Runs the best agent and returns the extracted information Here's a simple example in Python: import asyncio from evolving_agents.smart_library.smart_library import SmartLibrary from evolving_agents.core.llm_service import LLMService from evolving_agents.core.system_agent import SystemAgent async def main(): library = SmartLibrary("agent_library.json") llm = LLMService(provider="openai", model="gpt-4o") system = SystemAgent(library, llm) result = await system.decide_and_act( request="I need an agent that can analyze invoices and extract the total amount", domain="document_processing", record_type="AGENT" ) print(f"Decision: {result['action']}") # 'reuse', 'evolve', or 'create' print(f"Agent: {result['record']['name']}") if __name__ == "__main__": asyncio.run(main()) Next Steps Validating in real-world use cases and improving agent evolution strategies Adding distributed multi-agent support for better scalability Full integration with BeeAI Agent Communication Protocol (ACP) Better visualization tools for debugging Would love feedback from the HN community! What features would you like to see? Repo: https://ift.tt/3BZRAez https://ift.tt/3BZRAez March 9, 2025 at 10:21PM

Show HN: Math expressions and graph traversals of the Chinese language https://ift.tt/SKgnex9

Show HN: Math expressions and graph traversals of the Chinese language I've been working on a free Chinese language learning tool for awhile now. The main insight is that Chinese characters are used together to form words, and that this allows for a way of quickly getting information about related words and characters. By learning words and characters in a chain in this way, I've found it easier not to get lost in the long list of characters. In addition, I've found it helpful to break down characters into their components to find pronunciation clues, which can sometimes be hidden in components of components. The math feature uses a similar tree traversal mechanism to allow expressions like 酒-氵+各 = 酪 or 亻+寸+广+仌+⺆ = 腐. As it's 2025, it also has some AI features. Notably: * allowlisted users can get Chinese or English text explanations that span more than just a word, but that integrate with the other features, like flashcard creation and in-browser text-to-speech. * files and images (using the browser's `capture` mechanism to operate cameras) can also be processed similarly. * example sentences were generated and cached using AI The site is a PWA built with vanilla JS (because I like pain), with Cytoscape and D3 for various rendering tasks. The backend was built with Firebase, with Genkit + Gemini 2.0 providing the AI integration. Feel free to check it out: https://hanzigraph.com https://ift.tt/huD4V1r March 9, 2025 at 12:30AM

Show HN: Search input query parser and React component https://ift.tt/7fnwRSx

Show HN: Search input query parser and React component https://ift.tt/AiWgFuY March 8, 2025 at 11:14PM

Show HN: Simple Certificate Decoder Tool https://ift.tt/oNubm5t

Show HN: Simple Certificate Decoder Tool Sometimes I need to quickly check certificates, especially key details like SANs, expiration dates, issuer info, etc. I know there are dozens (if not hundreds) of certificate decoders out there already, but I built my own—mostly for fun, but also because I prefer tools that are clean, simple, and straightforward to use. Would appreciate your feedback! https://ift.tt/VRdFAgK March 8, 2025 at 11:09PM

Show HN: Ming-wm: A 100% keyboard-operated desktop environment in Rust https://ift.tt/Kv7XIhU

Show HN: Ming-wm: A 100% keyboard-operated desktop environment in Rust https://ift.tt/LEn8xNA March 8, 2025 at 12:24AM

Show HN: I Built a Telegraph Simulator https://ift.tt/3idg0xW

Show HN: I Built a Telegraph Simulator https://ift.tt/cp9U8LP March 5, 2025 at 03:30AM

Show HN: Ask AI Paul Graham (Open Sourced) https://ift.tt/mtvUpPY

Show HN: Ask AI Paul Graham (Open Sourced) https://ift.tt/geduCIf March 8, 2025 at 12:10AM

Show HN: Open-source, native audio turn detection model https://ift.tt/qz1uQ7o

Show HN: Open-source, native audio turn detection model https://ift.tt/fuGJrPj March 6, 2025 at 11:50PM

Show HN: DataBridge: Rule-Based Metadata Extraction, PII Redaction, and More https://ift.tt/Xkabhi8

Show HN: DataBridge: Rule-Based Metadata Extraction, PII Redaction, and More https://ift.tt/Y6aU8eB March 6, 2025 at 08:12PM

Show HN: Story Jam, a music composition tool for Storytellers https://ift.tt/30mn9GY

Show HN: Story Jam, a music composition tool for Storytellers https://ift.tt/rgSDBoK Hello! My name is Cortland Mahoney. I'm a music researcher, software engineer, and producer. I made Story Jam. This doc is intended to inform you of not just the product, but the centuries of work that have led up to its implementation. Are you tired of the barriers in traditional music composition? Story Jam is here to break them down. Designed for anyone with creative ideas — from poets to film directors — our tool offers a new way to create and edit chord progressions, powered by cutting-edge music theory. *Who Story Jam is for: Storytellers* Story Jam makes music composition accessible and meaningful to anybody, with or without musical training. It is designed for those who crave musical control but struggle with traditional composition methods. This includes film directors, slam poets, and self-taught musicians. Story Jam is not music production software. Do not expect fancy sounds or synthesizers. It's purely a composition tool, designed to spark your creative process. *Try it out!* The demo is free on the homepage, no login required! This is an MVP, so it has an "introductory" feature set. Feature requests welcome; help me build the product you want. *The chord progression suggestion logic* This service is built on a novel new music theory I have developed called Monic Theory. Monic Theory is a rigorous proof for music. Not "Western music": music. Monic Theory describes the tonal space of any conventional music on earth (except noise music. For that just use `Math.random()`). It describes the static and transient function of chords, instantaneously and differentially over time. This model enables empirical measurement of chords and the relationship between chords. (hint: It is nothing you have seen in Xenharmonic Alliance. This is a new approach I have been developing over the past 10 years.) Therefore, Monic Theory enables us to describe (or "predict" if you will) a chord progression to invoke a certain feeling. *Music Composition* Three people who helped set up the environment for Monic Theory are composers Paul Hindemith and Harry Partch , and music theorist Heinrich Schenker. These folks independently contributed new ideas to music composition and analysis. All of these people lived without access to rapid computation. This is critical for the Partch case, as he computed many tables of frequencies by hand to support his compositional technique. Partch recognized the human-math-music relation in "Genesis of a Music." He includes in this text some samples of his hand-computed tables of frequency values of overtones and (importantly) undertones which support the basis is technique. Partch's techniques were so far-fetched that he had to construct new instruments to perform his scores. Similarly, I had to build a digital synthesizer to render the output of Monic Theory. (See: https://ift.tt/DUEb56H ). *About me* I was a working composer and violinist from 2007 until 2017, and I have been a software engineer for the past 7.5 years. I was a volunteer organizer for Livecode.NYC, an NYC livecode community; and am the volunteer creator of Data Dancers, Atlanta's livecode community. I am passionate about algorithmic art and have provided about a dozen workshops over four years on the topic. https://ift.tt/PZM7gmi thank you for reading. May the flow of Spices be with you :) naltroc March 5, 2025 at 11:16PM

Show HN: Bayleaf – Building a low-profile wireless split keyboard https://ift.tt/hvAUOyZ

Show HN: Bayleaf – Building a low-profile wireless split keyboard Hey HN, I built a wireless, split, ultra-low profile keyboard from scratch called Bayleaf. As a beginner I learned all things electronics, PCB-building, designing for manufacturing, and many other hardware-related skills to put this together. This case study dives into the build process and of course the final result, hope you enjoy! https://ift.tt/JyI6MpR March 4, 2025 at 08:30PM

Show HN: Time travel debugging AI for more reliable vibe coding https://ift.tt/WEGjla2

Show HN: Time travel debugging AI for more reliable vibe coding Hi HN, I'm the CEO at https://replay.io . We've been building a time travel debugger for web apps for several years now (previous HN post: https://ift.tt/zZK1Er9 ) and are combining our tech with AI to automate the debugging process. AIs are really good at writing code but really bad at debugging -- it's amazing to use Claude to prompt an app into existence, and pretty frustrating when that app doesn't work right and Claude is all thumbs fixing the problem. The basic reason for this is a lack of context. People can use devtools to understand what's going on in the app, but AIs struggle here. With a recording of the app its behavior becomes a giant database for querying using RAG. We've been giving Claude tools to explore and understand what happens in a Replay recording, from basic stuff like seeing console messages to more advanced analysis of React, control dependencies, and dataflow. For now this is behind a chat API ( https://ift.tt/OIAU7BY ). We recently launched Nut ( https://nut.new ) as an open source project which uses this tech for building apps through prompting (vibe coding), similar to e.g. https://bolt.new and https://v0.dev . We want Nut to fix bugs effectively (cracking nuts, so to speak) and are working to make it a reliable tool for building complete production grade apps. It's been pretty neat to see Nut fixing bugs that totally stump the AI otherwise. Each of the problems below has a short video but you can also load the associated project and try it yourself. - Exception thrown from a catch block unmounts the entire app: https://ift.tt/jT8lHzL - A settings button doesn't work because its modal component isn't always created: https://ift.tt/MCcieYN - An icon is really tiny due to sizing constraints imposed by other elements: https://ift.tt/Wj9iOgu - Loading doesn't finish due to a problem initializing responsive UI state: https://ift.tt/Zw5HCnI - Infinite rendering loop caused by a missing useCallback: https://ift.tt/nkhxHaA Nut is completely free. You get some free uses or can add an API key, and we're also offering unlimited free access for folks who can give us feedback we'll use to improve Nut. Email me at hi@replay.io if you're interested. For now Nut is best suited for building frontends but we'll be rolling out more full stack features in the next few weeks. I'd love to know what you think! https://nut.new March 5, 2025 at 12:23AM

Show HN: FlakeUI https://ift.tt/x2ZVTzM

Show HN: FlakeUI https://ift.tt/43LrKov March 3, 2025 at 10:59AM

Show HN: LeetGPU – LeetCode for GPU Programming https://ift.tt/FRf2C90

Show HN: LeetGPU – LeetCode for GPU Programming After the incredible response to our launch of the first online CUDA playground, we have just shipped something we think all you GPU programming and ML enthusiasts will love. Introducing LeetGPU Challenges--the place to compete on writing the fastest CUDA kernels. We have problems like matrix multiplication, agent simulation, multi-head self-attention, with more dropping every couple of days! We have a lot of really cool things coming up, including support for PyTorch, TensorFlow, JAX, TinyGrad; Multi-GPU programs; H100, V100, A100 GPU options Give it a try and let us know what you think! https://LeetGPU.com March 4, 2025 at 12:52AM

Show HN: Firebender, a simple coding agent for Android Engineers https://ift.tt/dXz6nPa

Show HN: Firebender, a simple coding agent for Android Engineers Hey HN, I made a simple coding agent plugin in Android Studio called Firebender. Here’s an unedited 5-minute video where it writes tests for an Android app and iterates against the Gradle task output on its own ( https://ift.tt/S5b4L2q ). You can use the plugin for free, no sign up needed, on the jetbrains marketplace. The agent can edit multiple files, run gradle tasks like tests, and use the output to improve its changes. At the end, it reports a git diff of all changes that can be accepted or rejected. Under the hood, the agent relies on Claude 3.7 sonnet and a fast code apply model to speed up edits. We built tools to give deeper access throughout the IDE like IntelliJ’s graph representation of kotlin/java code, “everywhere search” for classes, and have more integrations planned. The goal is for the agent to have access to all the IDE goodies that we engineers take for granted, to improve the agent's responses and ability to gather correct context. In order to improve the agent, there are internal evals like “tasks” and simulate the IDE which serves as a gym for the agent. This is heavily inspired by SWE-bench. Whenever tools, prompts, subagents, or models are changed, this gym helps find regressions quickly. Building the UI was surprisingly hard. I had the great pleasure of becoming proficient in Java Swing (released in ‘96 by Netscape) to get this done right. Things like markdown streaming, or streaming git diffs are prone to layout flickering where Swing tries to recalculate where elements should go. We had to write our own markdown parsing and rendering engine that repaints Swing components only when changed portions of the markdown nodes. The UI tends to focus on simplifying reviewing AI changes, something I have a feeling we’ll be doing much more in the coming years. If you’re an Android engineer, please let me know if you run into any bugs or want anything improved in the plugin! https://ift.tt/S5b4L2q March 3, 2025 at 11:18PM

Show HN: Mmar – open-source, zero-dependancy, cross-platform HTTP tunneling https://ift.tt/v8uBSxi

Show HN: Mmar – open-source, zero-dependancy, cross-platform HTTP tunneling Hey HN! For the past couple of months, I've been working on and off on a cool project I'm excited to share. mmar (pronounced "ma-mar") is an open-source, zero dependency, cross platform and self-hostable HTTP tunnel built in Go. It allows you to easily expose your localhost to the world on a public URL. You can easily create an HTTP tunnel right away for free on a randomly generated subdomain on "*.mmar.dev" if you don't feel like self-hosting. This isn't something new, in fact there's quite a few of alternative HTTP tunneling tools out there. mmar is my attempt to optimize for a super easy developer experience and simplified implementation. None the less, I had a blast building it and I think developers could find it pretty useful. Additionally, I documented the whole process of building mmar through devlogs. You can read about the thought process and implementation details here ( https://ift.tt/62LFwUB ). If I would suggest one devlog to read, I highly recommend devlog 5 ( https://ift.tt/NIQVYbl ). I describe how I built a (very) basic DNS server just to run simulation tests for mmar (a bit of an overkill, but a fantastic learning experience). I dive deep into the DNS protocol and explain why I needed to implement it. Finally, I would love to hear your thoughts and feedback. If you try mmar out, let me know! https://ift.tt/6VgiTqC March 3, 2025 at 01:28AM

Show HN: Crop images into square, circle, heart, oval for free https://ift.tt/sY4fklJ

Show HN: Crop images into square, circle, heart, oval for free I developed an Image Cropper, which supports cropping images into square, circle, heart, and oval shapes. It also supports customizing the width and height for arbitrary cropping, which is very simple. https://cropimage.co March 2, 2025 at 10:10PM

Show HN: Schedual https://ift.tt/lhaw4GD

Show HN: Schedual No nonsense tasks. https://schedual.app/ March 2, 2025 at 01:10AM

Show HN: Open-source tool that send UI feedback with context https://ift.tt/cHnwMvd

Show HN: Open-source tool that send UI feedback with context https://ift.tt/Sv5aOm8 March 2, 2025 at 01:11AM

Show HN: I built an app to convert ChatGPT Deep Research to PDFs with footnotes https://ift.tt/0tbh1JH

Show HN: I built an app to convert ChatGPT Deep Research to PDFs with footnotes Whilst ChatGPT Deep Research is very useful for generating in-depth reports, it's time consuming to copy, reformat the text (thousands of words) and clean referenced hyperlinks for use in a professional context. Out of frustration, I built deep research docs to help save time by automating the reformatting, cleaning links, footnote references, and conversion to shareable PDF format. Hopefully this helps you save time to focus on meaningful work. Let me know your feedback. https://ift.tt/WD7l143 March 1, 2025 at 06:22PM

Show HN: Torii – a framework agnostic authentication library for Rust https://ift.tt/b0PxB15

Show HN: Torii – a framework agnostic authentication library for Rust https://ift.tt/4pKZVt2 March 1, 2025 at 04:46AM

Show HN: Find out if you qualify for an O-1 visa https://ift.tt/salSghL

Show HN: Find out if you qualify for an O-1 visa https://o1pathways.com/ March 1, 2025 at 03:49AM

Show HN: Betting game puzzle (Hamming neighbor sum in linear time) https://ift.tt/jOY0By7

Show HN: Betting game puzzle (Hamming neighbor sum in linear time) In Spain, there's a betting game called La Quiniela: https://ift.tt/jraveKc Players predict the outcome of 14 football matches (home win, draw, away win). You win money if you get at least 10 correct, and the prize amount depends on the number of winners. Since all bets are public, the number of winners and the corresponding payouts can be estimated for each of the 3^14 possible outcomes. We can also estimate their probabilities using bookmaker odds, allowing us to compute the expected value for each prediction. As a side project, I wanted to analyze this, but ran into a computational bottleneck: to evaluate a prediction, I had to sum the values of all its Hamming neighbors up to distance 4. That’s nearly 20,000 neighbors per prediction (1+28+364+2912+16016=19321): S_naive = sum from k=0 to r of [(d! / ((d-k)! * k!)) * (q-1)^k] (d=14, q=3, r=4) This took days to run in my first implementation. Optimizing and doing it with matrices brought it down to 20 minutes—still too slow (im running it in GAS with 6 minutes limit). For a while, I used a heuristic: start from a random prediction, check its 28 nearest neighbors, move to the highest-value one, and repeat until no improvement is possible within distance 3. It worked surprisingly well. But I kept thinking about how to solve the problem properly. Eventually, I realized that partial sums could be accumulated efficiently by exploiting overlaps: if two predictions A and B share neighbors, their shared neighbors can be computed once and reused. This is achieved through a basic transformation that I implemented using reshape, roll, and flatten (it is probably not the most efficient implementation but it is the clearest), which realigns the matrix by applying an offset in dimension i. This transformation has two key properties that enable reducing the number of summations from 19,321 to just 101: - T(T(space, d1), d2) = T(T(space, d2), d1) - T(space1, d) + T(space2, d) = T(space1+space2, d) Number of sums would be the result of this expression: S_PSA = 1 + (d - (r-1)/2) * r * (q-1) I've generalized the algorithm for any number of dimensions, elements per dimension, and summation radius. The implementation is in pure NumPy. I have uploaded the code to colab, github and an explanation in my blog. Apparently, this falls under Hamming neighbor summation, but I haven't found similar approaches elsewhere (maybe I'm searching poorly). If you know or you've worked on something similar, I'd love to hear your thoughts! colab: https://ift.tt/mfUvczN... github: https://ift.tt/ax5XhwC blog: https://ift.tt/xkrJKih... March 1, 2025 at 02:03AM

Show HN: News-briefing-generator – Local LLM-powered news digest https://ift.tt/G4g3oNV

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/pabim2V February 28, 2025 at 10:45PM