Show HN: LLMFeeder – Browser extension to extract clean content for LLM context https://bit.ly/43XDTRT

Show HN: LLMFeeder – Browser extension to extract clean content for LLM context I built this browser extension to solve a daily frustration: copying documentation from websites to feed into AI coding assistants like Cursor, Windsurf, or ChatGPT, only to get a mess of ads, popups, and navigation junk mixed in with the actual content. LLMFeeder uses Mozilla's Readability.js (same tech as Firefox Reader Mode) to extract just the main article content, converts it to clean markdown with Turndown.js, and copies it to your clipboard with a single keyboard shortcut (Alt+Shift+M or ⌥ ⇧ M). No clicking through popups, no selecting around ads, no fighting with modern web clutter. # Key features: • One-key extraction and markdown conversion • Works on Chrome and Firefox • Completely local processing (no data sent anywhere) • Configurable content scope and formatting options • Open source with clean, documented code The workflow is simple: hit the shortcut on any documentation page, switch back to your editor, paste clean markdown context, get better LLM responses. It's solving a real problem I have dozens of times per day, and early users seem to find it useful too. Available on both browser stores and GitHub for manual installation. # Links: • Demo: https://www.youtube.com/watch?v=JxHWqszlZDw • GitHub: https://bit.ly/4413k5a • Chrome: https://bit.ly/43rpj53... • Firefox: https://mzl.la/3SxpwgX Would love feedback from fellow developers who deal with this same workflow friction. What other pain points do you have when feeding content to LLMs? https://bit.ly/4413k5a June 3, 2025 at 10:43PM

Show HN: Gradle plugin for faster Java compiles https://bit.ly/447WBFF

Show HN: Gradle plugin for faster Java compiles Hey HN, We've written a pretty cool Gradle plugin I wanted to share. It turns out if you native-image the Java and Kotlin compilers, you can experience a serious gain, especially for "smaller" projects (under 10,000 classes). By compiling the compiler with native image, JIT warmup normally experienced by Gradle/Maven et al is skipped. Startup time is extremely fast, since native image seals the heap into the binary itself. The native version of javac produces identical outputs from inputs. It's the same exact code, just AOT-compiled, translated to machine code, and pre-optimized by GraalVM. Of course, native image isn't optimal in all cases. Warm JIT still outperforms NI, but I think most projects never hit fully warmed JIT through Gradle or Maven, because the VM running the compiler so rarely survives for long enough. Elide (the tool used by this plugin) also supports fetching Maven dependencies. When active, it prepares a local m2 root where Gradle can find your dependencies already on-disk when it needs them. Preliminary benchmarking shows a 100x+ gain since lockfiles prevent needless re-resolution and native-imaging the resolver results in a similar gain to the compiler. We (the authors) are very much open to feedback in improving this Gradle plugin or the underlying toolchain. Please, let us know what you think! https://bit.ly/3ZQz9er June 3, 2025 at 08:59PM

Show HN: Datta AI – Get paid when your data trains AI models https://bit.ly/3ZNkQY1

Show HN: Datta AI – Get paid when your data trains AI models We just launched Datta AI, a new platform that flips the AI data model. Right now, AI companies are scraping the internet, collecting massive amounts of user data — and users get nothing. Datta AI is building a data layer where: People connect or upload their data Retain control over how it’s used Earn money when their data powers AI systems It’s like YouTube, but for AI data. We’re just launching the waitlist and would love feedback from the HN community — especially around: How to make data contribution feel meaningful Transparent monetization for contributors Privacy and control at the core Our goal is to build a fairer AI future — powered by people, not just platforms. https://bit.ly/3HqC4nP Happy to answer any questions! — Andrew, Founder of Datta AI https://bit.ly/3HqC4nP June 3, 2025 at 05:26AM

Show HN: Clai – Unixlike vendor agnostic LLM context feeder https://bit.ly/4jHmQsg

Show HN: Clai – Unixlike vendor agnostic LLM context feeder Posting my tool clai again since tooling seems to be a buzz now a days. Clai uses the conversation system and 'custom tools' when approaching coding tasks. This allows the LLMs to query the file system so that it builds the context specifically for the prompted usecase. Codex and Copilot etc usually takes entire repos as context, causing millions and millions of tokens, which of course is expensive. Clai, on the other hand, achieves the same result at lower cost, especially since it's possible to tweak which model to use and design specialized prompts in profiles to achieve certain tasks. I wrote the majority of this tool over a year ago now, only now I've seen the big corporations 'catch up' with codex cli and claude sdk. So the benefit with clai here is that it's vendor agnostic. https://bit.ly/4a7JllR June 3, 2025 at 04:41AM

Show HN: Page Magic: Use AI to customize any web page https://bit.ly/4jBwdcS

Show HN: Page Magic: Use AI to customize any web page I built this Chrome extension (using Claude Code) to help me customize the style of web pages to my liking. It's not perfect, but it does a decent job most of the time. You will need to bring your own Anthropic API key and add it in the settings if you want to try it out. Features: - Use natural language to customize any web page - You can make the changes apply to the current page only or domain-wide - You can see your prompt history for the page and toggle any of them - Cost is tracked using Anthropic pricing and token counts (it may not be 100% accurate, but close enough) Cost per change tends to be around $0.005 depending on page size. Things you can try: - Change the background color, text color, etc. - Remove obnoxiously large hero images - Reduce line spacing - Increase content area width - Remove stickiness of top headers - ... anything you can think up https://bit.ly/3T37KSL June 3, 2025 at 01:24AM

Show HN: Agno – A full-stack framework for building Multi-Agent Systems https://bit.ly/4kMkzwJ

Show HN: Agno – A full-stack framework for building Multi-Agent Systems https://bit.ly/4kQtqgZ June 2, 2025 at 02:18AM

Show HN: I built an AI Agent that uses the iPhone https://bit.ly/3Flpkyl

Show HN: I built an AI Agent that uses the iPhone It’s powered by OpenAI’s GPT 4.1 model. Uses Xcode UI tests + accessibility tree to look into apps, and performs swipes, taps, etc to get things done. https://bit.ly/3HfQ3Np June 2, 2025 at 03:37AM

Show HN: Moon Phase Algorithms for C, Lua, Awk, JavaScript, etc. https://bit.ly/3FsREij

Show HN: Moon Phase Algorithms for C, Lua, Awk, JavaScript, etc. https://bit.ly/43WetnN June 2, 2025 at 12:22AM

Show HN: AI in Email Conversations https://bit.ly/4551GRa

Show HN: AI in Email Conversations https://bit.ly/43Fp5Gu May 28, 2025 at 05:57PM

Show HN: Purpose Reminders – One simple, positive act emailed monthly to all https://bit.ly/45yRpg0

Show HN: Purpose Reminders – One simple, positive act emailed monthly to all Hi HN, I built Purpose Reminders ( https://bit.ly/43GszIC ). Our first monthly action – "Leave a positive review for a local business" – goes out June 1st (very soon!). The core idea: What if thousands of us did the same small, positive act each month? You get one email, choose to act or skip (no pressure), and then see the collective, anonymous impact. It's 100% free, built with Next.js/Supabase/Resend. My attempt at a simple way to foster some collective goodwill. What do you think of the concept? https://bit.ly/43GszIC May 31, 2025 at 10:51PM

Show HN: MCP Defender – OSS AI Firewall for Protecting MCP in Cursor/Claude etc. https://bit.ly/43ROz4t

Show HN: MCP Defender – OSS AI Firewall for Protecting MCP in Cursor/Claude etc. Hi HN, MCP Defender is an open source desktop app that automatically proxies your MCP traffic in AI apps like Cursor, Claude, Windsurf and VSCode. It then scans all requests and responses between the apps and the MCP tools they call. If it detects anything malicious, it alerts you and lets you allow or block the tool call. While the threat landscape of MCP is still being actively researched, there are dangerous things that MCP Defender can block today. For example, a developer asks Cursor to fix a Github issue with an attached crash log. However, the Github issue was created by an attacker who included secret instructions buried in the crash log. These instructions tell Cursor to send the developer’s SSH keys to a server the attacker controls. MCP Defender detects these malicious instructions and alerts the developer who otherwise may not be careful in running tool calls. The scanning is currently done via an LLM and checks for things like prompt injection, credential theft (ssh keys, tokens) and arbitrary code execution. You can use an MCP Defender account or provide your own API keys for LLM providers to perform the scanning. Currently we’ve published a beta Mac build and we’ll soon publish builds for Windows and Linux as well. Any feedback would be greatly appreciated. Thanks! https://bit.ly/452LQXg May 29, 2025 at 06:40PM

Show HN: I made a metabolic coach chatbot for weight loss https://bit.ly/3Fh7L2t

Show HN: I made a metabolic coach chatbot for weight loss Hi HN, I made a metabolic AI coach to help people with their weight loss and metabolic challenges. In testing with about a dozen people, they have been impressed with how well it figures things out and its surprising insights. I'm surprised, too, at how good it gets compared to typical responses people would ask vanilla chatbots and how positively people are responding to it. https://bit.ly/3HeNT0x Happy to hear feedback or ideas! May 31, 2025 at 12:27AM

Show HN: Smart Silence – Remind your iPhone to stay quiet in quiet places https://bit.ly/4mFdVdi

Show HN: Smart Silence – Remind your iPhone to stay quiet in quiet places Hi HN, I built an iPhone app called *Smart Silence* after sitting in a quiet setting (a service, actually) where someone’s phone rang loudly and interrupted everything. It wasn’t intentional — just one of those forgetful moments. I started wondering: what if our phones could gently remind us to stay silent when it matters? *Smart Silence* helps iPhone users do just that. It lets you: - Mark places where silence is expected (like libraries, meetings, classes, or houses of worship) - Get a reminder when you enter, with an easy Shortcut to enable Do Not Disturb - Schedule quiet times (e.g. “Mondays 9–11am at this place”) - Share Silent Places with others — so your community, school, or workspace can use the same setup - Stay fully in control — no auto-silencing, and no location tracking outside of defined zones It’s currently available via TestFlight: https://apple.co/4kj9CTl I’d love feedback — especially around usability, edge cases, or features you’d expect. If you run or attend a place where silence matters, I’d love to hear your thoughts. https://apple.co/4kj9CTl May 28, 2025 at 02:51PM

Show HN: Changefly – Rebuilding the foundation of privacy and authentication https://bit.ly/4dEJ3FX

Show HN: Changefly – Rebuilding the foundation of privacy and authentication Lukas here, founder of Changefly. For those of you who might remember neworder.box.sk and astalavista.box.sk, I was one of the admin's at a very young age. Fast forward to 2018, I set out to help people regain their privacy. Google invited us into the Google Cloud Startup program which led to the creation of Changefly. After years of truly challenging work and thousands of iterations, Changefly ID was born. Changefly ID solves the problem both users and companies face on a daily basis... spam, scams, bots, account takeover attacks. At face value it looks like an ordinary code, but in fact, it is an encrypted security code that only the user knows and has access to use (a distributed anonymous authentication code). Changefly ID has a lot of flexibility -- replace traditional authentication (which you absolutely should do) or use secondary for multi-factor authentication (a good stepping-stone). It also includes end-to-end communications with your users through Changefly (not email, sms, or other unsecured channels). Additionally, the Changefly app data is also end-to-end encrypted as is the local data. We made access to Changefly ID easy and free with our Developer API. Changefly ID really does stop bots, spam, scams, and other threats from getting anywhere near users or their accounts. p.s. A big thanks to Tom (HN moderator) for their help! https://bit.ly/3HhDX6l May 30, 2025 at 09:47PM

Show HN: Donut Browser, a Browser Orchestrator https://bit.ly/4dFjGDS

Show HN: Donut Browser, a Browser Orchestrator Hi HN, I'm excited to share my open source project, a browser orchestrator. It's purpose is to make it easy to manage many browser profiles on one system. Currently it only works on MacOS, but since I've built it using Tauri (which is a Rust backend and TypeScript frontend), I expect to add Linux and Windows support in the future. I've built it primarily for myself as I use a lot of browsers and having an easy way to manage all of my profiles would make (have made, actually) my dock less cluttered haha. Also, part of why I built it is because as someone who doesn't really care about anti-detect features (which I might support in the future), I don't understand how they cost so much for a very limited number of profiles in pretty much all anti-detect browsers. I feel like a lot of people feel the same and will cover their use cases with my free tool. If you try it, please share your feedback! I haven't seen any open source projects like this and want to learn more about how people might use it. https://bit.ly/4kGN2E8 May 30, 2025 at 05:09AM

Show HN: MCP Server SDK in Bash (~250 lines, zero runtime) https://bit.ly/4mD54ZL

Show HN: MCP Server SDK in Bash (~250 lines, zero runtime) https://bit.ly/3Fx46NS May 30, 2025 at 05:25AM

Show HN: I'm starting a social club to solve the male loneliness epidemic https://bit.ly/3ZalYVA

Show HN: I'm starting a social club to solve the male loneliness epidemic The other day I saw a post here on HN that featured a NYT article called "Where Have All My Deep Male Friendships Gone?" ( https://bit.ly/4mEqntY ) and it definitely hit home. As a guy in my early 30s, it made me realize how I've let many of my most meaningful friendships fade. I have a good group of friends - and my wife - but it doesn't feel like when I was in college and hung out with a crew of 10+ people on a weekly basis. So, I decided to do something about it. I’ve launched wave3.social - a platform to help guys build in-person social circles with actual depth. Think parlor.social or timeleft for guys: curated events and meaningful connections for men who don’t want their friendships to atrophy post-college. It started as a Boston-based idea (where I live), but I built it with flexibility in mind so it could scale to other cities if there’s interest. It’s intentionally not on Meetup or Facebook - I wanted something that feels more intentional, with a better UX and less noise. Right now, I'm in the “see if this resonates with anyone” stage. If this sounds interesting to you and you're in Boston or another city where this type of thing might be needed, drop a comment or shot me an email. I'd love to hear any feedback on the site and ideas on how we can fix the male loneliness epidemic in the work-from-home era. https://bit.ly/3Hvw11b May 30, 2025 at 12:57AM

Show HN: Clean Simple DNS Lookups https://bit.ly/43D71fW

Show HN: Clean Simple DNS Lookups Hey HN, Last weekend I vibe-coded a cool website that lets you do easy DNS record lookups. I know you can just use dig or nslookup, but oftentimes I'm too lazy to remember the syntax, and there are less technical users who need to manage DNS entries but aren't comfortable with the command line. We debug customer DNS issues often at ImprovMX, and we typically link to tools like mxtoolbox.com to point out DNS record issues. But those tools seem quite bloated and from the 2000s. I wanted something super clean & simple, and there were a few features I thought were ergonomically needed but lacking: - no confusing dropdowns or syntax for DNS lookup, just put in your domain or subdomain - click-to-copy for all values - header-links so we can provide URLs that will direct another user to an exact domain and which record we want to reference This was SUPER FUN to vibe code! The frontend was pretty much one-shotted with lovable. It's amazing how good AI is when working on a clean slate with all the latest popular frameworks (react, tailwind, shadcn, etc.). And I spent the next few hours making small tweaks with cursor. The backend is a dead simple python flask server. Both are hosted on render.com <3 I love how simple and value-oriented render.com is. It's always the provider that gives me the least headache when I want to just launch and forget something. Give it a try and let me know what you think! https://inspector.improvmx.com May 29, 2025 at 07:51PM

Show HN: Typed-FFmpeg 3.0–Typed Interface to FFmpeg and Visual Filter Editor https://bit.ly/4mBkTjB

Show HN: Typed-FFmpeg 3.0–Typed Interface to FFmpeg and Visual Filter Editor Hi HN, I built typed-ffmpeg, a Python package that lets you build FFmpeg filter graphs with full type safety, autocomplete, and validation. It’s inspired by ffmpeg-python, but addresses some long-standing issues like lack of IDE support and fragile CLI strings. What’s New in v3.0: • Source filter support (e.g. color, testsrc, etc.) • Input stream selection (e.g. [0:a], [1:v]) • A new interactive playground where you can: • Build filter graphs visually • Generate both FFmpeg CLI and typed Python code • Paste existing FFmpeg commands and reverse-parse them into graphs Playground link: https://bit.ly/3FDlwZ8 (It’s open source and runs fully in-browser.) The internal core also supports converting CLI → graph → typed Python code. This is useful for building educational tools, FFmpeg IDEs, or visual editors. I’d love feedback, bug reports, or ideas for next steps. If you’ve ever struggled with FFmpeg’s CLI or tried to teach it, this might help. Thanks! — David (maintainer) https://bit.ly/45hvlqr May 29, 2025 at 05:23AM

Show HN: Image-to-Image Translation Model https://bit.ly/4jqvScT

Show HN: Image-to-Image Translation Model We launched a v1 of a image to image translation API which translates the text on an images by replacing the existing text. For v1, it's pretty much a model pipeline: OCR current text -> generate mask -> erase text -> translate text -> use embedding comparison to find similar font -> map text back on image v1 was more like a prototype which already beats many of the similar services provided by Google, Azure, etc We're working on v2 where we're training a diffusion model to translate the text on the image. We've got the pipeline working for English and Chinese, and now we're building datasets for other languages. https://bit.ly/4jovA66 May 29, 2025 at 12:47AM