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

Show HN: FizzBuzzAI – The Most Inefficient FizzBuzz Solution Ever Made https://bit.ly/3FdB3yZ

Show HN: FizzBuzzAI – The Most Inefficient FizzBuzz Solution Ever Made https://bit.ly/3HvbfPh May 29, 2025 at 12:19AM

Show HN: 3DGS implementation in Nvidia Warp: clean, minimal, runs on CPU and GPU https://bit.ly/3FneRCs

Show HN: 3DGS implementation in Nvidia Warp: clean, minimal, runs on CPU and GPU CPU & GPU with Zero Hassle Built with NVIDIA Warp, the same code runs seamlessly on both CPU and GPU — no need to deal with CUDA setup, driver issues, or device-specific kernels. Just flip one config line. Learn Modern Graphics the Easy Way Explore core concepts in differentiable rendering and parallel graphics programming — no need for expensive GPUs or thousands of lines of boilerplate. Minimalist & Educational This isn’t another massive codebase. It’s a clean, hackable implementation built for clarity — perfect for study, prototyping, or teaching yourself how Gaussian Splatting works. https://bit.ly/3FewJzs May 28, 2025 at 04:23AM

Show HN: AutoThink – Boosts local LLM performance by 43% with adaptive reasoning https://bit.ly/4dCoQAy

Show HN: AutoThink – Boosts local LLM performance by 43% with adaptive reasoning I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity. The core idea: instead of giving every query the same "thinking time," classify queries as HIGH or LOW complexity and allocate thinking tokens accordingly. Complex reasoning gets 70-90% of tokens, simple queries get 20-40%. I also implemented steering vectors derived from Pivotal Token Search (originally from Microsoft's Phi-4 paper) that guide the model's reasoning patterns during generation. These vectors encourage behaviors like numerical accuracy, self-correction, and thorough exploration. Results on DeepSeek-R1-Distill-Qwen-1.5B: - GPQA-Diamond: 31.06% vs 21.72% baseline (+43% relative improvement) - MMLU-Pro: 26.38% vs 25.58% baseline - Uses fewer tokens than baseline approaches Works with any local reasoning model - DeepSeek, Qwen, custom fine-tuned models. No API dependencies. The technique builds on two things I developed: an adaptive classification framework that can learn new complexity categories without retraining, and an open source implementation of Pivotal Token Search. Technical paper: https://bit.ly/3Z31NJ2 Code and examples: https://bit.ly/3Sm2LMT... PTS implementation: https://bit.ly/4kbUxCZ I'm curious about your thoughts on adaptive resource allocation for AI reasoning. Have you tried similar approaches with your local models? May 28, 2025 at 03:39AM

Show HN: Weather2Geo – Geolocate screenshots from weather widgets https://bit.ly/45wVSzV

Show HN: Weather2Geo – Geolocate screenshots from weather widgets Hi HN, I built an OSINT tool called Weather2Geo that helps locate where a screenshot was taken based on the weather widget data visible (e.g. temp, condition, and local time in the taskbar). People often post these without realizing how specific those values can be in combination. It works by comparing the given weather condition, temperature, and time against current data from thousands of cities. It’s timezone-aware, supports fuzzy matching, and groups results geographically to reduce noise. It’s most effective on recent screenshots, ideally taken within the last hour—since weather and daylight conditions change quickly. The tool helps pinpoint likely locations when screenshots lack EXIF data or other traditional OSINT clues. It’s open source here: https://bit.ly/44WfzB2 Would love feedback, bug reports, or to hear if you think this has other use cases. - Elliott https://bit.ly/44WfzB2 May 27, 2025 at 11:31PM

Show HN: Millau – self-configuring ingress proxy for Docker Swarm https://bit.ly/4dAa9xS

Show HN: Millau – self-configuring ingress proxy for Docker Swarm I still use Docker Swarm. It's simple, fast to set up, and easy to teach. But I got tired of managing routing to microservices. Nginx and HAProxy need config redeploys, Traefik is powerful, but its configuration via labels quickly becomes unmaintainable. So I built Millau — a free ingress proxy and load balancer for Docker Swarm microservices. Add a few labels to the service, and traffic gets routed. No proxy restarts, no config files. Example: ``` # service deploy: labels: - "millau.enabled=true" - "millau.port=9000" ``` Millau listens to Docker events, discovers labeled services, and routes traffic using host and path matching. Unlike Traefik, Millau supports load balancing across services. I use it to deploy different versions e.g. Blue, Green, Red of the same microservice. If Red crashes, Millau routes to Blue or Green. If Blue slows down, Millau marks it inactive for 60s and routes to Green. Millau supports TLS termination and mTLS. It exposes Prometheus metrics and ships with a prebuilt Grafana dashboard. It's in production, serving its own site and several side projects. Let me know what you think, especially if you're still using Docker ecosystem in prod. Thanks. https://bit.ly/3Zq2gW3 May 26, 2025 at 10:15PM

Show HN: Get Red Carpet, CloseUp – Photoshoots in 10 Mins https://bit.ly/4dJ8NRy

Show HN: Get Red Carpet, CloseUp – Photoshoots in 10 Mins https://bit.ly/43nzCWo May 26, 2025 at 04:12PM

Show HN: JSON Commenter, add comments with valid JSON syntax https://bit.ly/4dxkHxA

Show HN: JSON Commenter, add comments with valid JSON syntax JSON Commenter is a vscode extension that lets you create inline comments in a JSON file while keeping valid syntax. You create a block with a command that places the comment anywhere legal in the JSON. The text is edited inline and supports word wrap, padding, margins, etc. The comment is in a somewhat good-looking box with minimal extra characters. Zero-width unicode chars give keys that only show two quotes. This is a sample comment block... " ":"----------------------", " ":" This is a comment. ", " ":"----------------------", https://bit.ly/4kkMRic May 26, 2025 at 11:33PM

Show HN: I built an AI image tool solo in 1 month https://bit.ly/4mBPEoI

Show HN: I built an AI image tool solo in 1 month Hey HN! Over the past month, I built Styleloop, a solo side project that uses AI to transform images into stylized artworks. The primary focus is image-to-image transformation, with curated styles like Ghibli, pixel art, Animal Crossing, and more. It’s my first real SaaS project, and honestly, the process changed how I think about building and shipping products. From backend to payments to UI polish — doing it all solo was exhausting and incredibly rewarding. Styleloop was built with Next.js, Supabase, Stripe, and Cloudflare. I plan to keep improving it and add more creative modes. I'd love your feedback on whether you’re into AI x creativity or solo hacking projects! Thanks for checking it out! https://bit.ly/45qsBqx May 26, 2025 at 04:12AM