threadfork
Hi HN, I built threadfork. It's an AI notetaker where the whole pipeline runs locally on Apple Silicon. Your microphone and system audio gets captured without a meeting bot and most importantly your meeting data doesn’t get sent or saved anywhere. I've been building in the privacy + local LLM space for the past several years (I started DataFog, an OSS PII detection library with 300K+ downloads); keeping all the processing and data on-device was a day 0 condition for me when building this out. Granola's updated privacy policy, effective later this week, keeps non-enterprise users opted into model training on "de-identified" data by default. Having built PII detection for a living, I'll say plainly: de-identifying meeting transcripts is really hard. Names are the easy part; deal terms, client details, and health disclosures are the transcript. For the lawyers, consultants, and therapists I've been talking to, the only version of this that holds up is the model never seeing the data at all. It's macOS 14+ on Apple M-Series computers (for now), 14-day trial, no credit card. I have a user running this on an M1 8GB so older machines welcome. $40/month after that. I use this product daily and you can expect regular updates. Welcome any/all feedback.
Computable
Hey we are Computable. We spent years building trading infrastructure at Jump Trading and Coinbase. From that point of view, compute looks like energy markets before 2000: everything trades through private bilateral leases, there’s no visible price, and nothing can be resold. The same H100 rents at a 2x spread depending on who’s asking, and once you sign a 24-month lease, it can never change hands. So we built a market for GPU nodes, sold by the calendar week. Here are three things you can do on it that you can’t do anywhere else: - Buy exactly the weeks you need. Three nodes for the last two weeks of October means you pay for those two weeks and walk away when the run is done. You don't have to commit to 6-24 months, and there's no flexibility premium. - Sell back what you don’t use. If your plans change, unused weeks turn back into cash: we keep a market quote posted on every position, so there’s always a price to hit. - Buy (or sell) the future. Lock January in July at a price you set, so the cost of a future run is known before another 40% H100 rate jump makes it not. The first auction is live now at https://market.getcomputable.com: a block of nodes, August through the end of January. Bidding closes July 31. The bids are sealed. You bid how many nodes, which weeks, and your price. Every clearing price gets published after settlement, because nobody knows what a GPU week is worth and we want the prints to exist in public. Happy to go deep in the comments on anything, including the clearing mechanism, which is a packing problem and was fun to design!
Newrepublic
FBI Forced to Reveal New Details on How It Redacted Epstein Files
Turn casual photos into professional headshots with AI
A while back I needed an ID photo for something urgent. The only way to get one was to find a photo studio, book a time, and wait around for it to be printed, and just one set cost about $13 (converted from my local currency). With how far AI has come, I felt like this should be easier and cheaper by now. So, I built Portraify. It turns 1–3 casual photos into professional headshots, and also does US passport photos and 1-inch / 2-inch ID photos. The thing I cared most about was likeness. A headshot or an ID photo is only useful if it actually looks like you, otherwise there's no point. So the AI is tuned to reproduce the real you, no beautifying, no de-aging. It also checks your input photos before generating (lighting, sharpness, face visibility), so you don't waste a generation on a photo that was never going to work. I know people care a lot about uploading their face to some random AI tool, so to be clear: input photos are processed in memory and discarded after generation. They're never persisted or used for training. Generated portraits are stored so you can re-download them. One thing to know before you try: it needs a signup (no card) and you get 3 free generations. Let me know if there's anything that could be improved, or anything that doesn't work well in real-world use. Happy to answer any questions.
Ekko
Hi everyone, I am a big privacy activist and the amount of privacy concerns in the internet with the discussions around European Chat Control, Meta removing e2ee in Instagram and corporations harvesting personal data for AI training is on the rise. The closed source social media companies keep managing and storing our private keys, allowing them to effectively access all of our personal communications.. Many open source alternatives exist, but the problem I kept running into was not a lack of good private messengers. Signal, SimpleX, and other projects already do important work The problem was getting the people to move. A messenger is only useful when the person you need to reach is there. Asking friends, family, coworkers, or customers to abandon their existing chats is a very high barrier. Ekko takes a different approach. It runs as a browser extension on top of existing messengers. Both people still need Ekko, but they do not need to move their conversation. You can continue using the Instagram, WhatsApp, Telegram, or Messenger chat they already share. Actively building this and trying to achieve a seamless automatic encryption in the UI across all popular messengers and adding support across all browsers, IOS, android and social media.. Under the hood, Ekko uses hybrid X25519 + ML-KEM-768 and XChaCha20-Poly1305. Private keys are generated and kept on your device. You can claim an Ekko handle to make exchanging public keys easier, exchange invitations directly without an account, or self-host the public-key directory. Currently: - A Chromium browser extension, Experimental Firefox and Safari builds - Instagram, WhatsApp Web, Telegram Web, and Messenger integrations - A self-hostable key directory - Open-source client, protocol, and server code Early version Chrome Web Store: https://chromewebstore.google.com/detail/ekko/oaihgpmbkeafbp... Source code: https://github.com/useekko/ekko-core Website and demo: https://useekko.app I would genuinely appreciate direct feedback especially from people familiar with applied cryptography, browser security, key verification, messenger integrations, potential solutions for iOS UI integration (faster than using browser w/ Safari extension) If you try it, please tell me what breaks or what feels confusing. Actively trying to make this better as a side project! If you discover a security issue, email kirill@useekko.app rather than posting it publicly. Looking for feedback! :)
Ex Situ
Hi, I designed and developed a spatial index that maps museum artefacts as connecting arcs/hyperlinks from their origin site to institutional location/sources. The Index specifically looks at western/euro-american institutions and maps their collection categorised by them under Islamic art, Asian/African art, ethnological collections, Middle East, South America etc. Started as my MA thesis in 2022, kept building since, mostly solo with a little funding. Fully open source, self-hosted, AGPL-3.0, Next.js + Deck.gl on the frontend, Strapi backend, Python ETL pulling from museum open-access APIs. Currently indexing over 100k artifacts from all over the world, across 8 collections (Met, V&A, SMB Berlin). Recently added an md export so researchers can download provenance data for a filtered set of artifacts. The infrastructure is conceptualized as an indexer, not a hoster. Even images are kept as URLs pointing to the source institutions. It's connective tissue between archives that were never designed to speak to each other, with an origin-first search UI concept. The data model is on purpose flat, to avoid encoding problematic taxonomies, and routes researchers directly to the source giving responsibility to the source institutions rather than duplicating institutional data. It indexes the relationship between origin sites and destination collections. Coming from a design background, taking this project from prototype to production app has been incredibly rewarding, but honestly it’s getting a little bit overwhelming to scale alone. I would love community’s feedback on performance scaling, any code contributions, data pipelines for missing museum apis or general feedback. Repo: https://github.com/hburakyel/ex-situ Live: https://exsitu.app
Immersive Gaussian Splat tour of grace cathedral, San Francisco
Show HN: Immersive Gaussian Splat tour of grace cathedral, San Francisco
Wheesper
Show HN: Wheesper – Start an anonymous discussion with a link
A comprehensive, filterable list of AI agent jails
I built this from another Show HN thread where people were mentioning alternative AI agent sandboxes and jails
How much profit does your employer make per employee?
Show HN: How much profit does your employer make per employee?
A canvas-based note taking and organizer app
So I've been working on this app for a very long time now. Started off by wanting an app that separates long form notes from short form notes visually and keeps everything organized on a canvas. The app features: -Sticky notes for quick, small notes and A4 notes for long form documents -A quick mode that uses local storage to quickly open the app and jot down a thought on the canvas -A PDF export option that exports your notes into 3 custom designed PDF styles -Visual hierarchy to replicate file structure instead of a linear fashion, where your files are notes, stacks are folders and labels are names for your folders Would love to continue working on this app if you guys like the concept.
OfflineTTS
Show HN: OfflineTTS — Free browser-based TTS & STT that runs locally