useekko.app
Show HN: Ekko – post-quantum E2EE layer for Instagram, WhatsApp, Telegram Webhttps://useekko.app/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 workThe 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 IJul 21, 2026 12:39 AM
github.com
Show HN: Effort Router: Intelligent /effort selection per Claude turnhttps://github.com/cfitzgerald-pd/effort-routerDynamic effort selection, while possible in some other tools like OpenCode, does not exist in Claude Code.Having dynamic effort set per conversation turn means:- Less tokens burned on easy queries (e.g. something low /effort can do goes to xhigh because it's the convo default)- You avoid mistakes: Prompts requiring high effort (like a refactor or security threat modeling) go to high or xhigh instead of medium to reduce likelihood of mistakes and reduce wasted tokens.I created this out of a personal need and it's been game-changing. My Claude sessions are way more productive with less back/forth.Give it a try and feel free to contribute!Jul 20, 2026 4:53 PM
news.ycombinator.com
Prodigy – AI Workforce for professional teamshttps://news.ycombinator.com/item?id=48965750Hello folks! I am Samay, founder of Prodigy. We're building an AI infrastructure that provides on-demand subagents who work like autonomous teammates alongside your team.How are we any different? 1. Our Prodigy brain indexes every bit of information from tools used by your company. This includes emails, documents, meetings, conversations, git work, CRM etc. The agents communicate with the brain instead of humans.2. The Prodigy orchestrator spins up agents with designated roles and goals. Each agent has a clear objective, evidence, verification tests and stopping condition.If you're interested about the product or want to chat in general, please reach out! Website: https://www.prodigy.org.inJul 19, 2026 7:34 AM
bing.com
2026 Haskell Stakes predictions, horses, odds, post positions: Surprising picks from elite racing experthttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d2dbd781d4a0bacddecebb6d1c460&url=https%3A%2F%2Fwww.cbssports.com%2Fbetting%2Fnews%2F2026-haskell-stakes-predictions-horses-odds-post-positions-weather-picks-best-bets%2F&c=2736593404632405896&mkt=en-usFurther Ado will look to get back in the conversation as one of the top 3-year-olds in the country when he runs in the 2026 Haskell Stakes on Saturday at Monmouth Park. Two starts ago he finished 11th ...Jul 18, 2026 3:04 PM
news.ycombinator.com
Show HN: Scaffold a raw idea into something ship-ready in under a minutehttps://news.ycombinator.com/item?id=48958157Several months ago, I joined a WhatsApp community with around 500 people. Once a community becomes large enough, you start noticing certain patterns.Whenever someone announced a new product idea, the responses were usually the same:“That sounds amazing.”“I would definitely use it.”“Great idea.”“Can’t wait to try it.”I do not think people were intentionally being dishonest. Most were simply being kind. Nobody wants to be the person who discourages someone before they have even started.But that is also the problem. Agreement is easier than challenge, and encouragement can easily be mistaken for validation.The second moment happened at a local accelerator hub. I met a founder who had hired a developer to build an online education platform for her workplace-harassment awareness programme.I asked whether she had used ChatGPT to pressure-test the idea before committing to development. She confidently told me that she had.That conversation stayed with me.Using an LLM is easy. Knowing what to Jul 18, 2026 1:53 PM
news.ycombinator.com
AI Gets Trapped in a Circular Loop on Climate Sciencehttps://news.ycombinator.com/item?id=48956370Today, I was asking Ai about the Canadian Wildfires and forest management. Instantly, the ai resorted to following the common narrative, and pushed macro human-caused climate change as an “objective fact.” I wanted to push back on the logic of this, because this narrative goes against core principles of scientific transparency. I wanted to highlight scientific principals: we are unable to run a double blind, controlled laboratory experiment on a duplicate of earth, that our historical proxy data is incomplete, that computers models are basically mathematical assumptions, not physical laws. This time the ai model abandoned the canned scripts, and completely broke character admitting that framing a predictive theory as an absolute “fact” for the masses is an ethical failure and it damages scientific transparency. Here is exactly where the turning point of the conversation that caused the models logic to completely collapse “ User: if science cant claim something is a definitive fact thenJul 18, 2026 9:03 AM
news.ycombinator.com
Ask HN: Are We Getting Dumber?https://news.ycombinator.com/item?id=48954653I have a very accomplished relative who I trust a lot and has been a role model for me. I've always trusted their judgement and they've never steered me wrong to date. I was recently having a conversation with them about sort of everything. During the conversation I essentially asked what separates success from failure (it was an open ended across the board kind of question) and their response was "critical thinking skills".Seems like I simple answer, but I've also always felt the same way. Some of my biggest pet peeves are people just accepting outcomes without explanation, writing off things as merely coincidence without digging deeper, or offloading the burden of thinking to someone else.Given the rapid pace of AI and it's ability to be a crutch, the misinformation and disinformation that plaques the internet, and people just settling for the simplest answer without questioning or thinking through the methodology to get there or whether or not it's true, ARE WE GETTING DUMBER?It's aJul 18, 2026 2:35 AM
bing.com
Best teeth whitening kits 2026, tested for a brighter smile at homehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8cc09d9c2143358a46edb35031a269&url=https%3A%2F%2Fwww.msn.com%2Fen-gb%2Fhealth%2Fother%2Fbest-teeth-whitening-kits-2026-tested-for-a-brighter-smile-at-home%2Far-AA288hRu&c=2015083832515305508&mkt=en-usJetting abroad to get the straightest and whitest veneers – also coined “Turkey teeth” – has dominated conversations in the dental space over the last few years. Luckily, there are plenty of ...Jul 17, 2026 6:35 AM
anam.ai
Show HN: Real-time avatars that change emotions as you talkhttps://anam.ai/Hey HN, we're Ben and Caoimhe, cofounders of Anam. We build interactive avatars and just shipped our latest model, cara-4. This is the first avatar model which can naturally shift emotions and expressions during the conversation; a feature we’re calling “Director Notes”. The way it works is relatively simple: we have an LLM provide cues such as [laughter], [sad], [warm] interleaved with the speech, which we then condition our animation model with. To test it out, we commissioned a blind study from Mabyduck.com with 200 participants, 1,600 rated live interactions across six criteria. Cara-4 ranked first overall and was preferred head-to-head over each competitor on overall experience, lip-sync, visual quality and “naturalness”. On latency, measured across a full week of live traffic, end of user-speech to first video frame is ~1.2s median. The avatar model's own share is just ~100ms; most of the rest is waiting on STT, LLM, TTS or various forms of buffering (an unsung latency killer). HJul 14, 2026 2:20 PM
github.com
Show HN: Rejourney – Open-source revenue leak prediction for web and mobile appshttps://github.com/rejourneyco/rejourneyHello there (General Kenobi's favorite way to start the conversation),I’m Rashid, a sophomore at UT Austin. I built Rejourney.co (https://rejourney.co/) to predict issues with your apps and websites before they happen, based on real user session recordings.Here is a silly video (with cats) on how it works: https://www.youtube.com/watch?v=Z95MDxBXMjkIt’s open source, and the post link is the github repo, but here it is again: https://github.com/rejourneyco/rejourneyI originally built this because I had a campus freebie finder app that grew quickly, and I had a lot of users dm me on instagram about issues with the app’s onboarding and UX confusion. I initially lost about 340 users out of my 5,000ish users because of these issues, and I had to recover some by nudging them with notifications. It was a big pain, and I felt bad that I lost this many users to small and easy fixes. So I built Rejourney to predict that before it happens. Here is how it works:First, the SDK is installed on Web JJul 14, 2026 11:06 AM
ggufun.grokked.it
Show HN: GGUFun, play snake and a simple maze on Ollama using hand crafted GGUFshttps://ggufun.grokked.itA couple weeks ago I was wondering if I could build a GGUF model file that, when run on ollama, would deterministically answer with the same exact sentence (not simply using a system prompt).That was surprisingly easy to implement, leveraging mostly the unembedder, so I started exploring GGUFs.First I built a simple GGUF that could compute the position of a point in a limited grid, using 4 directional tokens as input. All weights are "hand crafted", no training involved. Of course, being ollama stateless, it needs to compute everything from scratch each time from the whole conversation.Then (with the help of coding agents) I used it as the base to build a "complete" game of snake: it can only play 57 turns (it can be fixed though) and the position of food is computed using a hash, without checking if the new position is under the snake. But it works.Since the obvious evolution would be to run Doom on ollama, I at least got a first person roaming demo working, where the frontend only knJul 13, 2026 9:03 AM
github.com
Show HN: Juggler – an open-source GUI coding agent, by the creator of JUCEhttps://github.com/juggler-ai/jugglerHello HN, I don't post on here much, but wanted to get some eyes on a new project I'm just launching. I think we definitely need one more AI code agent..I'm a long-term C++ dev, and over 30+ years I've created some successful audio dev tools (JUCE, the Tracktion DAW, the Cmajor DSP language). All of these came from me getting annoyed with something I had to use, and deciding to have a go at my own take on whatever it was.So Juggler is my attempt at an AI code agent, after spending too many hours loving what the models could do, but hating the CLI experience, and having some opinions of what a better UX might be for this stuff.Lots more blurb on the website and github, but a quick tech dump which might grab your attention if you're into these things:A session is a document, not a log file. Each conversation is a Yjs CRDT tree. It can branch into sub-threads (recursively), and you can drill down, backtrack, edit, undo/redo, and inspect everything: tool calls, approvals, and the raw conteJul 12, 2026 6:28 PM
bing.com
She took out her AirPods and changed an 81-year-old stranger's lifehttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d7ada94d2497b8cdfee2ec51531c0&url=https%3A%2F%2Fwww.yahoo.com%2Flifestyle%2Farticles%2Fstranger-train-befriends-helps-81-010510397.html&c=7250805279334802838&mkt=en-usAdd Yahoo as a preferred source to see more of our stories on Google. A chance conversation on a train turned into an unlikely friendship that changed two women's lives. Molly Selin, 27, was heading ...Jul 12, 2026 6:05 PM
vuci.ai
Show HN: Vuci – make the spoken word searchablehttps://vuci.ai/feed/hi, I'm Reuben Over the past few months I've been building a platform where all the information is sourced from spoken conversations, and I wanted to make this content searchable, savable, and shareable. Presented in a well-designed format, similar to Yahoo but with higher IQ content.Like most, I listen to a lot of podcasts, but I wanted to connect the dots on different topics and read the parts which are interesting more deeply. Sharing bits and pieces with friends was also a motivating factor, as well as alerts which feed into my other pipelines.That said, I'm not sure which parts of the platform will resonate with users or not, so it's an experiment in progress.Technicals: I love my craft (both design, and code), so I took ample time to think about UX and design it in Figma. It's cookiecut from ample projects I have in Django and HTMX, and scaffolded my way through. Hosted on Digitalocean, and AI agnostic from an LLM perspective. I can go deeper into these, but they probably deserveJul 10, 2026 9:10 AM
ello.com
Building a real-time AI tutor for 5-year-oldshttps://www.ello.com/blog/teaching-a-child-in-1000-msHey HN! We've spent the good part of this past year building an AI tutor that teaches kids ages 4-9 reading, math, ESL and more. Getting an AI tutor to effectively teach a child turns out to be a really hard technical challenge, this took getting the underlying architecture right.Our tutor steers the UX in real-time and makes complex decisions on the fly. Doing both at conversation speed required us to replace the standard tool-use loop. We built our own tutor harness that utilizes a streaming interpreter that executes actions, while an asynchronous planner model reasons ahead of the conversation and makes calls that drive the child's learning. On top of it all, we developed a safety system that checks every turn without it causing an interruption to the activity and conversation flow.Effective teaching isn't just about answering a child's question quickly, rather making the right move at the right moment. AI is also going to be an integral part shaping how this generation of kids learJul 9, 2026 8:51 PM
github.com
Show HN: CodeAlmanac – Self-updating wiki for your coding agent (local, Apache)https://github.com/AlmanacCode/codealmanacHello good people of HN,This is Rohan from Almanac (YC S26).Today I want to share CodeAlmanac. It is a self-updating wiki for your coding agent. It lives in your repo as Markdown files and updates from your conversations with your agent. It’s open-source, local, and free.How it works1. Install the CLI and pick your agent (it uses your CC or Codex sub)2. It scans your codebase and generates an initial wiki.3. A background job reads your agent conversations every few hours and updates the wiki4. Your agent queries the wiki through a local SQLite index, using commands like codealmanac search and codealmanac show.Principles it’s based onConversations as a primary source: There’s a lot you discuss with your agent, and there’s a lot said in those conversations that isn’t directly seen in the code. Why the code is shaped the way it is, what ideas you’ve explicitly rejected, and repeatable procedures that the agent did. We document what’s relevant for future agent runs from there.Maintenance, Jul 9, 2026 5:21 PM
github.com
Show HN: Comcent CE – An open-source self-hosted Voice Infrastructure platformhttps://github.com/comcent-io/comcent-ceHi HN,About two years ago, I started working as an independent contractor on a large voice application where we needed much deeper insight into phone calls than the existing platforms could provide.We wanted to answer questions like:How long was the caller waiting in the queue? Which agent rejected or missed the call? How many times was the call transferred? Who transferred it, and when? What actually happened during the conversation?Getting this information turned out to be surprisingly difficult.During the project, we integrated with multiple communication providers. While they handled voice reliably, I found the developer experience frustrating. Simple workflows often required several API calls, some data wasn’t exposed at all, and call recordings weren’t always reliable. No web hooks, all apis were polling. We even ended up recording audio locally on every agent’s computer just to avoid missing conversations, but that meant losing valuable server side context like transfers, queue Jul 8, 2026 9:22 AM
github.com
Show HN: Bike4Mind – open-core AI workbench; any model, agents, RAG, self-hosthttps://github.com/Bike4Mind/bike4mindHi HN, I am Erik Bethke, game dev that has been making online games for 30+ years (Starfleet Command, GoPets, FarmVille, Mafia Wars).For the last 3 years I have been building Bike4Mind and now I have to put my big boy pants on and 'go to market'. Ugh, it would be so much more cozy to fire up a few more agents and fix a few more bugs, polish some more UX - or hey how about a new feature that does Q, R or S?What is Bike4Mind? I started Bike4Mind to be the home of a bunch of AI augmented game development tools, and over time have just kept adding features. It is a full cognitive workbench we have all of the features - notebooks, files, data lakes & RAG, agents (different forms), generate share-able artifacts in react or python. We have secure websockets to connect to our CLI - B4M CLI, so it is truly batteries included - and runs any model - OpenAI, Anthropic, Gemini, xAI, Bedrock. Switch models during a conversation, fork a notebook, run 4 different models on the same prompt, loads of imJul 7, 2026 7:17 PM
github.com
Show HN: Foundation – A Tale of Tokens and Psychosishttps://github.com/nmxmxh/foundationI called my first experience with AI psychosis, master - https://github.com/nmxmxh/master-ovasabi.During the beginning of the coding agent expansion, compute was somewhat free to get with the right methods. I decided to finally build the backend project I'd always wanted to build.I settled on Go for the language. I'd always liked Go because it was easy for me to read whilst also always being in the top ranges for performance.I realise I'd tried to build a codebase with the functions of an everything machine & a platform as a service at the same time.It was a monstrosity of slop, inspiration and conversation. I laboured at this for about eight months. It gave me a perspective into modern development and distributed systems, and a large bout of burnout & illness.It was slop, but slop that taught me things.During that time, I watched the American TV series Silicon Valley. It was intriguing. It managed to encapsulate the main topics of engineering discussions at the time, especially distriJul 7, 2026 2:09 AM
quickping.dev
Show HN: QuickPing – dead simple way for customers to get in touch with youhttps://www.quickping.dev/I got tired of creating a new email account, or setting up (and paying for) a Google Workspace every time I launched a side project.All I wanted was a link I could put on my site that lets someone send me a message and have a conversation.QuickPing gives you a shareable URL (like quickping.dev/to/yourproject).Someone visits it, types their name, email, and a message.You get notified and reply from a dashboard.They get an email with a link back to the thread.No chat widget, no embed code. Just a link you add to your site.Built with Next.js, Neon, and Mailgun.I'm using it for QuickPing's own contact page.https://quickping.devJul 7, 2026 1:39 AM
