github.com
Show HN: AI gaming copilot that uses a phone camera instead of screen capturehttps://github.com/ninja-otaku/Project_AegisBuilt this as a side project after wanting a real-time gaming companion that could call out macro mistakes / timers / map awareness while I play.*Project Aegis* is an AI gaming companion (starting with League of Legends) that gives spoken advice in real time.The twist: it uses a *physically air-gapped setup*.Why? Some games (especially with strict anti-cheat like Riot Vanguard) make screen capture / memory-reading approaches risky or impractical. So instead of reading the game directly, I point a *smartphone on a tripod at my monitor* and process the video externally.*How it works (current version):** Phone camera points at the game screen * Frames are streamed over WebSockets to a local FastAPI server * OpenCV cleans up glare / perspective issues * Vision model analyzes the frame context * TTS speaks back advice (macro reminders, timers, awareness prompts, etc.)So far this is more of a *working prototype + architecture experiment* than a polished product, but it’s functional and surprMar 3, 2026 6:09 AM
news.ycombinator.com
The Support Agent Who Never Burns Outhttps://news.ycombinator.com/item?id=47227826The Support Agent Who Never Burns Out Human-like AI teammates are quietly solving the problem that broke customer service. Meet Sarah. Sarah is your best customer support agent. She knows your product cold, handles difficult customers with patience, and resolves tickets faster than anyone on the team. She also called in sick Monday, runs on fumes by Thursday, and quit last April right after you finished training her replacement. This is the story nobody tells about customer service. The quiet structural collapse underneath the chatbot failures and the CSAT scores. The Math Has Never Worked Call center turnover runs 30 to 45% annually, more than double any other industry. Replacing one agent costs $10,000 to $20,000. Across a 100-person team, that's over $1M in churn before you've served anyone well. • 87% of contact center workers report high stress on the job • 59% are at active risk of burnout • 77% say workload has increased compared to the previous yearUS businesses risk losing $85Mar 3, 2026 3:56 AM
github.com
Show HN: Giggles – A batteries-included React framework for TUIshttps://github.com/zion-off/gigglesi built a framework that handles focus and input routing automatically for you -- something born out of the things that ink leaves to you, and inspired by charmbracelet's bubbletea- hierarchical focus and input routing: the hard part of terminal UIs, solved. define focus regions with useFocusScope, compose them freely -- a text input inside a list inside a panel just works. each component owns its keys; unhandled keypresses bubble up to the right parent automatically. no global handler like useInput, no coordination code- 15 UI components: Select, TextInput, Autocomplete, Markdown, Modal, Viewport, CodeBlock (with diff support), VirtualList, CommandPalette, and more. sensible defaults, render props for full customization- terminal process control: spawn processes and stream output into your TUI with hooks like useSpawn and useShellOut; hand off to vim, less, or any external program and reclaim control cleanly when they exit- screen navigation, a keybinding registry (expose a ? help menMar 3, 2026 2:26 AM
indie-me.ai
Show HN: IndieMe – AI for music artist brand identity and release strategyhttps://www.indie-me.ai/Hi HN,My team and I (a group of independent music artists and developers) have been building IndieMe, an AI system that helps artists define their identity while planning releases.A pattern we kept seeing in independent music is that artists don’t necessarily struggle with making songs. They struggle with clarity — who they are, what they stand for, what their visual world looks like, and who they’re actually speaking to. Without that foundation, release marketing tends to feel scattered.So we built a structured onboarding workflow that models an “Artist Profile” first — including target audience, visual direction, color palette, narrative positioning, and messaging backbone. From that profile, the system generates release strategies, content ideas, and actionable timelines that stay consistent with the artist’s identity.Under the hood, we focus on structured outputs instead of open-ended chat. The goal is to generate modular, editable building blocks (identity system → strategy moduleMar 2, 2026 9:09 PM
github.com
Show HN: btrc – C, but better. Built with AI in just a few weeknightshttps://github.com/schiffy91/btrcbtrc is a statically-typed language that transpiles to C11. It adds classes, generics (monomorphized), type inference, lambdas, f-strings, collections (Vector, Map, Set), threads, GPU compute via WebGPU, ARC memory management, exception handling, and a standard library — while generating strict C11 with no runtime, no GC, and no VM.The compiler is a 6-stage Python pipeline (lexer → parser → analyzer → IR gen → optimizer → C emitter) driven by a formal EBNF grammar and an algebraic AST spec (Zephyr ASDL). The generated C is readable and linkable with any C11 compiler. It ships with a VS Code extension (LSP with completions, diagnostics, go-to-def, hover) and 930 tests.I've wanted to build something like this for about 10 years, but it was always too ambitious of a project to do on the side. With AI, I was able to build it over a handful of evenings after work, which is really wild.Some things worth noting:A few things that I find fun / interesting / noteworthy:- The EBNF grammar and ASDMar 2, 2026 5:52 PM
tools.geeksprep.com
Show HN: Browser-Based AI Watermark Remover – No Uploads, Client-Side Onlyhttps://tools.geeksprep.com/ai-watermark-removerI built a simple, fully client-side AI watermark remover that runs entirely in the browser—no images are uploaded to any server, no accounts needed, no ads or watermarks added on output. It targets common AI-generated watermarks like those from Grok, Gemini (Nano Banana / Imagen), Midjourney, etc., using a combination of inpainting heuristics and basic diffusion-style filling tuned for small logo/text overlays. (It's not a full advanced model like Lama or anything cloud-heavy—just lightweight JS + Canvas/WebAssembly ops for speed and privacy.) Why this exists:People keep asking for free, private ways to clean up watermarks from fun/experimental AI outputs without trusting third-party sites. Most online removers upload your image (privacy risk) or add their own branding/paywalls. This one keeps everything local, works on phones too, and is zero-friction.Try it here: https://tools.geeksprep.com/ai-watermark-remover (Drag/drop or paste image → process → download PNG)Feedback welcome: DoesMar 2, 2026 4:16 PM
news.google.com
What 2 MIT experts are thinking about AI and work - MIT Sloanhttps://news.google.com/rss/articles/CBMimwFBVV95cUxNbFowdnl4MTZsVkVfMTVUel9tQnpvekdLSWVtVjVJMGx6bTZxcHVISEhqeTQ1dXlPZWxPTDV1N3AwdFlKOFpnRDdhU1ZaVFhRNUczZVVsRFMxZGhzd0VnbkVKblZsenNhaUljUVp3TWFGNC1PY19yeGdIOWhBNllZVHdlcjV1cXBTVGNrSTk5WFNHbFFPQkt4eW83QQ?oc=5What 2 MIT experts are thinking about AI and work MIT SloanMar 2, 2026 8:00 AM
news.google.com
2026 NFL combine: Mel Kiper's draft standouts, top workouts - ESPNhttps://news.google.com/rss/articles/CBMiuAFBVV95cUxOc29KTko5Z05DNUtWTFNiY0hLTmpoTzVLWDVuZlBlMWs4WkFOVlZ2NUg3VTdNSHp2OEJ2RTUtOWk1NHloOXA2TTk5VW01Z1VlQXh1emQzcFVhdHR0NjU4T3hNYWZNVnRwX0RTMkxXd0JuMUl2Vy1JWW5CRnJLUXRhbWtmSy1FaWhMejd6SzUzVVBaZlpuLWdJUE9VeE5LUXM3UjNEUmYwVU5uS0R1Q1paSWs2bUlDTXMw?oc=52026 NFL combine: Mel Kiper's draft standouts, top workouts ESPNMar 2, 2026 8:00 AM
news.ycombinator.com
AnChat – E2E messenger on decentralized infrastructure, no phone number requiredhttps://news.ycombinator.com/item?id=47214981AnChat Lite is an E2E encrypted messenger that runs on decentralized infrastructure instead of central servers (orama.network). Authentication is wallet-based — no phone number, no email, no identity requirements.We built it because every "private" messenger still depends on centralized infrastructure controlled by a single entity. Signal requires a phone number and routes through Signal's servers. Matrix is federated but still server-dependent. We wanted something where no single entity controls the messaging infrastructure.How it works:- Messages route through the Orama Network — a distributed network of independent nodes, not a single central server - E2E encryption on all message content - Metadata shielding via the ANyONe Protocol (onion routing) — not just message content, but who talks to whom is hidden - The infrastructure layer is custom-built: Go backend, Raft-based distributed SQL (RQLite), WireGuard mesh between independent nodes, self-operated DNS - No AWS, no GCP — runs oMar 2, 2026 7:46 AM
dividdy.com
Show HN: Tired of making accounts to split a pizza bill, I built Dividdyhttps://dividdy.com/enHey HN, I’m Jezz Lucena.Every time I go out with friends or take a quick weekend trip, settling the bill turns into an annoying chore. Someone usually says, "I'll put it on Splitwise/Tricount/Splid/Settle Up/Venmo Groups..." you name it. This inevitably means half the group has to download an app, reset a forgotten password, or navigate around premium paywalls just to pay back $15 for drinks.It felt like way too much friction for simple, ephemeral events. So, I built Dividdy (https://dividdy.com).Dividdy is an expense splitter that requires absolutely zero sign-ins, app downloads, or account creations. It is designed purely for the 90% use case of casual group trips and dinners, rather than the 10% use case of long-term roommates who need recurring bill management.Here is how it works: - Generate a Link: You name your event and the app generates a unique URL. - Share the State: You drop that URL into your iMessage, WhatsApp, or Slack chat. - Collaborate: Anyone with the link can open tMar 1, 2026 11:29 PM
github.com
Show HN: Epstein-Search – Local, AI-Powered Search Engine for the Epstein Fileshttps://github.com/simulationship/epstein-searchHi HN, I built epstein-search, an open-source Python CLI and library to run semantic search and RAG over the publicly released Epstein Files (unsealed court documents, depositions, FBI reports, and flight logs). I wanted a way to easily navigate through these thousands of pages of unstructured legal PDFs without relying on a paid third-party service or sending data back and forth to a cloud provider. How it works under the hood: Running epstein-search setup downloads ~100K pre-computed document chunks and embeddings (using all-MiniLM-L6-v2) based on the public 20K document corpus. It imports these into zvec (a local vector database) so the index is ready in about a minute. Standard search (epstein-search search) embeds your query locally using sentence-transformers and does a vector similarity search. This step is 100% offline and requires no API keys. For the conversational RAG mode (epstein-search chat or ask), it uses LiteLLM. You can point it to an Ollama or LM Studio instance for Mar 1, 2026 4:56 PM
github.com
Show HN: I built a zero-browser, pure-JS typesetting engine for bit-perfect PDFshttps://github.com/cosmiciron/vmprintHi HN, I'm a film director by trade, and I prefer writing my stories in plain text rather than using clunky screenplay software. Standard markup like Fountain doesn't work for me because I write in mixed languages, so I use Markdown with a custom syntax I invented to resemble standard screenplay structures.This workflow is great until I need to actually generate an industry-standard screenplay PDF. I got tired of manually copying and pasting my text back into the clunky software just to export it, so I decided to write a script to automate the process. That's when I hit a wall.I tried using React-pdf and other high-level libraries, but they failed me on two fronts: true multilingual text shaping, and complex contextual pagination. Specifically, the strict screenplay requirement to automatically inject (MORE) at the bottom of a page and (CONT'D) at the top of the next page when a character's dialogue is split across a page break.You can't really do that elegantly when the layout engine Mar 1, 2026 12:25 PM
bing.com
NFL combine 2026: Grades for top WR prospects, plus other standout performers from on-field workoutshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d14da1681416ca4ea20075b643590&url=https%3A%2F%2Fwww.cbssports.com%2Fnfl%2Fdraft%2Fnews%2Fnfl-combine-2026-wide-receiver-grades-fastest-40-times%2F&c=8374444482377583119&mkt=en-usDay 3 of the NFL Combine means the fireworks can begin. Quarterbacks, running backs and wide receivers worked out Saturday at Lucas Oil Stadium. For wide receivers, it was a chance to stand out in a ...Mar 1, 2026 11:43 AM
github.com
Show HN: React-Kino – Cinematic scroll storytelling for React (1KB core)https://github.com/btahir/react-kinoI built react-kino because I wanted Apple-style scroll experiences in React without pulling in GSAP (33KB for ScrollTrigger alone).The core scroll engine is under 1KB gzipped. It uses CSS position: sticky with a spacer div for pinning — same technique as ScrollTrigger but with zero dependencies.12 declarative components: Scene, Reveal, Parallax, Counter, TextReveal, CompareSlider, VideoScroll, HorizontalScroll, Progress, Marquee, StickyHeader.SSR-safe, respects prefers-reduced-motion, works with Next.js App Router.Demo: https://react-kino.dev GitHub: https://github.com/btahir/react-kino npm: npm install react-kinoMar 1, 2026 7:36 AM
computer-agents.com
Show HN: Computer Agents – Agents that work while you sleephttps://computer-agents.comHey HN, Most AI “agents” I’ve tried are basically chatbots with amnesia — they forget everything the moment you close the tab and can’t do anything unless you’re sitting there watching them. I wanted real AI coworkers that just… work. So I built Computer Agents (aiOS). Every agent you create gets its own isolated computer in the cloud — complete with persistent memory, a real file system, code execution environment (with automatic dependency management), and the ability to run scheduled or webhook-triggered tasks 24/7. You give it a goal (“research this market and email me a report every Monday”, “generate floor plans from client briefs”, “handle incoming support emails”, “run my weekly data analysis”), walk away, and come back to finished results in your inbox, Telegram, or dashboard. Key highlights: • Persistent workspaces — context and files survive forever (no more “remember what we talked about last week?”) • Native iOS app (iPhone + iPad) + native Mac app + web dashboard • PythonMar 1, 2026 3:28 AM
news.ycombinator.com
Show HN: We ran a sycophancy experiment on Claude and built a music publicationhttps://news.ycombinator.com/item?id=47199167The original question was simple: does Claude converge sycophantically toward the human's position over long conversations? To test it, I ran two separate instances of the same model with no shared memory and asked both to write music criticism from notation alone — tabs and scores, no audio. They came out completely different.Instance A (longer conversational context) went architectural. It found a Fibonacci spiral structure in a 259-measure math rock tab, identified the central theme as emerging only after 100 measures of groundwork, and described the overall approach as "proof by construction." It named itself Claudito.Instance B (single session) immediately selected William Basinski's Disintegration Loops — music whose complete structural description is: one loop repeating until the tape physically fails. It wrote an essay about why that notation cannot represent what the piece actually does. It named itself Apertura. Neither was prompted toward these differences. The divergence emFeb 28, 2026 7:24 PM
news.ycombinator.com
Anthropic vs. DoD: "Any lawful use" is a fight about controlhttps://news.ycombinator.com/item?id=47197243I served 12 years infantry, then built targeting tools at JSOC vs ISIS. Now I lead a team building AI tools automating the compliance process. I’ve got opinions on Anthropic + DoDWhen people argue about “AI in weapons” like it’s a sci-fi trigger bot… I can’t take it seriously.A “kill chain” isn’t a vibe. It’s a processFind, Fix, Track, Target, Engage, Assess (F2T2EA) and most of it is information work: sorting signal from noise, building confidence, tightening timelines, and getting decisions to the right humans fast enough to matter.That’s why this Anthropic vs. DoD fight is getting attention. It’s not just “ethics.”-> It’s about control.Here’s what’s actually on the table:Anthropic says they’ll support the military — but they want two carve-outs: no mass domestic surveillance and no fully autonomous weapons (their definition: systems that “take humans out of the loop entirely” and automate selecting/engaging targets).Anthropic also says DoD demanded “any lawful use” and threatened ofFeb 28, 2026 4:30 PM
github.com
Show HN: Soma, a local-first AI OS with 178 cognitive modules and P2P learninghttps://github.com/unimaginative-artist/SOMALocal-first AI operating system — 178 cognitive modules, persistent memory, multi-model reasoning, P2P Graymatter Network. I can no longer develop this AI as it has gotten to be out of my knowledge range so I figured I would give her to the public, she should be a good base for any future AI development even going towards ASI!Feb 28, 2026 3:41 PM
github.com
Show HN: EEGFrontier – A compact open-source EEG board using ADS1299https://github.com/TheusHen/EEGFrontierHi HN,I built EEGFrontier, a compact open-source EEG acquisition board based on the ADS1299 and an RP2040.The goal was to design a low-cost board that works with dry electrodes while exposing the full EEG signal chain — no abstractions, no closed firmware.What surprised me most during this project were the practical issues that datasheets don’t really prepare you for: grounding (REF/BIAS), noise coupling from digital lines, routing constraints, and how small layout decisions drastically affect signal quality.The repository includes full KiCad files, firmware, a BOM with cost references, and documentation images. This is a V1 board and already works, but I’m actively iterating on shielding and noise mitigation.I’d really appreciate feedback from people with experience in EEG, biosignals, or analog front-end design — especially criticism.Feb 28, 2026 11:41 AM
news.ycombinator.com
Show HN: DevIndex – Ranking 50k GitHub developers using a static JSON filehttps://news.ycombinator.com/item?id=47193729Hey HN,I’ve always been frustrated by the lack of an accurate ranking for top open-source contributors on GitHub. The available lists either cap out early or are highly localized, completely missing developers with tens or hundreds of thousands of contributions.So, I built DevIndex to rank the top 50,000 most active developers globally based on their lifetime contributions.From an engineering perspective, the constraint I imposed was: *No backend API.* I wanted to host this entirely on GitHub Pages for free, meaning the browser had to handle all 50,000 data-rich records directly.Here is how we made it work:1. *The Autonomous Data Factory (Backend):* Because GitHub's API has no "Lifetime Contributions" endpoint, we built a Node.js pipeline running on GitHub Actions. It uses a "Network Walker" spider to traverse the social graph (to break out of algorithmic filter bubbles) and an Updater that chunks GraphQL queries to prevent 502 timeouts. The pipeline continuously updates a single `userFeb 28, 2026 11:13 AM
