#Accessibility
92
2026-10-16
midagedev/mwoyeo
A
Live, in-place screen translation for macOS — a lens that rewrites the text under it in your language, on-device.
2026-09-15
Show HN: Kinesis – Control your Mac with the Meta Neural Band
B
a couple hours ago i had astra take on a 10 month old repo of mine https://github.com/callbacked/neural-band-poc/ that involved finding a way to use the meta neural band independently from the glasses to read the sEMG data off of it. i really think it is a cool piece of technology that largely gets overlooked by the glasses, and always thought it was a shame it couldn't be used outside of its main application. after making quick work of that, i wanted to use it to control my mac using gesture controls and that's how kinesis was born. it has been very cool being able to swipe from desktops using my fingers, swiping up to open up mission control or controlling a virtual knob to adjust my volume. i definitely havent scratched the surface with the neural band but it has been a really fun endeavor thus far! i really hope others can find creative uses for their neural bands too :) note: i really hope this works on other bands because the sample size has just been me so far.
2026-10-13
ironicsans/livelight.koplugin
A
KOReader plugin: adjust brightness and warmth in realtime by dragging your finger on the screen edges, just like in Kobo’s own software.
2026-10-16
Calvino-Y/mcd-mcvoice
A
McVoice · Visually impaired users complete the entire McDonald's ordering flow by voice (choose store → order → price calculation → checkout) · Entry for the McDonald's Programmer's Day creative development contest
2026-09-27
tgeczy/ssi263-speech
A
The SSI-263 speech chip, emulated, with the original firmware of the Speak-Out, Braille Lite, Accent-mini and Accent SA driving it. NVDA add-ons.
2026-09-10
eperez28/sonar.cool
A
Control your Mac with hand gestures using its speakers and microphone. Experimental, camera-free scrolling, swiping, and zooming.
2026-09-04
masonasons/vocalwriter
A
VocalWriter 2.0's own PowerPC synthesis code, running again -- a user-mode PPC interpreter, its file formats decoded, and an accessible multi-track singing editor built on top.
2026-10-13
fauzulkc/circle-lens
B
A free screen magnifier that opens where you're looking: draw a circle twice with the mouse. For Windows, your browser, and your website (npm circle-lens).
2026-11-08
oscarcreatess/airpointer
B
Airpointer - Use your Airpods as an air-mouse for your Macbook! More OS's/Devices coming in the future. (This was made in collaboration with my friend Andy, we have seperate Repos due to having assignments but will ultimately continue progress through this one when they’re over)
2026-11-03
kevintngo/looseleaf
B
shadcn/ui, drawn by hand: 123 accessible React components that look drawn on paper, with a shadcn registry.
2026-09-03
MrZoic/zenspark-browser
B
An open-source controller-first web browser designed for TVs and 10-foot interfaces.
2026-10-22
TurnOver-For-Mac/turnover
B
A screen reader for the Mac that works alongside VoiceOver. Free and open source.
2026-08-28
omer-faruq/readingstyle.koplugin
B
a KOReader plugin that puts common book-layout settings behind simple controls. You can adjust how a book looks without digging through Style Tweaks or writing CSS.
2026-11-09
Coolerwave/AimMac
B
Point your iPhone at your Mac and the cursor follows. Tap to click, hold to drag. Bluetooth only, open source.
2026-10-03
masonasons/SingingVoiceStudio
B
VocalWriter Studio rebuilt in C++ and wxWidgets, singing with VocalWriter, DECtalk, the SSI-263 and Microsoft Sam, Mike and Mary. Screen-reader first.
2026-09-17
jaskirat1616/AirPoise
B
Mac menu-bar app: AirPods posture coaching and head-gesture shortcuts. On-device, no camera, no cloud.
2026-10-08
salvcy/meowse
B
Smooth scrolling for mouse wheels, Keep Awake and Wiggle Cursor in a native macOS menu bar app with zero idle cost.
2026-09-24
Nisaka520/JevBystander
B
Android accessibility-based WeChat interpretation: screen reading only, only pops 3 Toasts (intent / emotion / urgency / suggestion), generates no reply text and sends nothing · zero third-party dependencies, APK 861 KB.
2026-09-07
trypsynth/evvdroid
B
Eloquence text-to-speech engine for Android and Wear OS, built on openevv
2026-10-11
rbartoli/obsidian-tela-theme
B
An easy-to-read, easy-to-scan Obsidian theme, inspired by the Tela app. Every text colour passes WCAG AA in dark and light.
2026-09-15
MuhammadHajjar/PapaSangre-Windows
B
A faithful Windows port of Papa Sangre, the audio-only horror game by Somethin' Else. Keyboard, controller, screen reader, and the original's own HRTF.
2026-10-12
KorenKrita/simul-subtitle
B
Android real-time live subtitle translation: recognizes Japanese/English on the phone, translates into 22 languages with Index-Translate, floats over any app · Live on-device subtitles for Japanese/English
2026-09-26
Fwooffy/Qpro-Enhanced-FT-Wireless
C
Enables tongue tracking and eye convergence on a rooted Quest Pro over wifi
2026-08-25
Leon-kennedy-god/cat-apk
C
MeowMeowAssistant: a generalized feature-expanded version of QQMiaoAssistant. Based on Android accessibility services, it expands QQ-specific text rewriting (custom replacement rules / sentence-break appending / random kaomoji) to work in the input boxes of any chat app (QQ/WeChat/Telegram/WhatsApp/DingTalk/Discord/Feishu/Slack, etc.). Includes target app whitelist/blacklist, keyboard and password field protection, send fallback; pure native API with zero dependencies; AGPL-3.0; derivative secondary development of upstream QiCaiJie114514/QQMiaoAssistant. Download: https://github.com/Leon-kennedy-god/cat-apk/releases/latest
2026-10-25
CH-LaTiao/lumina-guide
C
LUMINA Guide / Lingxi: Jetson + Orbbec RGB-D wearable navigation assistant prototype
2026-09-17
heruoxin/FingerChord.app
C
Native trackpad gestures for macOS 27: ⌘ click, close windows, and quit apps. Haptic feedback, no Dock or menu bar icon. Built one-shot with GPT 6 Astra.
2026-09-16
CtrlcvMaster/HearMe
C
This is the first project I have released. It is mainly designed to assist hearing-impaired individuals and includes features such as speech-to-text, voiceprint recognition, web screen casting, cross-app screen reading, cross-app captions, and more. /This is the first project I have released. It is mainly designed to assist hearing-impaired individuals and includes features such as speech-to-text, voiceprint recognition, web screen casting, cross-app screen reading, cross-app captions, and more.
2026-09-12
MontyTheSoftwareEngineer/fievel
C
A linux application that aims to replace mouse movements with keyboard!
2026-08-27
zisenuomituan/qq-miao-miao-helper
C
QQ Meow Assistant - a QQ cat-tone assistant in the style of Blue Whale Charity LJGY (Java + accessibility service)
2026-10-05
AsheeHuang/Jevboard
C
A proof of concept for improving Bopomofo IME character selection with Jev | A proof of concept for improving Bopomofo IME character selection with Jev.
2026-10-11
9mtm/Web-Respect
D
Accessible reading preferences. Clear consent controls. Your brand, your services and your backend.
2026-10-30
Followertustuff/anomalith-steam-deck-small-text-accessibility
D
ANOMALITH Steam Deck small text accessibility guide: tiny UI, handheld readability, resolution scaling and on-screen text comfort.
2026-11-08
jsogn/Glint
unrated
A macOS English learning tool for native Chinese speakers, with switchable target languages: it reads the currently highlighted candidate from a Chinese pinyin input method and shows the corresponding translation next to the candidate bar.
2026-11-07
starman-tech/mousepods
unrated
Your AirPods are a mouse: AirPods 3 head tracking on Linux, and the first public documentation of Apple RemoteHID (HID over AACP)
2026-11-03
Sorasukiawa/VoxPalm
unrated
VoxPalm: hold to talk, release to type. Turn remotes and wireless mics into a voice button for your Mac · Hold to talk, release to type: turn remotes and wireless mics into a voice button for your Mac
2026-11-02
nilbuild/tinyhand
unrated
A tiny hand on a stick that points at things on your Mac screen.
2026-10-31
txwang-tju/RoboFlex
unrated
Zhiyi Suixing targets people with limited mobility and their caregiving families, using multimodal intent understanding to drive continuous mobile manipulation. The system combines GPT-6's understanding of images and user intent to organize fetch requests into task sequences with completion conditions, then coordinates the mobile base and robotic arm through motion policies, reliability-aware spatiotemporal whole-body planning, and phase-dependent switching control to complete approach, grasping, carrying, placement, and result verification.
2026-10-30
sanjayadanushka712/Dracula-Deep
unrated
A low-glare Dracula-inspired VS Code theme with measured WCAG AA contrast, muted UI accents, and six-step bracket-depth highlighting.
2026-10-27
Tongyu3/Tdsh-DSH-Mobile-Android-NO-ROOT
unrated
Ported dsh to mobile, no Root, one-tap APK install, can read and edit files, and can do more with accessibility permissions; welcome to try.
2026-10-26
littlebordercollie/mcd-together-order
unrated
McMcOrder Together: students with intellectual disabilities express choices with pictures, and parents take over to verify. A McDonald's MCP ordering communication prototype.
2026-10-22
Show HN: Euspell – Spelling reform: an enginnering approach
unrated
Hi HN. Euspell is a conservastive respelling of English and all the software needed to implement it. The link above converts the text you paste, in your browser. Other ways to try it out are the browser extensions and EPUB/PDF readers. Previous spelling reforms have failed for two reasons: they asked people to apply rules by hand or remember a large set of new spellings, and they couldn't handle homographs: "read" is reed or red, "records" is a noun or a verb, "wound" is an injury or a past tense - writing in pure phonetics will actually create hundreds of homographs. Euspell approaches spelling reform differently, with the goal of aiding reading and comprehension. - A lexicon with 205505 entries, each with CLAWS7 part-of-speech tags. Of these, 164067 (80%) are left unchanged. No diacritics are used. Proper nouns are untouched. American spelling is the base, in the line of Webster's reforms. - 5920 entries are ambiguous and need context. The noun/verb -s split (records/recordz) is a linear SVM: 93.2% on held-out text. The hand-written rule it replaced scored 75.9%. The full evaluation is at https://github.com/ossiak/euspell/blob/main/docs/paper-evalu... - Semantic splits (e.g. bow, tear, lead) are hand-written rules and less accurate: "read" gets about four in five right on its test set. - Runs locally in a browser extension (Chrome/Firefox/Safari, including PDFs), MS Word, LibreOffice, Google Docs, and a standalone EPUB/PDF reader for Windows, MacOS, Android and iOS. - Code is GPL-3.0, lexicon is CC BY-SA 4.0: https://github.com/ossiak/euspell. White paper: https://euspell.org/paper The changes can be toggled on and off: Euspell changes what you read, not the source text. AI tools (Claude) helped with the software, the site and the videos; the reform and the lexicon are mine. There is also a 14-part video series: https://www.youtube.com/playlist?list=PLfCd5hTV7IWg Most useful feedback: sentences where it picks the wrong spelling.
2026-10-21
ctoldigital/axuse
unrated
Accessibility-first browser & computer use for AI agents — one MCP server for every harness (Codex, Claude Code, OpenCode, Antigravity). Instruments the DOM/accessibility tree via CDP instead of screenshot loops: diffed snapshots, stable element refs, trusted input, typed errors. Zero dependencies
2026-10-19
MuuCake/LiveCaptions-Translator-Buddy
unrated
A lightweight Windows tool that saves Windows Live Captions to TXT files.
2026-10-19
Show HN: Connecting Captions Local Private AI Interpreter
unrated
Hi HN, I built Connecting Captions, a live captioning and translation overlay for macOS that runs entirely on-device. Nothing goes over the network: no API calls, no audio leaving your machine, and it keeps working offline. I wanted live translation I could use in meetings and conversations without worrying about connectivity, latency spikes, or sending sensitive audio to a third party. The technically interesting part is a low-latency, self-correcting pipeline for speech-to-text and translation. It has two modes: Sentence mode: buffers until a sentence boundary, then translates with full context. It’s more accurate, especially between languages with different word order. Streaming mode: translates word by word as speech arrives, trading grammatical accuracy for minimal delay. Current state: Platform: macOS Models: Whisper Latency: ~200 ms Languages: 25 Code: https://github.com/chrisswimlee/connectingCaptions I’d love feedback, especially on the self-correction approach and which use cases matter most to people.
2026-10-16
amywork777/lipflow
unrated
Wispr Flow for your lips: hold a key, silently mouth words, and they're typed at your cursor. Runs locally on your Mac.
2026-10-16
webkubor/dsh-bloom-theme
unrated
DeepSeek Harness (DSH) theme plugin: Bloom Morandi color palette with 10 Chinese-style names (Dai Blue/Cinnabar/Taoyao/Sky Blue/Bamboo Green/Ochre/Lapis/Amber/Sunset/Lotus), OKLCH color tuning, light and dark themes, one-click toggle in the top bar, all 20 color schemes tested to meet WCAG AA.
2026-10-16
Show HN: Content-adaptive display brightness for macOS with DDC/CI support
unrated
I was always annoyed that I had to adjust brightness when switching from an IDE in dark mode to a bright web page. I was aware of Lumen https://github.com/anishathalye/lumen but didn't use it since it does not support external monitors. Therefore, I built Lumos, which is heavily inspired by Lumen but adds support for external monitors. The DDC/CI part of the code is vendored from https://github.com/MonitorControl/MonitorControl. It really improved my experience and I almost never have to manually adjust brightness anymore. And it is open source so I wanted to share it here.
2026-10-14
Show HN: Keep your eyes in one place while typing
unrated
I wanted a way of typing that's tuned towards stream of consciousness/get down a bunch of words quickly. And I'm too lazy to move my eyes, so I wanted something where I could relax my eyes/brain and just get words out.
2026-10-13
Show HN: Turn spoken thoughts into system design diagrams
unrated
I recently had an issue with my right hand, and couldn't use it very effectively. So I was trying to figure out how I could still get work done without typing everything with my right hand. I looked around for some tools, but then thought, why not try building something myself? The idea was to make an accessibility and productivity tool that lets me get thoughts out of my head and turn them into something useful with less manual effort. That's how I started building Lucid. You can turn rough input into structured notes, diagrams, and tables, and edit everything afterwards. I'm also using a local AI model through LM Studio. One use case I had in mind was system design. Imagine thinking through a system, talking about its components, and getting a diagram out of it instead of manually creating everything. I'm currently using a separate dictation app for voice input, so there's still a lot I can improve here. It started as a way to help myself, but I thought it was a cool thing to build and might be useful to others as well. So sharing it here! Demo: https://youtu.be/AwlJ8LJbfw4 GitHub: https://github.com/triggeredcode/lucid Website: https://triggeredcode.github.io/lucid/
2026-10-12
Threadduregister/risk-of-rain-2-steam-deck-controller-helper
unrated
Windows utility repository focused on controller layouts, input profiles, handheld-friendly setup organization, and Steam Deck style control workflows for Risk of Rain 2.
2026-10-10
Show HN: Compose Unstyled – Unstyled Components for Jetpack Compose and CMP
unrated
Compose Unstyled is a collection of fully accessible, unstyled components that you can use to build your own components using Jetpack Compose and Kotlin. I started the library because I found Jetpack Compose too coupled to Material. I wanted to build apps with my own look and feel. 2 years and 1221 commits later, the project is used by companies such as Perplexity, Warner Bros and Expo. All components are unopinionated and can be styled using just plain Modifiers. All the UX is handled for you, so that you can focus on your product instead of trying to figure out how to build Bottom Sheets and dialogs.
2026-10-10
Show HN: Coolphabets – Teaching kids to read and write in their mother tongue
unrated
COOL + ALPHABETS = COOLPHABETS COOLPHABETS teaches you to read and write in your mother tongue - for kids who are just starting, and adults who never did. Millions of families live outside the country they were born in. While parents can read and write in their native language, their kids - the second generation - can barely do so. Kids often speak their mother tongue fluently because it is the language they use at home. But reading and writing is rarely a "felt need" for them. And kids are unlikely to feel that need unless parents nudge them - preferably at an early age. Many parents genuinely want their kids to be able to read and write in their mother tongue. This usually means a textbook or a weekend language class. Both can feel like a chore. Most language apps teach you to 'speak' a language. COOLPHABETS teaches you to 'read' and 'write'. Reading and writing are a genuinely difficult problem to solve - especially on an app. Getting a child to write letters correctly is the harder part. That's where we built CoolphaSense - a collection of tiny AI models that run entirely on the device and provide instant feedback on handwriting. COOLPHABETS is designed for kids. No ads. No tracking. COPPA compliant. The apps are designed to work fully offline. No cloud roundtrips to a 'Mothership AI model'. COOLPHABETS is currently available in Indian languages. - Telugu - Kannada - Hindi - Tamil - Marathi Most other Indian languages will be onboarded by December 2026. Other world languages (Asian, Middle Eastern, European) are early next year. The bigger motivation is cultural. A language can survive for several generations as a spoken language, but if its script is lost, something important is lost with it. If one generation stops reading and writing in its native script, reconnecting with that part of the culture becomes much harder. If you are a parent who feels this way, COOLPHABETS is for you and your kids. https://coolphabets.com/ Android: https://play.google.com/store/apps/details?id=com.coolphabet... iPhone: https://apps.apple.com/us/app/coolphabets/id6762379998 We would love to hear from parents settled outside their native countries, parents raising kids in multilingual households, and from people working on handwriting recognition, on-device AI/ML, and language learning.
2026-10-09
Show HN: Chromatics, a classics reader that colors every character's dialogue
unrated
I have been working on a classics reading app for iPhone & iPad called Chromatics. The app colors character dialogue and it helps you stay immersed in the story. If you are interested, please try it!
2026-10-07
Show HN: Free IAAP CPACC Practice Tests and Mock Tests
unrated
Renewed my IAAP CPACC exam last week, added some practice tests and mock tests which i found very useful for preparation.
2026-10-07
Show HN: Aether: Check and fix web accessibility issues from your coding agent
unrated
Hi, HackerNews! I'm Samy, co-founder of Allchemy Labs. We built Aether, an MCP server that enables engineers to check for, understand, and fix web accessibility issues all from their IDE. Your preferred coding agent can leverage Aether to open a webpage, scan it using axe-core and return a short, prioritized list of violations along with code fixes or guidance. Every suggested fix is re-tested in a real browser before you see it, and once you apply it, your agent can re-scan the page to verify it worked. You never need to open a browser, use multiple tools, or be an expert in WCAG criteria. Aether uses our own custom ontology architecture to provide grounded insights to any WCAG violations the scanner finds. Every WCAG technique the engine cites must pass our quality gate. Specifically, it must satisfy the violated success criterion, apply to that kind of element, and remediate that axe rule. If nothing passes, our engine will abstain rather than guess. We compared Aether against standalone coding agent on its own (Opus 5, 30 anonymized live sites, 111 targets). While the results were mixed we have published the results especially calling out specific wins and improvement opportunities for our insight engine. Read the study here: https://allchemylabs.substack.com/p/we-tested-our-own-access... Try Aether today, no signup needed. npx -y @allchemylabs/aether-wcag-scanner (any MCP client: Claude Code, Cursor, Codex…) Claude Code plugin: /plugin marketplace add https://github.com/allchemylabs/claude-plugins.git then /plugin install aether-wcag-scanner@allchemylabs Without a key you get the browser scan, local template fixes and verification. A free beta key adds the cloud engine: https://beta.allchemylabs.ai/?src=hn Feedback from people who have used accessibility scanners and/or suggestion engines would be highly valuable to us, as we aim to build a tool that solves real problems and makes people's lives easier. Happy to answer any questions and hope to hear from you. Note: Right now Aether only checks WCAG 2.1 AA. Sites behind bot protection (e.g. Cloudflare challenges) return a "blocked" result instead of a fake scan, so point it at localhost or staging.
2026-10-06
Show HN: Reader Mode for Chrome
unrated
A reader mode Chrome extension I built to solve a problem for myself: a reader mode that doesn't look ugly and removes all the clutter from a web page. This was carefully designed by me to create a clean reading experience for wherever on the internet you may be. It has light, dark and sepia modes and a serif font mode as well.
2026-10-04
Show HN: Focus Tool for ADHD
unrated
We live in a noisy digital world. For anyone with adhd, doing one thing at a time is the key. NOT using fancy todo managers. Win one intention at a time instead of planning, prioritizing, and juggling 100s of things. This tool is a free, open-source application to help you stay on track. You set an intention before you work, and a big, fat overlay stays in your periphery to keep you on track. Written purely in C, using raylib.
2026-10-03
Show HN: I'm color blind, so I built a way to show people how I see
unrated
I'm color blind and for as long as I can remember, the first question people always ask me after finding out is: "what color is this?" So I thought it could be cool to build a color blind simulator where I can point my phone's camera at anything and show people live what it looks like to me. Once I built that, I thought it would be interesting to also see how other people with different vision issues see too. So there are also 20 other conditions you can experience, along with a short color blind test if you want to check your own eyes & share a link to how you see. It all runs in the browser and your camera feed never leaves your device. Thanks for checking it out
2026-10-03
Show HN: Cinematic Grade, a real-time GLSL color grade for the Cinnamon desktop
unrated
Hey guys! I made a screen filter for the computer with the Iron aesthetic, because I really love what it conveys. I was already using my screen in black and white day to day, and I tweaked it a bit so it sits closer to the Iron look without draining the battery in the process github.com/mateolafalce/iron-within I sent this applet to Linux Mint's official Cinnamon Spices repo, so maybe someday it can be downloaded straight from that store: github.com/linuxmint/cinnamon-spices-applets/pull/9088 Just that, take care, and I hope you lock in this weekend that's about to start!!
2026-10-01
Show HN: Focusgrid– keyboard-controlled webapps like tmux
unrated
Hi HN, Whenever I use web software I usually wish they put more thought into keyboard user's experience. So i made Focusgrid! It's a library (vanilla web, with optional react bindings) that lets you build web software with resizable, splittable panes and reprogrammable shortcuts, just like tmux. Would love to see what you build with it. I think email clients, browsers, and various creative tools could all benefit from pane layouts like this. NPM: https://www.npmjs.com/package/@andrewcyuan/focusgrid?activeT...
2026-10-01
Show HN: Quiet – exploring when an AI assistant should intervene
unrated
I’m Ruggiero, a CS student working on a research project about humanComputer interaction and AI. I built QUIET because I’ve been thinking about a problem with current AI interfaces: they usually either wait for an explicit prompt, or try to take over a task. I wanted to explore a different relationship between humans and AI: an assistant that can understand when to stay out of the way, when to point something out, when to teach, and when to act. I’ve built a small interactive demo of this idea. It’s obviously still very early, and I want to understand whether the interaction itself makes sense before trying to build the actual AI system behind it. The prototype is intentionally not AI-powered yet. The four examples are scripted so I can test the interaction itself before spending time building the underlying AI system. The idea is that the assistant can choose different levels/forms of intervention: * stay silent * point at something * explain / teach * do the task The important question for me isn’t whether an AI can perform these actions. Current systems can already do many of them. I’m trying to understand whether an assistant that decides when and how much to intervene is actually useful. I’d particularly like feedback on: * Did the interventions feel helpful or annoying? * Would you want an assistant to behave this way? * When would you prefer it to teach you rather than do something for you? * Does this interaction model make sense even without the AI being there yet? I started working on this because I feel there is an increasing gap between what computers/AI are capable of and what users actually understand and can make use of. At the same time, AI systems are becoming increasingly capable of explaining and performing tasks for us. I’m interested in whether the interface itself should evolve to bridge that gap. Demo: https://quiet-hci.pages.dev I’d really appreciate any criticism, especially if you think the interaction model doesn’t make sense. The demo suit best the desktop screens on phones Im working on a totally different but also similar idea of interaction, and since this is a simulation of the desktop tool it should work best on it , Thank You <3
2026-09-29
the-Ashkanian/rtl-chat-zcode
unrated
RTL (right-to-left) chat patch for ZCode Desktop — Persian/Arabic message support
2026-09-26
Show HN: PDF Remediation that you can validate before and after with PAC
unrated
You can verify the improved score of your PDF Accessibility in PAC directly.
2026-09-26
Show HN: MyA11yReport MCP – Build and test accessible websites with AI
unrated
Give your AI development tools (like Claude Desktop or Cursor) the ability to run WCAG accessibility audits locally and compliant code.
2026-09-19
Show HN: Big Calendar – an iOS calendar with big fonts and readable events
unrated
I've been using google calendar for over 10 years, but since turning 40 I've found the fonts too small. So I built an opinionated ios calendar app, "big calendar", that suits my needs. Big fonts, readable (multi-line) events, wide column for today, etc. Basically it's for people who don't use timed events much. It shows whatever is in your apple calendar, so google calendars synced to your iphone show up too. Now I use it every day, and it has pretty much replaced google calendar for me. - free to use, with a one-off purchase to unlock more - not open source - built with claude (max plan 5x) in vscode/xcode If you find your calendar too small to read, maybe give it a try. Any feedback is appreciated. https://github.com/minho42/bigcalendar-public
2026-09-15
Show HN: Shortcut Express – My attempt to get the world using keyboard shortcuts
unrated
I often see people reach for the mouse to select text or close a tab, even when they're already typing. Most know how to copy and paste with the keyboard, but use the mouse for almost everything else. I use the mouse plenty myself, but a few shortcuts have become habits. You don't need to learn that many to find them useful. Things like moving between words or selecting a whole line come up often and are mostly universal across apps and operating systems. I think most people just get used to doing things with the mouse. Learning shortcuts takes a bit of effort, and looking through a cheatsheet doesn't help much if you don't use what you've learned right away. I wanted to make something where you could practice them as you go. That's why I built Shortcut Express, a small desktop app that teaches shortcuts for everyday tasks. You practice them in a simulated text editor, browser and other familiar parts of an app. Completely free and open source. Available for macOS, Windows and Linux. https://github.com/chimit/shortcut-express/releases/latest
2026-09-12
Show HN: Claude Read Aloud – Hear Claude's Replies Instead of Reading
unrated
When I'm working all day sometimes my eyes get tired and I don't read Claude's replies fully and understand them. So I made Claude Read Aloud to read Claude's replies for me. It's very helpful for when I'm running on low energy and I think it can also be helpful for people who are visually impaired. It's kind of soothing to hear sometimes. My Claude Code plugin reads claude code's replies out loud in whatever voice you choose. It comes with a VS code extension to make it super easy to use. You just click the speaker button and you can start hearing the replies or you can highlight the text you want to hear and right click to listen to it. It comes with many different API configurations to choose the best voice you can use speechify, eleven labs, open AI, and other freeware.
2026-09-10
Show HN: Ambient Context v1.0.0 (Missing context for AI assistants)
unrated
The other week I posted a concept to use the macOS Accessibility API to capture the text on your screen into a markdown file. It seemed to be interesting with 150+ github stars. I've done a bunch of updates and packaged them into a signed macOS app. One of the biggest changes was moving away from 'one context file per day' to three markdown files for apps, website, and messages. I then run Andrej Karpathy's LLM Wiki process to turn into a simple knowledge base for the day. This is then used by a smarter model to synthesise into a daily overview. Let me know what you think Original: https://news.ycombinator.com/item?id=49429095
2026-09-04
Show HN: Competitive Language Learning (E-Sport)
unrated
For the past few years i've been on Duolingo & was able to learn Hindi & Spanish (even helped me get state seal of biliteracy) One of the biggest problems that I see in my generation (Gen Z) is loneliness. I love Duolingo's community, but sometimes (well actually oftentimes), I felt myself struggling to come back. Online language learning is a skill where dominantly, the entire motivation is connection and the entire daily practice is solitude. Nobody learns Spanish to know Spanish. They learn it to talk to their partner's family, to not be the silent one at the table, to move somewhere and have a life there. Then they spend 90 days alone with an owl. I was thinking of a way to connect people around the globe-through the shared passion of learning languages, & creating a competitive social space where people could compete in rapid-fire matches, instantly get feedback, & learn through teaching their own avatar (vs a more passive "lesson-style" learning). They learn on the spot, under pressure, & are put in different situations where they have to maneuver through different absurd scenarios & speak or type the language in a satisfactory way). The core flow is: Learn (2–5 min interactive segment) → Teach (explain it to your avatar) → Avatar attempts (your score). Then you take that into ranked 1v1 matches against someone near your level, chess.com style: a blind judge grades both players on speaking and writing, ratings move, there's a global ladder with titles and perks. The point is to bridge this through competition & internal community-building. Beyond the sport, users can interact with each other & create micro-societies based on their shared interests of the language. People learning Spanish who have gotten an interest in creating foods-stuff like Carne Asada or Gazpacho would join a community (based on their shared interest of the language). On the technical side I found an interesting mix of problems (that turned out to just be one). Matchmaking needs P(A beats B) from two ratings. Grading open-ended output is unreliable with rubrics, so instead of scoring one answer I only ever ask "which of these two is better", Comparative Judgment, with scores recovered via Bradley–Terry. Calibrating content difficulty across CEFR/JLPT levels is Item Response Theory, usually a Rasch model. All three are the same logistic function. Elo is an online gradient step on the Bradley–Terry likelihood; Rasch is Bradley–Terry with one side fixed as "the item." So a 1v1 match is the pairwise comparison the judge needs, the judge's output is the observation the rating update consumes, and item difficulty falls out of the same fit. Ratings are Glicko-2, so a new player carries explicit uncertainty (high RD) and converges in a handful of matches instead of thirty. Users see it as a Fluency Score. Two Questions: The human one: does competition make you want to practice, or does it just make you anxious about practicing? If you've shipped LLM-as-judge somewhere the score had real consequences, how did you detect drift you couldn't see from inside the system? If you think you may benefit/want to use from this, I put together a small waitlist of people who might be interested in using this in the future (I also put a small demo of a little creative writing prompt on the site... see if you can get highest accuracy!) Thanks for taking the time to read https://thelingo.xyz
2026-09-01
Show HN: Open-source hands-free mouse control with Tracky Mouse
unrated
Tracky Mouse lets you control your whole computer with just a webcam. It supports different modes to click, including dwell clicking and facial gestures. It can even provide three button mouse functionality, using closed eyes as modifiers to change what type of click is performed when opening your mouth. It also supports different modes to move the mouse, including Direct, Joystick style, and D-pad style modes. It's free (and ad-free) and will always will be. I want to make this the best accessibility software that I can. I have big plans already, but I'm always open to ideas. Downloads and an in-browser demo can be found on the website: https://trackymouse.js.org/
2026-08-31
alphaparkinc/genpark-autonomous-dom-tree-vision-web-interactor-skill
unrated
Autonomous DOM tree vision web interactor & accessibility mapper (Browser-Use style)
2026-08-29
Accesserty Pulse
unrated
Accesserty Pulse monitors interaction signals and detectable accessibility risks on live websites. Free plans for everyone and 14-day Pro trial.
2026-08-29
Pa11y
unrated
Automated accessibility testing tool that runs HTML CodeSniffer or axe-core from the command line. Supports CI/CD integration, multiple reporters, and testing against WCAG 2.1 AA standards.
2026-08-29
squirrelscan
unrated
squirrelscan is a website QA tool built for coding agents such as Claude Code and Cursor. Its squirrel CLI crawls a live site and runs 260+ audit rules across SEO, performance, security, accessibility, structured data and agent experience, then returns exact source-mapped fixes. Runs from the terminal, CI, the cloud, or over MCP.
2026-08-29
axe-core
unrated
Accessibility engine for automated Web UI testing. Tests HTML against WCAG 2.0, 2.1, and 2.2 guidelines. Used by Google Lighthouse, Microsoft Accessibility Insights, and thousands of organizations worldwide.