Updates
Project releases, articles, and new tech being explored — in reverse-chronological order.
Inner Compass is a personal reflection app with a crystal card guide, affirmations, angel-themed messages, and saved favorites. It is meant for reflection and inspiration only. It is not medical advice, diagnosis, or treatment.
Read
Score Reader is an accessible sheet-music reader for iPhone. It imports MusicXML and compressed MXL files, plus simple PDF scores, and lets a person move through the music with VoiceOver and play it back. Reading dense PDF scores and capturing sheet music with the camera are still being improved.
Read
Language Explorer teaches useful, contextual vocabulary through real-world situations. Learners encounter phrases and words inside scenarios such as catching a bus, ordering food, asking about a job, or understanding a lease. It is currently a prototype in active development and is not yet a finished public release.
Read
Jen is a supportive wellness-planning tool based on the Wellness Recovery Action Plan (WRAP) model. It helps you identify what keeps you well, notice early changes, build a personal action plan, and organize strategies for harder times. Jen is designed to be calm, autonomy-centered, and non-medicalized: it supports reflection and planning, not diagnosis or treatment. It does not replace professional care, therapy, or emergency help.
Read
Just Tell Me is a focused food-label assistant within the AIVIS Vision mobile experience. A user asks a specific question—such as whether a product contains an allergen, what the ingredients are, what the nutrition facts say, whether an expiration or best-by date is visible, or what product a barcode identifies—then points the rear camera at the package or selects up to six photos. Because food information is often spread across different sides of a package, the app combines evidence from multiple camera angles or selected images, then gives a short spoken and on-screen answer supported only by what is visible. It can read ingredient lists, identify potential allergens from visible ingredients, summarize nutrition labels, locate expiration or best-by dates, and recognize barcodes. For supported food items, verified product information from Open Food Facts may be used when a reliable barcode or product match is available. It must never invent an ingredient, allergen, nutrition value, or date that is not visible or supported. Users should verify critical allergy and food-safety decisions because AI analysis can be incomplete or incorrect. Simple positioning guidance such as move closer, hold steady, or slowly turn the package helps the user capture what the app needs. Other visual questions, such as finding a Start button, reading a price, or comparing two items, are secondary uses.
Read
Howe is a simple assistant for understanding how to do tasks in plain language. A person asks Howe how to do something, and Howe explains it as clear, manageable steps without unnecessary jargon or assumed knowledge. The guiding invitation is simple: just ask Howe.
Read
Beth is a body-double and executive-function assistant. It stays present while a person works, helps define the next manageable action, breaks tasks into smaller steps, checks in at a useful pace, and helps someone recover when attention or energy shifts. The experience is meant to feel collaborative and grounding rather than like a productivity tracker or a generic chatbot.
Read
Cue Interpreter is an AI-assisted social-cue and body-language interpretation tool. During or after an interaction, it identifies meaningful observable changes — turning toward or away, leaning closer or farther, nodding, head shaking, pointing, waving, posture changes, increased movement, or a possible attempt to enter or leave the interaction. It always separates what was observed from what it might mean, states its confidence, and offers alternative explanations. It never claims to read minds or presents emotion as fact, because body language varies across people, cultures, disabilities, neurotypes, and situations.
Read
Open Builder is a live, hands-on program for turning ideas into working apps, games, websites and tools using AI development agents. It is designed first for blind and visually impaired builders and works for anyone with little or no coding experience. Every lesson asks you to do something, and the course ends with your own published project.
Read
Visual Narrator watches a video alongside you and narrates what is happening — action, places, people, and on-screen text — so the description arrives in time with the scene rather than after it.
Read
Technology is only one part of expanding independence. Sometimes the work begins by protecting the services, opportunities, and support systems that make independence possible.
Read
Two projects — Sign Sense and ASL Speaker — are working to make American Sign Language easier to learn, use, and share across blind, sighted, Deaf, and hearing users.
Read
Career Compass helps people build a resume around transferable strengths and then find work that fits their real needs — accommodations, schedule, remote options, and physical demands — instead of matching on job title alone.
Read
SpeakEasy Translator listens through the microphone in one language and speaks the translation aloud in another in near real time, with simple from/to language pickers and no reading required.
Read
Sign Sense is a suite of ASL lessons and practice games designed to be equally playable by blind and sighted learners, using descriptive language, audio cues, and tactile-friendly explanations alongside visual demonstrations.
Read
Type Braille turns the home row of any keyboard into six braille keys, so learners can practise cells, letters, contractions, and full words directly in the browser. Lessons build from single dots to reading and writing sentences, with audio feedback at every step.
Read
Warden's Call is an audio adventure game inspired by the Demon Cycle series. You play as a warder facing the threats of the night, using keyboard or controller to move, fight, and make choices in a world rendered through spatial audio, voice acting, and screen-reader-friendly text. The game is built so anyone can play — with eyes open, with a screen reader, or with headphones and no screen at all.
Read
Mirebound is an audio-first adventure game. The world is built entirely from sound: spatial cues tell you where paths open, ambient layers reveal rooms and weather, and characters speak with distinct voices and directions. You move with the keyboard or gamepad, interact with a single action button, and listen to understand where you are. The objective is to explore the town of Mirebound, complete small quests for its residents, and piece together what happened to the place through conversation and discovery. Because every clue is delivered as audio or text, the game can be played with eyes closed, with a screen reader, or with visuals on.
Read
A browser-based, keyboard-and-audio game built in a few days with Godot and AI — and why stereo spatial audio is a native way to play, not an accessibility add-on.
Read
Access Atlas is an accessible map for discovering and sharing accessibility information about real places. Users can now submit their own accessibility data, which sits side by side with AI-generated insights, so both are visible for a place. Together they cover a location's mobility, sensory, restroom, and parking accessibility, so people know what to expect before they go and can add what they learn back to the shared record.
Read
NORA records short audio snippets triggered by keywords to support memory recall. It listens for specific cue words and automatically captures a brief recording, helping people remember appointments, names, places, and other details from their day, then prompts follow-up questions to log the relevant information. NORA is now being built with Letta, an AI focused on persistent memory, so recall gets stronger over time instead of being limited to individual snippets.
Read
An AI visual interpreter that discusses what your camera sees in real time. Point your camera at anything and have a live, voice-driven conversation about it, with customizable AI agents, spatial audio voice commands, and task-specific focus modes. Also available as a downloadable Mac app. AiVi is now being built in partnership with Embr Technologies (embrintellegence.ai) to make the app as good as it can be, with the first build from that partnership rolling out to beta testers soon.
Read
SceneCast transcribes audio or video into readable, downloadable text. Alongside the speech it identifies who is speaking, tags sound effects and music, and marks scene changes, so the transcript reflects what happened rather than only what was said.
Read
ASL Speaker translates American Sign Language gestures into spoken words in real time, using computer vision and machine learning to recognize signs and vocalize their meaning.
Read
Awareness Engine increases situational awareness by detecting and summarizing important events in your environment. It can be configured to recognize speech, environmental sounds, and more, with notifications available on Apple Watch.
Read
Echo Pal listens through the microphone and speaks back everything it hears using text-to-speech.
Read
An AI image editor for generating, modifying, and describing visual content. Users can create new images with AI or upload existing ones, then make in-place modifications without regenerating the whole image from scratch. It also produces descriptive text for any uploaded or generated image.
Read
Most conversations about accessibility focus on end users. But what about the people building the tools? A look at how inaccessible development workflows can exclude the very creators trying to make technology more inclusive.
Read
A gamified educational app that teaches typing skills to users of all abilities, using audio and video to create an engaging, accessible learning experience for diverse learners.
Read
An AI-powered augmentative and alternative communication (AAC) app that predicts and speaks text. It learns user patterns to predict what someone wants to say, with a text-only mode and a picture mode that pairs images with words to support diverse communication styles.
Read
Thinking out loud about the difference between memory, context, and surveillance in camera-based assistants.
Read
Notes on the difference between products that anticipate a person and products that decide for them.
Read
A short piece on the difference between self-sufficiency and self-direction, and why the distinction matters for how we design tools.
Read
A short introduction to what Open Independence is, why it is anonymous, and how the work will unfold in public.
Read
