IKKIO
IKKIO is an AI-powered assistant for smart glasses and mobile phones that narrates the world in real time for blind and visually impaired users. The platform detects objects, reads text, and provides audio descriptions through voice-activated commands, with a contextual memory that learns user routines. It is hardware-agnostic, launching in 2026 with compatibility for Ray-Ban Meta and Brilliant Labs Frame glasses.
- AI Agents
- Artificial Intelligence
- Software Only
Funding
Founders
Founder details are not available yet.
Product
Problem
An estimated 235 million people worldwide live with blindness or low vision, often relying on sighted assistance or limited accessibility tools to navigate everyday environments. Identifying products, reading signs, recognizing people, and understanding spatial surroundings are constant challenges that reduce independence and quality of life.
Solution
IKKIO is an AI-powered assistant that runs on compatible smart glasses and mobile phones to narrate the world in real time for blind and visually impaired users. By pointing the device at any object, environment, or person, IKKIO delivers instant audio descriptions in the user's language. The system integrates object detection, text recognition, and spatial awareness to handle everyday scenarios, while a contextual memory feature learns routines and preferences over time to reduce the need for repeated explanations. Designed to be hardware-agnostic, IKKIO currently supports Ray-Ban Meta and Brilliant Labs Frame glasses, with more devices planned. The platform combines edge and cloud AI processing to deliver fast, responsive feedback without lag between looking and knowing.
Target Audience
IKKIO's primary customers are blind and visually impaired individuals seeking greater independence in daily life, along with accessibility organizations and low-vision service providers.
Features
- Hardware-agnostic architecture compatible with Ray-Ban Meta and Brilliant Labs Frame smart glasses at launch, with more devices planned
- Real-time object detection, text recognition, and audio description delivered through voice-activated, hands-free commands
- Hybrid edge and cloud AI processing that minimizes latency for fast, responsive feedback
- Contextual memory system that learns user routines, preferences, and frequently visited locations over time
- Privacy-first design with on-device data processing where possible and no storage of visual history
- Adaptive network optimization ensuring reliable performance on 5G, LTE, or local WiFi connections