README.md
June 6, 2026 Β· View on GitHub
ποΈ SightlineAI
Empowering independent navigation through multimodal artificial intelligence.
"π Live Demo" (https://rudra496.github.io/sightlineai) β’ "π Documentation" (https://github.com/rudra496/sightlineai) β’ "π Report Issue" (https://github.com/rudra496/sightlineai/issues) β’ "π‘ Feature Request" (https://github.com/rudra496/sightlineai/issues)
"License" (https://img.shields.io/badge/License-MIT-green.svg) "Python" (https://img.shields.io/badge/Python-3.11+-blue.svg) "FastAPI" (https://img.shields.io/badge/FastAPI-Modern_API-009688.svg) "Open Source" (https://img.shields.io/badge/Open%20Source-Yes-success.svg) "AI" (https://img.shields.io/badge/AI-Gemini%20%7C%20Qwen-purple.svg)
π Overview
SightlineAI is an open-source accessibility platform designed to help blind and visually impaired individuals better understand, navigate, and interact with their surroundings.
By combining computer vision, OCR, conversational AI, and navigation intelligence, SightlineAI transforms ordinary devices into intelligent accessibility companions capable of delivering real-time environmental awareness and guidance.
π Key Features
- ποΈ Real-time scene understanding
- π OCR and document reading assistance
- β οΈ Obstacle and hazard awareness
- πΊοΈ Context-aware navigation support
- π¬ Conversational AI assistance
- π Multi-language accessibility support
- π Offline fallback capabilities
- β‘ Real-time WebSocket communication
π§ AI Architecture
SightlineAI follows a multi-model architecture that supports multiple AI providers.
Supported Models
Provider| Capability Google Gemini| Multimodal reasoning, scene understanding, accessibility guidance Qwen| Vision analysis, conversational intelligence, contextual assistance
This provider-agnostic design improves flexibility, reliability, and future scalability.
ποΈ System Workflow
Camera / Voice Input β Visual & Context Processing β Gemini / Qwen AI Analysis β Risk & Accessibility Assessment β Voice and Text Guidance
π Impact
SightlineAI addresses accessibility challenges faced by more than 285 million visually impaired people worldwide, particularly in regions where advanced assistive technologies remain financially inaccessible.
United Nations SDGs
- π SDG 3 β Good Health & Well-Being
- β€οΈ SDG 10 β Reduced Inequalities
- π SDG 11 β Sustainable Cities & Communities
π οΈ Technology Stack
Category| Technologies Backend| Python, FastAPI Frontend| React, HTML, CSS, JavaScript AI Models| Google Gemini, Qwen Vision| OCR, Computer Vision Infrastructure| Docker, Redis Database| SQLite, PostgreSQL Navigation| OpenStreetMap
βοΈ Quick Start
git clone https://github.com/rudra496/sightlineai.git
cd sightlineai
cp .env.example .env
pip install -r requirements.txt
python -m app.main
π€ Contributing
Contributions are welcome.
Areas of contribution include:
- Accessibility improvements
- AI model enhancements
- Documentation
- Localization
- Bug fixes
- UI/UX improvements
π License
Released under the MIT License.
π¨βπ» Maintainer
Rudra Sarker
Industrial & Production Engineering Shahjalal University of Science and Technology (SUST)
π Portfolio: https://rudra496.github.io/site
π GitHub: https://github.com/rudra496
πΌ LinkedIn: https://www.linkedin.com/in/rudrasarker
π§ Email: rudrasarker130@gmail.com
Built for accessibility. Built for independence. Built for impact.