Getting Started
Welcome to Oneliac, a privacy-preserving healthcare AI platform that leverages zero-knowledge proofs and blockchain technology to secure patient data while enabling advanced medical analysis.
What is Oneliac?
Oneliac is a decentralized healthcare platform that combines:
- Zero-Knowledge Proofs (ZK-SNARKs): Verify patient eligibility and medical data without exposing sensitive information
- Blockchain Integration (Solana): Immutable, transparent record of medical transactions on the Solana network
- Federated Learning: Train diagnosis models across multiple healthcare providers without centralizing patient data
- IPFS Storage: Encrypted patient records distributed across the InterPlanetary File System
- Cross-Chain Oracles: LayerZero integration for pharmacy verification across multiple blockchains
Key Features
1. Privacy-Preserving Eligibility Verification
Check insurance coverage without exposing medical history using cryptographic zero-knowledge proofs.
2. Secure Prescription Validation
Validate prescriptions with:
- Automatic drug interaction checking
- Patient eligibility verification
- Cross-chain pharmacy confirmation via LayerZero oracle
- Zero-knowledge proof verification
3. Federated Learning for Diagnosis
Train diagnosis models across multiple healthcare organizations while maintaining data privacy through:
- Encrypted gradient computation
- Differential privacy noise injection
- Secure aggregation without centralizing patient data
4. Encrypted Data Storage
All patient data is encrypted before storage on IPFS, with cryptographic hashes ensuring data integrity.
Quick Start
Prerequisites
- Python 3.9+
- Docker (optional, for containerized deployment)
- Access to Solana Devnet or Mainnet
Installation
Option 1: Install from PyPI (Recommended)
pip install oneliac
See PyPI package for version info.
Option 2: Clone repository and install from source
# Clone the repository
git clone https://github.com/Oneliac/Product-Oneliac.git
cd Product-Oneliac
# Install dependencies
pip install -r requirements.txt
Option 3: JavaScript/TypeScript
npm install oneliac
See npm package for JavaScript SDK.
Running the API Server
# Start the FastAPI server
uvicorn agents.api:app --reload --host 0.0.0.0 --port 8000
The API will be available at http://localhost:8000
API Documentation:
- Interactive docs: http://localhost:8000/docs
- ReDoc: http://localhost:8000/redoc
First API Call
Check the health endpoint:
curl http://localhost:8000/health
Response:
{
"status": "healthy",
"version": "0.1.0",
"message": "Healthcare agents API operational"
}
Architecture Overview
Oneliac operates through multiple integrated layers:
Patient Layer
↓
Encrypted Data + IPFS Storage
↓
Zero-Knowledge Layer
↓
ZK-SNARK Proof Generation (Groth16)
↓
Blockchain Layer (Solana)
↓
Smart Contract + Verifier
↓
AI Agent Layer
↓
Eligibility Agent | Prescription Validator | Federated Learning
↓
External Systems
↓
Insurance APIs | Pharmacy Systems | EHRs
Main Components
Eligibility Agent
- Verifies patient insurance coverage for procedures
- Uses ZK proofs to protect patient identity
- Returns coverage percentage and authorization requirements
Prescription Validator
- Validates prescriptions against medical history
- Checks for drug interactions
- Queries LayerZero oracle for pharmacy confirmation
- Ensures patient eligibility before approval
Federated Learning Coordinator
- Aggregates encrypted training data from multiple agents
- Applies differential privacy for additional protection
- Updates the global diagnosis model
- Never exposes raw patient data
Next Steps
- Learn the Architecture: Read about ZK-SNARKs integration
- Integrate with the API: Follow our API integration guide
- Deploy to Production: Check out deployment instructions
- Understand Security: Review security best practices
Support
For issues, questions, or contributions:
- GitHub: https://github.com/orgs/Oneliac
- Telegram: https://t.me/oneliac_bot
- Website: https://www.oneliac.xyz
- PyPI: https://pypi.org/project/oneliac/
- npm: https://www.npmjs.com/package/oneliac
License
Oneliac is licensed under Apache 2.0. See LICENSE for details.