Lux Protocol / Provenance Chain
LuxProtocol combines blockchain technology and artificial intelligence to provide tamper-proof authentication for luxury goods, creating a secure bridge between physical collectibles and their digita
Created on 1st March 2025
•
Lux Protocol / Provenance Chain
LuxProtocol combines blockchain technology and artificial intelligence to provide tamper-proof authentication for luxury goods, creating a secure bridge between physical collectibles and their digita
The problem Lux Protocol / Provenance Chain solves
Counterfeit Luxury Goods Market
The luxury goods industry loses billions annually to counterfeits. Lux Protocol creates an immutable, decentralized authentication system that:
- Verifies authenticity of luxury items using AI analysis and blockchain verification
- Prevents forgery through cryptographic proofs that cannot be duplicated
- Establishes provenance by recording the complete ownership history on-chain
Trust Issues in Resale Markets
When buying second-hand luxury items, collectors face significant trust challenges:
- ✓ Builds confidence by providing transparent, tamper-proof verification
- ✓ Eliminates intermediaries by replacing traditional authentication services with decentralized AI operators
- ✓ Reduces fraud through NFC tags that link physical items to their digital certificates
Technical Fragmentation
The luxury market lacks standardized digital authentication:
- Unifies verification across brands and marketplaces through a common protocol
- Simplifies integration for luxury brands through flexible operator architecture
- Scales with demand through a decentralized network of validators
Document Verification
Luxury items often come with certificates, receipts, and warranties that can be lost or forged:
- Digitizes documentation by securing images of important papers on IPFS
- Verifies paperwork using the same AI systems that authenticate the physical items
- Links documents to items through immutable blockchain records
Economic Incentives
The protocol creates a self-sustaining ecosystem where:
- Operators stake assets to participate, ensuring honest behavior
- Authenticators are rewarded for accurate verifications
User Interaction and Data Flow
User Interaction and Data Flow
Collector Journey
Authentication Request
- Scan Physical Item: Collector uses the mobile app to scan NFC tag on luxury item
- Submit Images: Upload high-resolution photos of the item from multiple angles
- Add Supporting Documents: Include receipts, warranty cards, and certificates
- Create Authentication Task: System hashes images and documents, then creates a task on the blockchain
graph LR
A[Collector] -->|Scans NFC Tag| B[Mobile App]
B -->|Uploads Images| C[IPFS Storage]
C -->|Returns Content Hash| D[LuxServiceManager]
D -->|Creates Task| E[Blockchain]
Verification Process
- Task Broadcasting: The authentication task is broadcast to the network
- ElizaOS AI Processing: ElizaOS-powered operators retrieve the task and analyze images using Google Vision API
- AI Feature Analysis: Google Vision extracts key features and patterns from luxury goods images
- Consensus Building: Operators submit signed authenticity verdicts
- Result Notification: Collector receives notification when verification is complete
Viewing Authentication Results
- Authentication Dashboard: Collector views detailed results including:
- Overall authenticity score (0-100%)
- Specific feature verifications (materials, craftsmanship, etc.)
- AI confidence metrics from Google Vision analysis
- Operator consensus information
- Digital Certificate: Upon successful verification, a digital certificate is issued
- Provenance Tracking: Complete history of the item is visible on the blockchain
Seller Workflow
- Listing Authenticated Items
- Connect Wallet: Seller connects their wallet to the marketplace
- Select Verified Item: Choose from previously authenticated collectibles
- Create Listing: Set price, auction parameters, and additional details
- Publish: Listing appears on marketplace with verification badge
The project architecture and development process
Project Architecture & Development Process
Core Architecture
Lux Protocol combines blockchain, AI, and NFC to authenticate luxury goods:
-
Smart Contract Layer
- LuxServiceManager: Manages authentication tasks
- AuthenticationController: Handles authentication logic
- CollectibleRegistry: Stores verified items
- NFCLuxuryMarketplace: Enables trading of authenticated items
-
AI Authentication
- ElizaOS-based agents run on decentralized nodes
- Google Vision API analyzes luxury item images
- Operators sign and submit verification results
-
Physical-Digital Bridge
- NFC tags connect physical items to digital certificates
- IPFS stores images and documents permanently
- Blockchain records authentication history
Development Workflow
-
Contract Development
- Design → Implementation → Testing → Deployment
- Forge scripts automate deployment and testing
-
Operator Development
- Node.js environment with ethers.js integration
- Blockchain monitoring for new tasks
- AI model integration with Google Vision
- Cryptographic signatures for responses
Key Implementation Details
- Authentication Process: Task creation → AI analysis → Verification → Certificate
- Security: Cryptographic signatures ensure operator integrity
- Error Handling: Robust recovery mechanisms for continuous operation
- Discovery System: Flexible contract address detection across environments
Challenges Solved
- Unified signature format across different ethers.js versions
- Fallback mechanisms for contract function compatibility
- Automated environment setup for quick deployment
Product Integrations
Key integrations to include:
- Google Vision API - central to the AI authentication process
- ElizaOS - the framework for the AI agents
- Ethereum/blockchain integrations
- IPFS for decentralized storage
- NFC technology integration
- Any other APIs or services mentioned in the files
I'll describe each one's specific role in the project.
</think>
Product Integrations
AI and Machine Learning
Google Vision API
- Core Function: Powers visual authentication of luxury items
- Integration Points:
- Image analysis for material identification
- Pattern recognition for brand-specific manufacturing details
- Logo verification and authenticity checks
- Anomaly detection for identifying counterfeits
- Implementation: Called from ElizaOS-based operator nodes after retrieving image hashes from IPFS
ElizaOS
- Core Function: Provides AI agent framework for decentralized operators
- Integration Points:
- Hosts the authentication logic
- Manages communication with Google Vision
- Processes authentication results before blockchain submission
- Ensures consistent operation across the operator network
Blockchain Infrastructure
Ethereum Smart Contracts
- Core Function: Provides immutable record-keeping and verification
- Integration Points:
- ethers.js for contract interaction
- Web3 providers for blockchain connection
- Contract event monitoring (TaskCreated events)
- Transaction signing and submission
Eigenlayer Protocol
- Core Function: Provides security through staking
- Integration Points:
- Operator staking mechanism
- Slashing conditions for malicious behavior
- Economic incentives for honest verification
Key differentiators and uniqueness of the project
Physical-to-Digital Bridge: NFC tags link real-world collectibles to on-chain NFTs.
AI-Driven Authentication: Automated, scalable verification using Eliza OS and Ora RMS for brand/condition checks, plus Google Vision for metadata extraction.
Decentralized Attestation: EigenLayer AVS ensures no single point of failure in authenticity decisions.
Comprehensive Provenance: Every ownership transfer and authenticity check is recorded on-chain, fostering transparency and trust.
Multi-Chain Deployment: Deployed on zkSync and Base for high throughput, low fees, and easy user onboarding.
Trade-offs and shortcuts while building
AI Dependence: We rely on a combination of Google Vision, Eliza OS, and Ora RMS for image analysis. Some components are more centralized than ideal; we plan to migrate certain features to more open or decentralized ML models.
Partial Off-Chain Storage: Storing large media files on IPFS is cost-effective but introduces dependency on pinning services. We balanced cost and reliability by choosing Pinata.
Time Constraints: Certain UI features and advanced search functionalities were simplified for the BUIDLathon deadline. We’ll enhance them post-hackathon.
Additional Features
Extended Marketplace: We added multi-category support (watches, sneakers, handbags) specifically during the BUIDLathon.
Improved NFC Scanner App: Enhanced the mobile app to instantly fetch on-chain data upon tag scan, providing a smoother user experience.
AI Confidence Score: Displayed a simplified “authenticity confidence” metric on each listing, leveraging Eliza OS + Ora RMS analysis, introduced for this event.
Tracks Applied (5)
Best Consumer App Deployed on ZKsync
zkSync ∎
Best EigenLayer AVS
EigenLayer
Best AI application or agent on EigenLayer
EigenLayer
Build an AI-powered app on Base
Base
