Loreum Cortex is a decentralized AI inference network implemented in Go. It provides a robust p2p network that supports the DAG-aBFT consensus mechanism and enables core functions such as Sensor Hub, Agent Hub, and RAG (Retrieval-Augmented Generation) system.
The Loreum Cortex node consists of three primary layers:
- Network Layer: Handles P2P communication, API Gateway, and Consensus mechanism
- Business Layer: Implements Agent Hub, Sensor Hub, and RAG system
- Data Layer: Manages data storage with SQL, Redis, and Vector databases
- Go 1.20 or higher
- Docker and Docker Compose
- PostgreSQL 14+
- Redis 7+
- Vector database (Milvus/Qdrant/Weaviate)
-
Clone the repository:
git clone https://github.com/loreum-org/cortex.git cd cortex -
Install dependencies:
go mod tidy -
Build the project:
go build -o cortex ./cmd/cortexd -
Run the node:
./cortex serve
Comprehensive documentation for the Loreum Cortex project is available in the docs directory. The documentation covers:
- System architecture and core concepts
- Network, business, and data layer components
- Implementation details and API references
- Development and deployment guides
- Example use cases and integration examples
cortex/
├── cmd/
│ └── cortexd/ # Main executable
├── internal/
│ ├── api/ # API Gateway
│ ├── consensus/ # DAG-aBFT implementation
│ ├── p2p/ # P2P networking
│ ├── agenthub/ # Agent implementations
│ ├── sensorhub/ # Sensor implementations
│ ├── rag/ # RAG system
│ ├── storage/ # Data storage
│ └── reputation/ # Reputation system
├── pkg/
│ ├── types/ # Shared data types
│ ├── crypto/ # Cryptographic utilities
│ ├── config/ # Configuration management
│ └── util/ # Shared utilities
├── test/ # Test suites
├── scripts/ # Deployment scripts
└── docs/ # Documentation