Edge Node Layer

The Edge Node Layer forms the foundation of the Evora network, composed of distributed devices that run AI workloads close to users. These devices process real-time interactions, reduce latency, and preserve privacy by minimizing cloud dependency.

Key Capabilities:

• Real-time Audio I/O: Supports speech-to-text (STT) and text-to-speech (TTS) locally for instant voice interaction.

• Local Inference: Runs lightweight AI models such as quantized LLMs, Whisper.cpp, and compact TTS engines directly on-device.

• On-Device Task Execution: Handles specialized tasks like object detection, surveillance, and sensor data classification.

• Local Identity Management: Manages decentralized identifiers (DIDs) for secure and verifiable identity.

• Status Reporting: Periodically sends heartbeats, performance stats, and usage metrics to the AI Gateway.

Software Stack:

• Dockerized Microservices: Modular services for LLMs, audio processing, and task handlers.

• K3s (Lightweight Kubernetes): Orchestrates containerized services efficiently on resource-constrained hardware.

• gRPC or WebSocket: Enables fast and secure real-time communication with the AI Gateway.

• Edge Agent Daemon: A lightweight background service that handles device coordination, task reception, and model updates.