> For the complete documentation index, see [llms.txt](https://docs.ig3.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ig3.ai/how-ig3-works/ig3-overall-architecture/edge-node-layer.md).

# Edge Node Layer

The Edge Node Layer forms the foundation of the iG3 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.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.ig3.ai/how-ig3-works/ig3-overall-architecture/edge-node-layer.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.