# Embedl Hub

Embedl Hub is a secure, traceable MLOps platform for edge AI workflows. It centralizes
model compilation, on-device testing, validation, and artifact tracking into a single
system. This enables teams to deliver production-grade edge AI with full traceability
and compliance support — especially in safety-critical environments.

The Embedl Hub Python library (`embedl-hub`) enables you to programmatically interact
with the Embedl Hub platform. [Create a free Embedl Hub account](https://hub.embedl.com/docs/setup)
to get started with the `embedl-hub` library.

## Installation

`embedl-hub` requires Python 3.10 or newer.

The base install gives you experiment tracking, the CLI shell (`auth`,
`init`, `log`, `list-devices`), and the Python tracking API — without
any backend execution toolchain:

```sh
pip install embedl-hub
```

To use the bundled compile, profile, and invoke components (Embedl's
ready-made wrappers for TFLite, ONNX Runtime, and TensorRT), install
one or more toolchain extras:

| Workflow                                | Install command                         |
| --------------------------------------- | --------------------------------------- |
| TFLite (local + QAI Hub + device cloud) | `pip install 'embedl-hub[tflite]'`      |
| ONNX Runtime (QAI Hub + embedl-ORT)     | `pip install 'embedl-hub[onnxruntime]'` |
| TensorRT (`trtexec` over SSH)           | `pip install 'embedl-hub[tensorrt]'`    |
| Everything                              | `pip install 'embedl-hub[all]'`         |

Linux aarch64 installs of `[tflite]` skip the `onnx2tf`-based local
conversion path and the `ai-edge-*` quantization deps because the
upstream TensorFlow package does not publish Linux aarch64 wheels. The
QAI Hub TFLite provider still works.

Running a backend command without its extra installed prints a clear
hint pointing at the right `pip install` command rather than a raw
import traceback.

## Documentation

Tutorials and guides are available at [hub.embedl.com/docs](https://hub.embedl.com/docs).

```{eval-rst}
.. toctree::
   :maxdepth: 1
   :caption: References

   api
   cli
```