The Path › Chapter 6 of 9

Your own hardware

CPU, GPU, laptop, rack

About 30 minutes · for operators · bricks: awdk · awnode

Teach

How the kit picks a brain for your machine

Chapter 2 ran a brain on your CPU or GPU. But how did the kit know which one you had? And how big a model is safe for your RAM?

The kit measures your hardware — how much RAM, whether you have a GPU, whether Docker is running — and picks a model and a backend that fit. An 8B model needs at least 8 GB of RAM (or VRAM); Bonsai's 1-bit family fits in less. vLLM on NVIDIA is faster than llama.cpp on a CPU. The kit makes that choice so you do not have to know the numbers.

Model size and memory

A model is numbers — weights. An "8B model" has 8 billion of them. A 4-bit quantization stores each in 4 bits instead of 32, so it fits in 8× less memory. This is why quantization exists: the same brain in a smaller space.

  • The orchestrator model is the open 8-billion-parameter brain the platform itself runs on. It is a good default.
  • Bonsai is the 1-bit family — Bonsai-27B is 27 billion parameters in 3.8 GB. It fits on a machine with 8 GB of RAM and runs on a CPU. It is the brain for tiny machines.

What a backend is

A backend is the software that loads and runs a brain. llama.cpp runs models on CPUs and small GPUs. vLLM runs them on NVIDIA with high throughput. Ollama is a middle ground — easy to use, a bit slower.

Registering a backend is what lets agents anywhere reach it. A brain nobody registered is a brain nobody can call. adk backend status tells you which brain the kit is pointed at. adk up registers this machine as a service.

Do

1
bash
adk quickstart

You should see: hardware detected, a recommended setup for it, and a running backend

If not: On a machine with no GPU this is the same as chapter 2 and says so. On NVIDIA it offers vLLM if Docker is present.

2
bash
adk backend status

You should see: Backend, Endpoint and Model - the brain the kit is currently pointed at

If not: If it says not configured, chapter 2 did not finish - run adk quickstart-local first.

3optional
bash
adk up

You should see: your agent deployed as a service on this box, enrolled with your workspace, a heartbeat every 60 s

If not: Needs a login (chapter 3) and Docker. Without either, adk run from chapter 4 is the offline equivalent.

Check you are done

bash
adk backend status

You should see: the backend you chose, with an Endpoint that answers

What you learned

One estate, 8 doors

These projects are organs of the same system — the same identity plane, the same agent runtime, the same operational discipline. Follow any of them.

The ecosystem this belongs to

Every Aitherium repository publishes an aither-manifest.json beside its page, and each surface reads all of them — so the network is browsable from any node in it.