Nobody has validated a card yet. If you have a spare AMD box, flash it and file the run — you would be first. Test a box
cameo github

your AMD card.
serves LLMs.

Flash a USB, boot the AMD box, open the local web app. Models run offline.

RX 580RX 68007900 XTXMI210APUs

Compatibility depends on the card, driver, model, and available memory. Check before release use.

Download Cameo

Free • Open source • Apache 2.0

I have a spare box GitHub
Cameo console: GPU list, endpoints, start a smoke-test model

01how

ISO. Flash. Boot. cameo.local:9090

That’s the product. After login the box prints that URL. The screenshot above is the real console, not a mock.

02tiers

Vulkan on every card. ROCm when it helps.

Tier 1

Train + Serve

7900 XTX · MI210

train
serve

Tier 2

Serve

RX 6800 · 6700 XT

train
serve

Tier 3

Vulkan Inference

RX 580 · APUs

train
serve

03get it

Image. Flash. Done.

flash cameo-*.iso → boot Install Cameo to disk → chat cameo.local:9090
Knossos standalone for Windows

Standalone harness

Current Windows beta: knossos.exe. Needs a model — Ollama, Anthropic, or a running Cameo box. Not a certified release; replace this zip when you cut the next one.

Windowsx86_64 · beta

Knossos 0.2.0-beta.1 CLI plus constitution and license.

Download Windows zip

SHA-256 checksum

Linux + macOScoming later

Packages will appear here after their release builds pass validation.

Installation guide · USB to local chat · erases the selected disk

2 · Flash a USB

Windows: Rufus in DD Image mode (ISO mode often will not boot), or Etcher. Linux/macOS: Etcher, or:

sudo dd if=cameo-*.iso of=/dev/sdX bs=4M status=progress oflag=sync

3 · Plug it in, set an account

Disable Secure Boot (or the stick is ignored and Windows boots). Put the USB in the AMD machine. Install Cameo to disk is already the default entry. It shows the detected GPU and tier, then asks for:

which disk to erase admin username admin password

Nothing is downloaded. The installer copies the live image onto that disk, writes a console key, and enables cameod. Then reboot and pull the USB.

4 · Play, offline

From a laptop or phone on the same LAN (plug the box into Ethernet if it has a port), open the URL printed after login — http://cameo.local:9090 or the IP. Enter the key. Start qwen2.5-0.5b (smoke test, already on disk). Chatting never phones home. Extra GGUFs: drop them in /var/lib/cameo/models.

Cameo Mesh: that’s when you connect Wi-Fi

A single box does not need Wi-Fi. Cameo Link joins it to a request-level pool; Mesh does not combine VRAM or shard one inference across machines.

Ethernet — plug in, DHCP is automatic Wi-Fi — iwctl on that node only extra models — cameo pull 
iwctl
  station list
  station wlan0 scan
  station wlan0 get-networks
  station wlan0 connect 'YourSSID'

Pair Cameo Link to the hub with a single-use code. Request routing and pairing are preview; mutual TLS is not available yet. One machine, one card, one house can stay offline after you flash.

Developers: container or build the ISO yourself

Container — host owns the GPU driver:

podman build -f containers/Containerfile -t cameo:vulkan .
podman run --rm -p 9090:9090 \
  -v cameo-models:/var/lib/cameo/models \
  --device=/dev/kfd --device=/dev/dri \
  --group-add video --group-add render \
  cameo:vulkan

Build the ISO on an Arch host:

git clone https://github.com/sadlowskik/Cameo
sudo ./scripts/build-iso.sh
sudo CAMEO_EDITION=lite ./scripts/build-iso.sh

Beta, pre-v1. Flash an .iso, not Source code. Check SHA256SUMS. The disk installer erases the drive you pick. Source: github.com/sadlowskik/Cameo.