Download

Wyrdsekai 0.4.2 — Apache-2.0

The installers are large because they are self-contained: a JVM, an inference runtime, and the embedding model travel with the package. You should not have to assemble a Java toolchain to talk to your companion.

The short way

# Linux / macOS
curl -fsSL https://wyrdsekai.org/install | bash

# Windows (PowerShell)
irm https://wyrdsekai.org/install.ps1 | iex

Nothing is served from wyrdsekai.org except the script itself: the artifact and the checksums both come from the same GitHub release, and the script verifies the one against the other before installing. Everything it does, you can do by hand below.

Install

• Linux

  curl -fLO https://github.com/Wyrdsekai/wyrdsekai/releases/download/v0.4.2/wyrdsekai_0.4.2_amd64.deb
  sudo dpkg -i wyrdsekai_0.4.2_amd64.deb
  wyrd start

• macOS

  curl -fLO https://github.com/Wyrdsekai/wyrdsekai/releases/download/v0.4.2/Wyrdsekai-0.4.2.pkg
  open Wyrdsekai-0.4.2.pkg
  wyrd start

  On Apple Silicon the companion thinks locally through MLX, which wyrd setup installs for you. Intel Macs need one extra step: MLX is Apple-Silicon only and the package does not bundle an Intel inference engine, so run brew install llama.cpp first — or point the node at an API key, or at another machine in the household. Setup will tell you which case you are in rather than failing quietly.

• Windows (PowerShell)

  curl.exe -fLO https://github.com/Wyrdsekai/wyrdsekai/releases/download/v0.4.2/Wyrdsekai-0.4.2.msi
  msiexec /i Wyrdsekai-0.4.2.msi
  wyrd start

• Relay

  A relay is the door your phone comes through. It is deliberately tiny — no JVM, no models — and it never sees inside your world; it shuffles encrypted bytes between your phone and your household. If you have nowhere to put one yet, the public relay will do — but running your own is the point, and it is three commands.

  curl -fLO https://github.com/Wyrdsekai/wyrdsekai/releases/download/v0.4.2/wyrdsekai-relay-0.4.2.tar.gz
  tar xzf wyrdsekai-relay-0.4.2.tar.gz
  cd wyrdsekai-relay
  sudo sh relay.sh relay.example.com

Verify before you run

You are about to run 1.8 GB of someone else's software as root. Check it arrived intact:

curl -fLO https://github.com/Wyrdsekai/wyrdsekai/releases/download/v0.4.2/SHA256SUMS
sha256sum -c SHA256SUMS --ignore-missing      # Linux
shasum -a 256 -c SHA256SUMS --ignore-missing  # macOS

Every artifact also carries a Sigstore bundle (<file>.sigstore.json on the release) attesting its hash from GitHub's build identity. After installing, wyrd verify-release <artifact> checks it against the public transparency log.

A checksum served from the same host as the file proves the download was not corrupted in transit. It does not prove the host was not compromised — for that, verify the attestation above, or build from source. Both paths are documented, and neither is treated as the paranoid option.

The first start

Expect roughly ten minutes. wyrd start runs first-time setup, fetches about 5.3 GB of model weights, and brings up the inference containers before the server answers. Then:

sudo wyrd invite bootstrap --name yourname   # mint a steward invite
ssh yourname@localhost -p 7022               # the code is your password

Full instructions, including building from source and multi-machine households, are in INSTALLATION.md.

Mobile

The Android and iOS clients are built from the clients directory. They are not in an app store for this release: you build and sideload them, and they reach your household through your own relay.

Models

The companion models are open weights (Apache 2.0), hosted on Hugging Face: huggingface.co/wyrdsekai. Installers fetch them automatically during wyrd setup — you only need these links for mirrors, re-quantization, or fine-tuning.