Install and first run — Armore Edge docs

Step 1

Download

Pick your platform from the download page. Five installers, all free:

Platform	File	Size
macOS · Apple silicon	Armore-Edge-1.0.10-arm64.dmg	123 MB
macOS · Intel	Armore-Edge-1.0.10-x64.dmg	130 MB
Windows · x64	Armore-Edge-Setup-1.0.10-x64.exe	93 MB
Linux · deb	Armore-Edge-1.0.10-amd64.deb	88 MB
Linux · AppImage	Armore-Edge-1.0.10.AppImage	134 MB

!

There is no GUI installer for Linux-arm64 or Windows-arm64. Those architectures ship the command-line tool only — switch to the other tab if you are on one of them.

The command-line tool is a separate download from the same release. It is not inside the installer, and installing the app does not get you the binary.

gh release download v1.0.10 --repo uniQ-Ventures/armore-edge-public \
  --pattern 'armore-darwin-arm64' \
  --pattern 'armore-darwin-arm64.sigstore.json'

Pick the build for your platform — there are five, and unlike the app they cover arm64 on every OS. The command-line guide lists all twenty commands once you have it.

Step 2

Verify it before you run it

!

There is no in-app control for this, by design. A signature check is something you do to the installer before you trust it — so it cannot live inside the thing you have not yet decided to run. Switch to the command line for this one step, then come back.

The release carries 94 files: 47 payload files, each paired 1:1 with its own Sigstore bundle. No payload ships unsigned. You can check that a file came from our build pipeline without trusting us — the verification runs against a public transparency log, not against anything we control.

# download the artifact and its bundle, then:
cosign verify-blob \
  --bundle Armore-Edge-1.0.10-arm64.dmg.sigstore.json \
  --certificate-oidc-issuer https://token.actions.githubusercontent.com \
  --certificate-identity-regexp '^https://github.com/uniQ-Ventures/' \
  Armore-Edge-1.0.10-arm64.dmg

Verified OK

!

Two commands that will not work, so you do not waste time on them. gh attestation verify returns 404 against these files. And the top-level sha512 in a latest*.yml manifest names a different artifact than you may expect — match your own filename in the files: list.

Step 3

Install

The app on first launch, with a short introduction card centred over the
dimmed assistant screen. The card is headed Ask, your private AI, with
the line that everything here runs locally and your files stay on your
device unless you say so, and buttons to Skip or go Next through five
cards. — First launch. The app opens on a short tour whose first card states the whole proposition plainly — *“everything here runs locally — questions, answers, and your files stay on your device unless you say so.”* Five cards, and **Skip** is offered as an equal choice beside **Next**.

macOS is signed and notarised, so it installs normally.

!

Windows and Linux are not code-signed. SmartScreen will warn you — choose More info → Run anyway, or verify the bytes with the command above first. Updates are manual on Windows for the same reason: you install each new version the way you installed this one.

There is nothing to install. The command-line tool is a single static binary — make it executable and put it on your PATH.

chmod +x armore-darwin-arm64
mv armore-darwin-arm64 /usr/local/bin/armore
armore --help

!

On macOS the binary is not covered by the installer's notarisation — it is a separate download, so Gatekeeper may quarantine it on first run. The app's .dmg is signed and notarised; this file is not the same artifact.

Step 4

First run downloads a model

The app's This device screen on an 8 GB iMac. A Get started panel
recommends a 3B model for this hardware, explains the reasoning from
the machine's memory, cores and acceleration, notes which coding model
it does not recommend and why, and offers to download the recommended
model or choose another. — **On an 8 GB machine the app recommends a smaller model and says why** — reading the memory, cores and acceleration first, then naming the trade. It also volunteers what it would *not* use: a coding model marked *“not recommended — 0% measured … 0% verified solveRate on-device.”* **A product willing to tell you a model scores zero on your hardware is the thing to look for**; the alternative is finding out yourself.

The app's AI models settings screen. A This device panel reports the
machine's memory, core count, GPU and free disk. A Recommended for you
panel explains which models suit that hardware and offers buttons to
download a recommended chat model or vision model. A separate panel
offers to set up offline transcription. — Where the model comes from, in the app. It reads the machine first — memory, cores, GPU, free space — and recommends accordingly, stating plainly that *“downloading a model is a one-time network step”* and that questions are then answered *“right here on your device — no cloud model in the loop.”* **You choose and start the download; nothing is fetched until you do.**

Armore Edge runs a real language model on your own hardware. It is not bundled in the installer — the app fetches it on first launch, after asking you. This is the slow part, and it is worth knowing the shape of it before you start.

What	Measured
Model	Llama 3.1 8B Instruct (Q4_K_M) — third-party open weights we package; Armore did not train it
Size	4,920,739,232 bytes (~4.9 GB)
Active download	27 min 26 s on our connection
Realistic wall clock	~46 min including verification

!

There is no resume. It needs one unbroken stretch — if the connection drops at 90%, it starts again. Start it when you can leave the machine alone, and make sure you have the disk space, because a full disk surfaces as a raw error rather than a helpful one.

After this, inference is local and works offline. You can confirm that for yourself later with armore models capabilities, or by pulling your network cable and asking it something.

The command-line tool does not download a model for you. You point it at a .gguf file you already have, every time:

armore ask --json \
  --model ~/models/llama-3.1-8b-q8.gguf \
  "a question"

!

This is the biggest difference between the two surfaces. The app fetches and manages a model for you after asking; the command line assumes you have brought your own and names it on every call. Neither one reaches the other's model store.

Step 5

What you get

The app's assistant home. A prompt box sits above three suggested
questions about summarising a contract, recalling recent work, and
extracting totals from an invoice. Below, one card offers to finish
setting up cross-device search and another offers to bring a second
device into the workspace. — The assistant home, where you land after the tour. It opens with suggestions rather than an empty box, and the cards beneath it are the two optional next steps — neither is required to start asking questions.

The app's This device screen. A summary panel lists the device name,
workspace, handle, version and an On-device status badge. Below it a row
of tiles shows counts for paired devices, indexed files, conversations
and research reports, all zero on a fresh install, alongside the chat
model in use, the on-device data size, and a Network tile reading
Local-only with the note no web egress. — What a fresh install looks like in the app. The counters are all zero, the chat model is named, and the **Network** tile reads **Local-only — “no web egress”** before you have changed anything. The header carries the same claim as the rest of the product: *“No cloud sees your data.”*

Ten surfaces, in two areas:

Assistant — Ask, Research, Extract, Vision, Docs, Your files
Build & Act — Code, Actions, Workflows, Build

Plus four destinations in the rail: This device, Collaboration, Activity and Settings.

✓

Two cards you may see are prompts, not errors. “Finish setting up cross-device search” means a dedicated search model has not been downloaded yet, so asking across devices can come back empty even when the answer exists. “Add a device to your fleet” is optional — Edge is fully usable on one machine.

No dashboard — you ask the binary what it can do, and it answers from the build you actually have rather than from a spec:

$ armore models capabilities

That reports the backends compiled into this binary. It is the honest check before you assume a feature is present: the command-line guide lists what each of the twenty commands refuses to do, which is usually more informative than what it does.