pickfit

BrowseLocal AI tools

omarchy-cluster

Runs one local model across networked machines as one OpenAI-compatible endpoint.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • Runtimes: Python 3.9+
  • System packages: Avahi, dns-sd
  • Needs the network
  1. create venv ~/mlx and pip install mlx mlx-lm omarchy-cluster from git

    python3 -m venv ~/mlx && ~/mlx/bin/pip install --upgrade pip && ~/mlx/bin/pip install mlx mlx-lm git+https://github.com/joshuaswarren/omarchy-cluster.git
    
  2. symlink binary to ~/.local/bin and verify --help works

    mkdir -p ~/.local/bin && ln -sf ~/mlx/bin/omarchy-cluster ~/.local/bin/omarchy-cluster && omarchy-cluster --help
    

Check that it works

omarchy-cluster --version

The output should contain “0.3.2”.

First thing to try

omarchy-cluster discover

Run omarchy-cluster discover to find cluster nodes on your network.

Linux x86_64

You need first

  • Runtimes: Python 3.9+
  • System packages: Avahi, dns-sd
  • Needs the network
  1. Install omarchy-cluster via venv pip and expose on PATH

    python3 -m venv ~/.local/share/omarchy-cluster/venv && ~/.local/share/omarchy-cluster/venv/bin/pip install --quiet git+https://github.com/joshuaswarren/omarchy-cluster.git && ln -sf ~/.local/share/omarchy-cluster/venv/bin/omarchy-cluster ~/.local/bin/omarchy-cluster && ~/.local/bin/omarchy-cluster --help

Check that it works

omarchy-cluster --version

The output should contain “0.3.2”.

First thing to try

omarchy-cluster discover

Run omarchy-cluster discover to find cluster nodes on your network.

What it does

  • Run one local model across several networked machines
    Not tested
  • Serve the cluster as an OpenAI-compatible endpoint
    Not tested
  • Find nodes over mDNS and test routes between them
    Not shown working

How far pickfit got

macOS arm64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

Linux x86_64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

Good for

  • Serve a split model as one OpenAI-compatible endpoint on :8020
  • Find cluster nodes over mDNS
  • Measure every node pair to pin fastest route
  • Check model fit and print each node's layer cap
  • Split a model that does not fit on one machine across nodes

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

macOS arm64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 0.3.2

Differences the test machine hit

  • README: omarchy-cluster install-agent starts agent via launchd
    In the test: launchd Load failed: 5 in VM but agent still runs manually via ~/mlx/bin/omarchy-cluster agent; discovery still works

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.3.2

Differences the test machine hit

  • README: venv pip install && omarchy-cluster install-agent
    In the test: pip install plus symlink alone puts omarchy-cluster 0.3.2 on PATH and discover/status work; install-agent fails here with FileNotFoundError: systemctl

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.