DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run a local model on your GPU and open a coding agent on it with Omarchy Local AI

Install the plugin, set up once, start a model tested for your card, and open a coding agent on it.

Credentials. Setup turns on Sudoless Docker, which Omarchy describes as root-equivalent, so only enable it on a machine you trust.

Who it is forA developer on Omarchy with a supported GPU who wants a coding agent that runs on their own machine instead of a hosted service.

The problemSetting up a local model usually means finding weights that fit your card, configuring a server, and wiring an agent to it by hand.

The outcomeA validated model runs behind a keyed gateway on this machine, and a coding agent opens in your chosen folder already pointed at it.

What you need first

  • Omarchy with the Quattro shell and its bar
  • Docker, jq, curl, flock, sha256sum and sha1sum installed
  • A supported GPU, or an x86-64 CPU with AVX2 and enough RAM for the recipe
  • Enough free RAM and disk for the model you pick, as the panel lists them
  • Your Omarchy password for setup, since setup runs Omarchy's Sudoless Docker command, which is root-equivalent

Steps

  1. Run omarchy plugin add https://github.com/0xSero/omarchy-local-ai --enable.
  2. Open Local AI in the bar, click **Set up Local AI**, and enter your password when Omarchy asks.
  3. On the models tab, pick a model the panel lists for your card (or type its name) and click **Start**.
  4. Click the folder row to choose a project folder, pick an agent such as Claude Code or Codex, and click **Open**.

Prompt for your agent

Using the repo 0xSero/omarchy-local-ai on Omarchy, run setup, start the model <model-name> from the models tab, and open <agent> in the folder <folder-path>. Expected output: the agent opens in a terminal and answers from the local gateway. Verify that the model shows as running on the home tab before you open the agent.

Caveat. Model downloads can be large, so the first run may take much longer than setup itself, and the model you can run depends on your card and RAM.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page