# AI use cases for Omarchy Local AI (0xSero/omarchy-local-ai)

Repo: [0xSero/omarchy-local-ai](https://github.com/0xSero/omarchy-local-ai) | Use cases: 3 | Page: https://dedupedai.com/use-cases/0xsero-omarchy-local-ai/

Local AI is an Omarchy plugin that runs a validated local model on your own GPU or CPU in Docker and opens coding agents on it.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Run a local model on your GPU and open a coding agent on it: https://dedupedai.com/use-cases/0xsero-omarchy-local-ai/run-local-model-with-coding-agent/
- Share a running local model with your tailnet: https://dedupedai.com/use-cases/0xsero-omarchy-local-ai/share-running-model-on-tailnet/
- Call a running local model from your own scripts: https://dedupedai.com/use-cases/0xsero-omarchy-local-ai/call-local-model-from-own-scripts/

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

Repo: [0xSero/omarchy-local-ai](https://github.com/0xSero/omarchy-local-ai) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README

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

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

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

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

### 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 to paste into your agent

```text
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.

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

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/0xsero-omarchy-local-ai/run-local-model-with-coding-agent/

## How to share a running local model with your tailnet with Omarchy Local AI

Repo: [0xSero/omarchy-local-ai](https://github.com/0xSero/omarchy-local-ai) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Expose a running model to other devices on your Tailscale tailnet, still behind the gateway key.

**Who it is for:** A small team or a person with several devices on one tailnet who wants one machine to serve a local model to the others.

**The problem:** A model running on one machine is only useful on that machine unless it can be reached from your other devices, and exposing it carelessly is risky.

**The outcome:** A running model is reachable on your tailnet through tailscale serve, still requiring the gateway key, and you can stop sharing from its page.

### Steps

1. Make sure Tailscale is running and logged in, and that your account is Tailscale's operator (Omarchy's Tailscale install sets this).
2. Start a model from the models tab so it is running.
3. On the running model's page, click share to share it on your tailnet.
4. To remove the share, click **Stop sharing** on the model's page.

### Prompt to paste into your agent

```text
Using the repo 0xSero/omarchy-local-ai, share the running model <model-name> on the tailnet and confirm the share is active. Expected output: the model's page shows it as shared and another device on the tailnet can reach it with the gateway key. Verify by checking that the share is listed on the model's page, then stop sharing and confirm it is removed.
```

### Caveat

Sharing needs Tailscale running and logged in with the right operator, and if another account is the operator you must ask that account to manage sharing.

Risk, credentials: Anyone on your tailnet who has the gateway key can use the shared model, so give the key only to people you trust.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/0xsero-omarchy-local-ai/share-running-model-on-tailnet/

## How to call a running local model from your own scripts with Omarchy Local AI

Repo: [0xSero/omarchy-local-ai](https://github.com/0xSero/omarchy-local-ai) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Send OpenAI-compatible requests to a running model's gateway from your own code.

**Who it is for:** A developer who already has scripts or tools that use the OpenAI API and wants them to run against a model on their own machine.

**The problem:** Existing tools expect an OpenAI-style endpoint, and pointing them at a local model normally takes custom wiring for the address and key.

**The outcome:** Your scripts send requests to the model's gateway on this machine with the key, and get answers back from the local model.

### Steps

1. Start a model with the panel, or run `bin/omarchy-local-ai run qwen38-27b-exl3-3bpw-rtx3090-sglang-tp1 nvidia:0` using a recipe your machine supports. (inferred, check the README)
2. Open the model's page and copy its address under **this machine**; the address is hidden until you click it.
3. Read the key from `~/.local/state/omarchy/local-ai/gateway.key`.
4. Send OpenAI-compatible requests to the gateway address with the key, and check that you get an answer.

### Prompt to paste into your agent

```text
Using the repo 0xSero/omarchy-local-ai, start a validated model and send one OpenAI-compatible chat request from <script-path> to its gateway using the key in gateway.key. Expected output: a text reply from the local model. Verify that a request without the key is refused.
```

### Caveat

The README says the key should go only to the gateway address on the model's Docker network, so calls from outside this machine will not reach it.

Risk, credentials: The gateway key is the only protection on the gateway, so send it only to the gateway address and never paste it into shared code.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/0xsero-omarchy-local-ai/call-local-model-from-own-scripts/