# Run your coding agent on your own hardware

> Point Claude Code or Codex at a model server running on your own machine, so the prompts never leave your network.

**Goal:** run an agent in crystl against a model you host yourself, instead of the frontier API.

## What you need

- A model server you can reach: Ollama, LM Studio, vLLM, or llama.cpp, on your Mac or on a box on your network.
- For **Claude Code**, an Anthropic-compatible server. Current LM Studio, vLLM, and llama.cpp releases provide a Messages endpoint directly; put a translation proxy such as [LiteLLM](https://docs.litellm.ai/) in front of Ollama. Codex, aider, opencode, and goose can use the Ollama or OpenAI-compatible connection directly.
- Configuring open-model connections, reading the reachability line, and running an endpoint by typing its agent name are **free on every plan**. Only `crystl shard create` from the CLI is a [Guild](/pricing/) control command.

## Steps

1. **Start the server.** For example, `ollama serve` on the machine with the GPU. For Claude Code, put a proxy in front of it:

   ```bash
   litellm --model ollama/qwen3-coder --port 4000
   ```

2. **Add an open-model connection.** Open **Settings → agents → providers & keys**, scroll past the hosted keys to open models, and add one:

   | Field | Value |
   |-------|-------|
   | Label | `closet-box` |
   | Kind | `anthropic-compatible` for the Claude Code proxy, `Ollama` or `OpenAI-compatible` for everything else |
   | Base URL | the address as seen from your Mac, for example `http://localhost:4000` |
   | Key | the proxy or server key if it has one, empty if it doesn't |
   | Start command | the CLI that calls it — `claude`, `codex`, `aider`. crystl fills this in for you |

   The start command is what turns the connection into an agent you can type. With `claude` and a label of `closet-box`, you get `claude@closet-box`.

3. **Check that it answers** before you spend a shard on it:

   ```bash
   crystl status
   ```

4. **Start the agent against the endpoint.** A shard that was already open keeps the old values, so it has to be a new one either way.

   With an **anthropic-compatible** endpoint (the LiteLLM proxy above), Claude Code gets a name you can type in any new shard — `claude@closet-box` — while plain `claude` keeps running hosted Claude.

   Codex reads its endpoint from launch flags rather than the environment, so it is started with `--local`:

   ```bash
   crystl shard create --gem myapp --agent codex --local closet-box \
     --prompt "fix the lint errors in src/"
   ```

   `--local` is checked before any shard opens. A label that doesn't exist, or is the wrong kind for that agent, gets you an error listing your endpoints instead of a worker that quietly ran somewhere else.

## What you'll see when it works

`crystl status` prints a reachability line next to the memory telemetry:

```
local model: closet-box http://100.x.y.z:11434 reachable (loaded: qwen3-coder · pulled: +5)
```

`loaded` means the model is in VRAM and will answer now. `pulled` means it's on disk and cold, and the first request can take minutes with no output while it loads. In a Claude Code shard, `echo $ANTHROPIC_BASE_URL` returns your slot's URL rather than nothing.

Two limits. A good local coder model is genuinely useful on mechanical work and will disappoint you on an architectural decision, so keep the hard calls with the strongest model you have. And a local worker under a hosted manager is not an air gap: the manager's whole conversation still goes to a hosted API.

## Go deeper

- [open models](/docs/open-models/) for every field, the model id shapes each CLI wants, and the troubleshooting list.
- [remote vantage](/docs/open-models/#remote-vantage-when-the-agent-is-somewhere-else) when the agent runs on the GPU box itself.
- [model sizes](/docs/model-sizes/) and [teach crystl your models once](/docs/scenario-teach-crystl-your-models/) to stop typing model ids.

---
Source: https://crystl.dev/docs/scenario-agent-on-your-own-hardware/