microsoft-azure/pr_77/en/harness/codex.md

# Codex

Codex is OpenAI's coding agent. The CLI works from your terminal, where it can inspect a repository, edit files, and run commands with your approval.

![OpenAI Codex Landing](https://huggingface.co/datasets/huggingface/documentation-images/resolve/refs%2Fpr%2F653/microsoft-azure/harness/codex/thumbnail.png)

## Install the harness

On macOS or Linux, install the Codex CLI with:

```bash
curl -fsSL https://chatgpt.com/codex/install.sh | sh
```

On Windows, run:

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://chatgpt.com/codex/install.ps1 | iex"
```

You can also install Codex with npm or Homebrew.

## Connect the model

> [!TIP]
> This guide assumes that you already have a model running on Microsoft Foundry. If you do not, follow the [quickstart](../get-started/quickstart) and deploy one from the Foundry portal or with Python first.

Codex allows you to define custom profiles to connect to custom model providers through the Responses API.

For example, suppose you deploy Qwen3.8 27B on Microsoft Foundry in a project named `huggingface-demo`, you can create a custom profile at `~/.codex/microsoft-foundry.config.toml` with:

```toml
model = "qwen--qwen3-8-27b"
model_provider = "microsoft-foundry"
model_reasoning_effort = "medium"

[model_providers.microsoft-foundry]
name = "Microsoft Foundry"
base_url = "https://huggingface-demo.openai.azure.com/openai/v1"
env_key = "MICROSOFT_FOUNDRY_API_KEY"
wire_api = "responses"
```

The value of `model` must be the **deployment name**, which may differ from the model name shown in the catalog.

Set the API key in the same shell where you will run Codex:

```bash
export MICROSOFT_FOUNDRY_API_KEY="<API-KEY>"
```

For PowerShell, use:

```powershell
$env:MICROSOFT_FOUNDRY_API_KEY="<API-KEY>"
```

You can copy the key from Microsoft Foundry, or retrieve it with the Azure CLI:

```bash
az cognitiveservices account keys list \
  --subscription <SUBSCRIPTION-ID> \
  --resource-group <RESOURCE-GROUP> \
  --name <FOUNDRY-RESOURCE-NAME> \
  --query key1 \
  --output tsv
```

## Test it!

Finally, to test Codex with the open-model on Microsoft Foundry you can e.g., clone a repository and start `codex` with the previously created profile.

```bash
git clone https://github.com/huggingface/transformers.git
cd transformers/
codex --profile microsoft-foundry
```