Codex

Overview

OpenAI's terminal agent. It talks the OpenAI API natively, so LIBRA is a drop-in.

You need a LIBRA API key (libra_sk_...) from the console (API keys > Create key), and the base URL https://<your-host>/v1.

Installation

1. npm install -g @openai/codex

Configure LIBRA

~/.codex/config.toml:

model = "libra/smart"
model_provider = "libra"

[model_providers.libra]
name = "LIBRA"
base_url = "https://<your-host>/v1"
env_key = "LIBRA_API_KEY"
wire_api = "chat"

Then export LIBRA_API_KEY=libra_sk_....

Quick start (up and running in 5 minutes)

1. Write the config, export the key.
2. Run codex in a project.
3. Ask "Siapa kamu?" to verify.

FAQ

• 404 / timeout? The base URL is missing /v1 or has an extra /chat/completions. Use exactly https://<your-host>/v1.
• Model not found? Model ids are case-sensitive and must match the console Models page, e.g. libra/smart or asix-deepseek-v4/deepseek-v4-flash.
• 401? The key is wrong, disabled or expired. 402? Your organization balance is Rp 0; see Credits.
• 403 model_not_allowed? The key's guardrails block that model. Ask your workspace Admin or pick another model.