DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to set up an OpenAI-compatible provider profile for Codex CLI with Agent Launcher

Add a provider profile, let the app check it with a real request, and keep native config in sync.

Credentials. API keys are stored as plaintext in ~/.agent-launcher/config.json and in CLI-native config files, so anyone with access to your local user account can read them.

Who it is forA developer who wants Codex CLI to use an OpenAI-compatible provider or relay instead of, or alongside, a ChatGPT account.

The problemEditing Codex config files, environment variables, and credentials by hand is error-prone, and a bad endpoint or key is hard to diagnose.

The outcomeA saved profile whose endpoint, credentials, model, and account status were verified by a minimal model request, with native config files written for you.

What you need first

  • A desktop computer running macOS, Windows, or Linux, with the Agent Launcher package downloaded from GitHub Releases
  • Existing coding-agent CLIs installed on the system, or permission to let Agent Launcher install missing ones in one click
  • An official account or provider API key for each agent you plan to run
  • For the source build use case only: Node.js 22 or newer and the pnpm version declared in package.json

Steps

  1. Open Agent Launcher and select Codex CLI in the agent list.
  2. Add a provider profile that uses an OpenAI-compatible provider, entering the endpoint, model, and API key.
  3. Run the connectivity check, which sends a real minimal model request to test the endpoint, credentials, model, network, and account status.
  4. Open the native config preview and confirm that secrets are masked and that the Codex config.toml and auth.json values look correct.
  5. Activate the profile and start a Codex session in your project folder.

Prompt for your agent

Using the Agent Launcher repo at https://github.com/agent-launch/agent-launcher, create an OpenAI-compatible provider profile named <profile-name> for Codex CLI with endpoint <endpoint-url> and model <model-name>, then run its connectivity check. Expected output: a pass or fail result for endpoint, credentials, model, network, and account status. Verify that the masked native config preview shows no plaintext key.

Caveat. Active API profiles override provider credentials for the launched process, so a profile you activate can change which account a session uses.

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