Connect Codex
Codex is connected as a custom model provider. How much Guardrail can do depends on how Codex is signed in, and it detects that per request.
Connect
guardrail connect codexThis adds a model provider pointing at http://localhost:4000/openai/v1 to your ~/.codex/config.toml, preserving the file’s permissions and leaving your other settings untouched. Restart Codex afterwards.
Two login modes
| Signed in with | What Guardrail does |
|---|---|
| An OpenAI API key | API-key requests are proxied and checked against your policies. Pre-send blocking: Supported. |
| A ChatGPT subscription | Subscription traffic is not proxied. Visibility does not block requests or guarantee remaining quota. You get visibility, not enforcement. |
Nothing needs configuring for this: the mode is detected from the credentials on each request.
Check it worked
guardrail status
guardrail doctorRun a Codex prompt and confirm a session shows up in the dashboard with codex as its tool.
Disconnect
guardrail disconnect codexCursor is coming. Cursor routes model calls through its own cloud, so it is metered differently from the tools above: support is in progress through Cursor Hooks, which give per-session activity metering and enforcement. See the supported tools for what ships today.
Documentation review: 2026-09-11. Integration mode matters; minimum binary versions are not specified for every guide. Run guardrail doctor to inspect your installation.
Website changes and known limitations