Use ChatGPT sign-in with n8n. Keep every credential where it belongs.
Relmio helps self-hosted n8n use models available through your own
ChatGPT/Codex sign-in. It installs an unofficial openai-oauth sidecar on the
same private Docker network as n8n. The bridge has no host port.
Need the supported OpenAI API instead? Relmio can set up a separate local
/v1 endpoint backed by your OpenAI Platform API key.
ChatGPT sign-in is not an OpenAI Platform API key. Relmio keeps those paths separate.
On macOS, Linux, WSL, or Git Bash:
npx --yes --ignore-scripts relmio@latestThe command opens a private browser wizard on 127.0.0.1. Pick an option,
review exactly what it will create, then confirm the install.
Choose Existing n8n model bridge.
- Sign in with your own ChatGPT/Codex account.
- Select the running n8n container and its private Docker network.
- Review and install the sidecar.
- In n8n, use
http://n8n-openai-oauth:10531/v1with the placeholder API keylocal-only.
Relmio does not edit, restart, rebuild, or expose n8n. The bridge is unofficial, private, experimental, and policy-uncertain. Check the rules that apply to your account before using it.
Choose New local n8n + ngrok. Relmio creates a separate n8n stack and walks you through the ngrok domain, token, and Basic Auth fields. Only the new n8n route is public. Its model bridge, Code Sandbox, and optional SearXNG stay off the host network.
Choose OpenAI API and enter your own Platform API key. Platform usage is billed separately from ChatGPT. Relmio stores the key in its private local service and gives your app a different local credential.
Choose n8n AI Assistant tools in the local browser wizard to add Code Sandbox beside an existing n8n container. SearXNG web search is optional and off by default. Relmio shows the sandbox key and n8n settings once. It does not change or restart n8n.
The Assistant model provider still needs its own supported credential. Enter your Platform API key directly in n8n. The privileged local runner is for development and testing; n8n recommends Daytona for production.
The Codex App Server and Codex Chat Adapter options use the official Codex device-code sign-in. The ChatGPT credential stays inside the isolated Codex container. These experimental routes are for trusted local apps and development backends, not browsers or public servers.
ChatGPT/Codex sign-in tokens expire. The official Codex client refreshes them automatically during active use before they expire, so active sessions usually continue without another browser login. Official OpenAI documentation does not publish a fixed 10-day lifetime; do not plan around one. This provider credential is separate from Relmio's local capability, which remains valid until you rotate it.
- Docker is not running. Start Docker Desktop or Docker Engine, then open a fresh wizard session.
- Authentication fails. Close old sign-in tabs and use the newest local URL printed by the active Relmio terminal.
- Local image build failed. Check Docker, disk space, and registry access.
- Getting started
- Local endpoints and n8n bridge
- New local n8n + ngrok
- VPS and n8n
- n8n AI Assistant
- Security and policy notes
- Reference
- Changelog
Relmio is free to use. If it helped you, you can buy me a coffee.
Relmio is an unofficial, community-maintained project. It is not affiliated with, endorsed by, or sponsored by OpenAI.
Treat ChatGPT/Codex credentials like passwords. Use only your own account. Do not pool, share, forward, or sell access tokens. Any request made with those credentials must be authorized by the account owner.
You are responsible for following OpenAI's Terms of Use, Usage Policies, and any other agreement that applies to your account.
Warning
Do not bypass rate limits, restrictions, or safeguards.
Relmio is provided as-is without warranties. OpenAI or an upstream service may change or discontinue access at any time. You accept the risks of using this experimental community project.