hughminhphan/claudemix

32 stars · Last commit 2026-08-04

One Claude Code session, two subscriptions: Claude orchestrator + GPT executor subagents via a credential-clean loopback splitter

README preview

# claudemix

Run one Claude Code session that mixes models: a Claude model as the orchestrator, GPT subagents as executors. Your Claude subscription login is never proxied, stored, or re-signed; your OpenAI/Codex subscription powers the executor lanes.

```
Claude Code session
      |
      v
loopback splitter (127.0.0.1:8318, ~110 lines of Node you can read)
      |
      +-- model claude-* --> api.anthropic.com   (byte-for-byte passthrough, your own OAuth headers)
      +-- model gpt-*    --> CLIProxyAPI :8317   (your Codex OAuth, local API key)
```

## Why this shape

Claude Code's API endpoint is process-global, so per-agent routing needs a gateway in front. Existing mixed-model setups put the Claude subscription login inside the proxy too, which re-originates your Claude traffic under a spoofed client identity. This project does not do that: Anthropic-bound requests pass through untouched with the session's own credentials, which is the same base-URL gateway pattern Anthropic documents for enterprise LLM gateways. Only `gpt-*` requests are re-authed, with a local key, to a CLIProxyAPI instance that holds only your OpenAI/Codex OAuth.

## Quick start (agent setup)

View full repository on GitHub →