JSPM

make codex open!

npm install -g @bitkyc08/opencodex · ocx start · localhost:10100

English · 한국어 · 简体中文 · 📖 Full documentation →

Use Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Ollama, or any other LLM with Codex — without waiting for OpenAI to add support.

opencodex is a lightweight local proxy that translates Codex's Responses API into whatever your provider speaks. Streaming, tool calls, reasoning tokens, images — everything works, in both directions.

Codex CLI / App / SDK ──/v1/responses──▶ opencodex ──▶ Any provider
                                              │
              Anthropic · Google · xAI · Kimi · Ollama Cloud · Groq
              OpenRouter · Azure · DeepSeek · GLM · …and OpenAI itself

Supported platforms

Requires Bun 1.1+. All three platforms work natively (no WSL needed on Windows).

Quick start

# Install
npm install -g @bitkyc08/opencodex      # or: bun install -g @bitkyc08/opencodex

# Interactive setup (writes config + injects into Codex)
ocx init

# Start the proxy
ocx start

# Use Codex normally — it now routes through opencodex
codex "Write a hello world in Rust"

# macOS / Linux / WSL
curl -fsSL https://bun.sh/install | bash

# Windows (PowerShell)
powershell -c "irm bun.sh/install.ps1 | iex"

Add a provider

The fastest way to add a provider is through the web dashboard:

ocx gui

This opens the dashboard at http://localhost:10100. From there:

1. Click "Add Provider"
2. Pick from 40+ built-in providers — or enter a custom OpenAI-compatible endpoint
3. Paste your API key (or log in via OAuth for Anthropic, xAI, and Kimi)
4. Models are auto-discovered from the provider's /v1/models endpoint

Your new provider is ready to use immediately. No restart needed.

You can also add providers through ocx init (interactive CLI) or by editing ~/.opencodex/config.json directly.

Model routing

Target any configured provider and model using the provider/model syntax:

# Use Claude Opus through Anthropic
codex -m "anthropic/claude-opus-4-8" "Explain this stack trace"

# Use Gemini through Google
codex -m "google/gemini-3-pro" "Write unit tests for auth.ts"

# Use GLM through Ollama Cloud
codex -m "ollama-cloud/glm-5.2" "Write a SQL migration"

# Use a local model through Ollama
codex -m "ollama/llama3" "Refactor this function"

When you omit the provider/ prefix, opencodex routes to the default provider — or auto-matches based on the model name pattern (e.g., claude-* routes to Anthropic, gpt-* routes to OpenAI).

Routed models also appear in the Codex App model picker with per-model reasoning effort controls:

Highlights

• Use any LLM with Codex. 5 protocol adapters cover Anthropic Messages, Google Gemini, Azure, OpenAI Responses passthrough, and every OpenAI-compatible Chat Completions endpoint — that's 40+ providers out of the box.
• Log in once, skip the API key. OAuth support for xAI, Anthropic, and Kimi means you can authenticate with your existing account. Tokens auto-refresh. Or forward your codex login, paste an API key, or use ${ENV_VAR} references — your call.
• Works everywhere Codex does. Injects into Codex CLI, TUI, App, and SDK automatically. Routed models show up in Codex's model picker just like native ones.
• Delegate to the right model. Feature up to five routed or native models in Codex's subagent picker from the dashboard or config — route complex tasks to a reasoning model, fast tasks to a cheap one.
• Give any model superpowers. Non-OpenAI models get real web search and image understanding via a gpt-5.4-mini sidecar over your ChatGPT login.
• See what's happening. The web dashboard shows providers, OAuth status, model selection, and a live request log — no more guessing why a request failed.
• Runs in the background. Install as a system service (launchd / systemd / Task Scheduler) and forget about it. The proxy starts on boot and stays out of your way.
• Clean exit, zero residue. ocx stop (or the dashboard's Stop button) shuts down the proxy, stops the background service if one is installed, and restores Codex to its original configuration. Plain codex works exactly as it did before — no leftover config, no orphaned processes.

Providers & adapters

Plus DeepSeek, Groq, OpenRouter, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Portal, and more. See the full list with ocx init or in the provider docs.

CLI

ocx init                       # interactive setup
ocx start [--port 10100]       # start the proxy
ocx stop                       # stop + restore native Codex
ocx restore                    # restore without stopping (alias: ocx eject)
ocx sync                       # refresh models + re-inject into Codex
ocx codex-shim install         # auto-start the proxy whenever `codex` is launched
ocx status                     # is the proxy running?
ocx login <xai|anthropic|kimi> # OAuth login
ocx logout <provider>          # remove a stored login
ocx gui                        # open the web dashboard
ocx service <install|start|stop|status|uninstall>   # background service (launchd/systemd/schtasks)
ocx update                     # update opencodex to the latest published version

Configuration

Config lives at ~/.opencodex/config.json. Here's a typical multi-provider setup:

{
  "port": 10100,
  "defaultProvider": "anthropic",
  "providers": {
    "anthropic": {
      "adapter": "anthropic",
      "baseUrl": "https://api.anthropic.com",
      "authMode": "oauth",
      "defaultModel": "claude-sonnet-4-6"
    },
    "ollama-cloud": {
      "adapter": "openai-chat",
      "baseUrl": "https://ollama.com/v1",
      "apiKey": "${OLLAMA_API_KEY}",
      "defaultModel": "glm-5.2"
    }
  }
}

Local models work too. Point opencodex at any OpenAI-compatible server running on your machine:

{
  "port": 10100,
  "defaultProvider": "ollama",
  "providers": {
    "ollama": {
      "adapter": "openai-chat",
      "baseUrl": "http://localhost:11434/v1",
      "authMode": "key",
      "apiKey": "",
      "defaultModel": "llama3"
    },
    "vllm": {
      "adapter": "openai-chat",
      "baseUrl": "http://localhost:8000/v1",
      "authMode": "key",
      "apiKey": "",
      "defaultModel": "Qwen/Qwen3-32B"
    }
  }
}

WebSocket transport is off by default. Set "websockets": true only if you want Codex to advertise and use the Responses WebSocket path instead of HTTP/SSE.

See the Configuration reference for every field.

Documentation

The public docs — install, providers, routing, sidecars, Codex integration, Codex App model picker, and CLI/config reference — are built from docs-site/ and published to lidge-jun.github.io/opencodex.

Maintainer source-of-truth notes live under structure/. Historical investigations remain under docs/.

Development

git clone https://github.com/lidge-jun/opencodex.git
cd opencodex
bun install
bun run dev          # start the proxy in dev mode
bun x tsc --noEmit   # typecheck

See Contributing.

License

MIT