opencodex

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

What is opencodex?

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

Overview of opencodex

What it is

opencodex is a lightweight local proxy that translates OpenAI Codex's Responses API into the format required by various LLM providers. It supports streaming, tool calls, reasoning tokens, and images in both directions. It allows using models from providers such as Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Ollama, or any OpenAI-compatible endpoint with Codex CLI, Codex App, Codex SDK, Claude Code, Claude Desktop, and Grok Build. It can also manage a ChatGPT account pool for Codex authentication, including quota tracking and session routing.

Key features

  • Acts as a universal provider proxy for OpenAI Codex and Claude Code, enabling use of multiple LLMs with those tools.
  • Supports streaming, tool calls, reasoning tokens, and images bidirectionally.
  • Includes a web dashboard at localhost:10100 for configuring providers (40+ built-in or any OpenAI-compatible endpoint), selecting models, and managing accounts.
  • Can manage a ChatGPT account pool for Codex auth: add accounts, refresh quotas, and route new sessions to the lowest-usage healthy account while keeping existing threads pinned.
  • Available as a CLI tool (npm install) and a desktop app (beta) for macOS, Windows, and Linux.
  • Also deployable via Docker Compose with a digest-pinned, non-root build.

Use cases

  • Developers who want to use models other than OpenAI's default with Codex CLI, App, or SDK.
  • Users of Claude Code who wish to run it with different LLM backends.
  • Teams that need to manage multiple ChatGPT accounts for Codex authentication and quota distribution.
  • Anyone who wants to run Codex or Claude Code with local or third-party models via Ollama or other providers.

Getting started

bash npm install -g @bitkyc08/opencodex # Node 18+; the Bun runtime is bundled automatically ocx start # proxy + dashboard on localhost:10100 Open http://localhost:10100 in a browser to configure providers and accounts. Use ocx service to run in the background. For Docker Compose deployment, see the repository README.

License and pricing

The project is licensed under MIT and is open source. No pricing information is stated beyond the open source nature.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/lidge-junopencodex.svg)](https://yunodb.com/tools/lidge-junopencodex?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/lidge-junopencodex?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/lidge-junopencodex.svg" alt="Featured on YunoDB" height="20"></a>