lidge-jun/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 it solves

OpenCodex is a local proxy that allows users to use any Large Language Model (LLM) with tools that are normally locked to specific providers, such as Codex, Claude Code, Claude Desktop, and Grok Build. It removes the provider lock-in by translating the Codex Responses API into the format required by various LLM providers.

How it works

It acts as a lightweight translation layer between the client application and the AI provider. It supports over 40 built-in providers (including Anthropic, Google Gemini, xAI, DeepSeek, and Ollama) or any OpenAI-compatible endpoint. The tool includes a web dashboard for managing providers, models, and accounts. It also features a ChatGPT account pool to manage multiple accounts, handling quota-aware auto-switching and thread affinity to ensure conversations stay pinned to the same account.

Who it’s for

Developers and AI power users who want to use their preferred LLMs within the existing interfaces of Codex, Claude Code, or Grok Build, or those who want to manage multiple AI accounts to optimize quota usage.

Highlights

  • Universal Model Routing: Use 40+ providers with Codex, Claude Code, Claude Desktop, and Grok Build while keeping the native UI.
  • Account Pooling: Manage a pool of ChatGPT accounts with automatic quota-aware routing and failover.
  • Model Combos: Create virtual model IDs that distribute requests via failover or weighted round-robin.
  • Sub-agent Support: Route specific models to be used as sub-agents within the Codex interface.
  • Cros-Provider Capabilities: Adds web search and vision capabilities to non-OpenAI models via a sidecar over a ChatGPT login.
  • Easy Deployment: Available via npm, Docker Compose, or source install, with options for background service or on-demand shim.

Related

  • Project
    raine/claude-code-proxy

    A proxy that allows the Claude Code coding harness to use alternative LLM providers like OpenAI Codex, Kimi, Grok, and Cursor Agent by translating Anthropic API traffic.

  • Project
    icebear0828/codex-proxy

    Codex Proxy is a local service (desktop app, lightweight “no‑node” zip, or Docker container) that converts the Codex Desktop Responses API into standard OpenAI, Anthropic, Gemini, and Ollama endpoints. After logging in with a ChatGPT account, it issues a local API key; any client that understands the usual `/v1/chat/completions` or `/v1/messages` format can call Codex, with full support for streaming, function/tool calling, structured outputs, image generation, multi‑account rotation, and TLS fingerprint spoofing.

  • Project
    Mirrowel/LLM-API-Key-Proxy

    A self-hosted universal LLM API proxy that provides OpenAI and Anthropic compatible endpoints for multiple providers with built-in key rotation and failover.

  • Project
    xing61/zzz-api

    A unified API gateway providing stable access to OpenAI, Claude, Gemini, and other major LLMs for enterprises and developers without requiring foreign accounts.

  • Project
    chatanywhere/GPT_API_free

    A unified API gateway providing direct, proxy-free access to multiple frontier LLMs like GPT, DeepSeek, and Claude using a standardized OpenAI protocol.