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 specific API responses of these tools into a format that any chosen LLM provider (like Gemini, DeepSeek, Ollama, or Claude) can understand.

How it works

It acts as a lightweight translation layer between the AI application and the LLM provider. It translates the Responses API into streaming, tool calls, and reasoning tokens in both directions. Users can configure providers and models via a web dashboard or CLI, and the proxy then routes requests from the supported applications to the target LLM.

Who it’s for

Developers and power users who want to use their preferred LLMs (including local models via Ollama) within the specialized interfaces of Codex, Claude Code, Claude Desktop, or Grok Build.

Highlights

  • Universal Model Support: Connects 40+ built-in providers or any OpenAI-compatible endpoint to specific AI coding tools.
  • ChatGPT Account Pooling: Manages multiple accounts with quota-aware auto-switching and thread affinity to maintain conversation continuity.
  • ChatGPT Sidecars: Adds web search and vision capabilities to non-OpenAI models using a ChatGPT login.
  • Model Combos: Creates virtual model IDs that support failover or weighted round-robin routing across different providers.
  • Sub-agent Routing: Enables the use of routed models within the sub-agent pickers of supported tools.
  • Memory Management: Implements strict byte budgets and LRU caps for all long-lived caches to prevent memory leaks.

Related

  • Project
    raine/claude-code-proxy

    A local proxy that lets Claude Code use multiple LLM providers (Codex, Kimi, Grok, OpenCode Go, Cursor) by translating Anthropic‑style API calls, handling auth, routing, streaming and offering a TUI monitor.

  • Project
    router-for-me/CLIProxyAPI

    CLI Proxy API is an open‑source proxy server that presents a unified OpenAI‑compatible API for many LLM providers (OpenAI, Gemini, Claude, Grok, Kimi, Meta, etc.). It handles OAuth logins, multi‑account load‑balancing, streaming, function calls, and multimodal inputs, and offers optional dashboards for usage and cost tracking. Ideal for developers with multiple AI subscriptions who want a single local endpoint for their CLI tools.

  • Project
    Alishahryar1/free-claude-code

    Free Claude Code is a unified proxy that connects your favorite coding agents to over 60 AI providers, enabling seamless model switching, automatic fallback during outages, and significant token usage optimization.

  • Project
    icebear0828/codex-proxy

    Codex Proxy is a local service that converts Codex Desktop’s API into standard OpenAI/Anthropic/Gemini/Ollama endpoints, letting any AI‑coding client use Codex models. It offers multi‑account management, smart routing, TLS fingerprinting, Docker/desktop/npm installers, and supports image generation.

  • Project
    kaitranntt/ccs

    A multi-provider profile and runtime manager that allows users to switch between different AI providers, local models, and account contexts via a unified CLI and dashboard.