Progress will not be saved. This browser is blocking storage (often private browsing). You can still learn, but closing the tab loses your progress.
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
- Stars
- 18,696
- +7 days
- —
- Forks
- 1,540
- Language
- TypeScript
- License
- MIT
- Last push
- 21 Nov 2026
Summary
Summary written by AI from the README; it may be imprecise.This local gateway lets developers route requests from coding tools like Claude Code and Codex to over 40 model providers, including Gemini, Grok, DeepSeek, and local Ollama instances. It translates between OpenAI Responses, Chat Completions, and Anthropic Messages API formats while preserving streaming, tool calls, and reasoning. Developers can configure model failover combos, account pools, and routing through a web dashboard or CLI.
Use it when
- Route Claude Code or Codex traffic to alternative providers like Gemini, DeepSeek, or local Ollama models
- Set up failover combos or round-robin load balancing across multiple LLM providers and API keys
- Manage ChatGPT account pools with quota-aware routing and automatic account switching
Install
npm install -g --allow-scripts=bun @bitkyc08/opencodexCommands quoted from the repo's README. Read the README before running them.
Needs a token or API key.
Stars over 90 days
Collecting: 2 of 90 days so far. The chart appears after 7 days.