whatisgithub

What is codex-helper?

xqnode/codex-helper — explained in plain English

Analysis updated 2026-05-18

110RustAudience · developerComplexity · 2/5Setup · easy

In one sentence

A Rust system tray app for Windows and macOS that lets OpenAI's Codex coding tool use Chinese AI models like DeepSeek or GLM instead of OpenAI models.

Mindmap

mindmap
  root((repo))
    What it does
      Local proxy
      Model switching
      Format translation
    Tech stack
      Rust
      System tray app
    Use cases
      Switch AI models
      Manage API keys
      Use CLI mode
    Audience
      Developers
    Setup
      Auto-detects Codex
      Guided key setup

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Switch Codex Desktop between DeepSeek, Tongyi Qianwen, Moonshot, GLM, and other models.

USE CASE 2

Store and manage API keys for multiple providers in one encrypted settings panel.

USE CASE 3

Use a CLI mode to switch models without opening the tray app.

USE CASE 4

Cleanly uninstall and restore your original Codex configuration.

What is it built with?

Rust

How does it compare?

xqnode/codex-helperpolarityinc/zenithyarlabs/hyperspace-db
Stars110109113
LanguageRustRustRust
Setup difficultyeasymoderatehard
Complexity2/54/55/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

Auto-detects an existing Codex install and API key on first launch.

So what is it?

Codex Helper is a small system tray application for Windows and macOS, written in Rust, that lets you use OpenAI's Codex Desktop coding tool with Chinese AI models instead of OpenAI's own. Models you can switch to include DeepSeek, Tongyi Qianwen (from Alibaba), Moonshot, Zhipu GLM, and MiniMax, plus any OpenAI-compatible third-party endpoint. Switching happens from the tray icon menu, not through config files or a terminal. The tool works by running a local proxy on your machine at a fixed port. Codex is configured once to point at that proxy, and then Codex Helper forwards your requests to whichever model you have selected. It also handles the format difference between OpenAI's Responses API and the Chat Completions format that most Chinese providers use, so you do not have to think about that translation layer. Setup is meant to be minimal. On first launch the app detects whether Codex is already installed and auto-fills any existing API key it finds in your environment. A guided window appears if neither is present, with direct links to apply for keys from each supported provider. The settings panel lets you manage API keys (stored encrypted, never uploaded), set a startup preference, and back up or restore your configuration. A CLI mode mirrors every tray action for users who prefer the command line. The uninstaller restores your original Codex config from a backup and removes startup entries, leaving no leftovers. The application binary is under 10 MB and is expected to use less than 30 MB of memory at runtime. The project is primarily aimed at users who want cost-effective alternatives to OpenAI without editing configuration files or understanding how proxy routing works.

Copy-paste prompts

Prompt 1
Explain how this app translates between OpenAI's Responses API and Chat Completions format.
Prompt 2
Walk me through setting up an API key for a Chinese model provider in this app.
Prompt 3
How does the local proxy in this tool work with Codex Desktop?
Prompt 4
Show me the CLI commands that mirror the tray menu actions.

Frequently asked questions

What is codex-helper?

A Rust system tray app for Windows and macOS that lets OpenAI's Codex coding tool use Chinese AI models like DeepSeek or GLM instead of OpenAI models.

What language is codex-helper written in?

Mainly Rust. The stack also includes Rust.

How hard is codex-helper to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is codex-helper for?

Mainly developer.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.