Tuesday, October 7, 2025

How to quickly onboard a programmer to a project - Chatgpt Codex vs. Gemini CLI

How to quickly onboard a programmer to a project

many years ago I would worked with https://doxygen.nl/ to document the code but today the easy way will be using Chatgpt Codex or Gemini CLI:

Lets look the differences between the tools:

AreaGemini CLIChatGPT Codex CLI
Vendor / modelGoogle, Gemini 2.5 ProOpenAI, GPT-5 / GPT-5-Codex
Installnpm i -g @google/gemini-cli or brew install gemini-clinpm i -g @openai/codex or brew install codex
AuthGoogle login or Gemini/Vertex API keySign in with ChatGPT (Plus/Pro/Team/Enterprise/Edu) or API key
LicenseApache-2.0, open sourceApache-2.0, open source
OSmacOS, Linux, WindowsmacOS, Linux; Windows via WSL (experimental)
Core behaviorTerminal AI agent with ReAct loop; built-in tools and MCP serversLocal coding agent that reads/edits files and runs commands; MCP support; approval modes
Web / groundingBuilt-in Google Search grounding and web fetchInternet access available in Codex Cloud; CLI supports MCP and can delegate
Context / quotasFree tier includes Gemini 2.5 Pro with 1M-token context and ~60 RPM / 1,000 req/day during previewUses GPT-5 by default; switchable to GPT-5-Codex; plan-based access via ChatGPT
MultimodalImages/video via Imagen/Veo integrationsAccepts image inputs; IDE and cloud variants can execute and draft PRs
IntegrationsVS Code (Code Assist agent mode), GitHub Actions, Zed (ACP)IDE extensions (VS Code, Cursor, Windsurf), Codex Cloud



Bottom line:

  • Pick Gemini CLI if you want generous free usage, built-in Google Search grounding, and easy MCP-based extensions. blog.google

  • Pick Codex CLI if you want tighter ChatGPT + IDE integration, fine-grained local approvals, and GPT-5-Codex for deep, agentic coding. developers.openai.com



Do it from PowerShell in that folder.

  1. Install and sign in

npm install -g @openai/codex # installs Codex CLI codex login # OAuth with your ChatGPT account


  1. Work in c:\code\

Set-Location c:\code codex # starts an interactive session scoped to this directory

No comments:

Post a Comment

The Engine and The Network: How NVIDIA's New Hardware Is Powering the AI Future and 6G

  The Engine and The Network: How NVIDIA's New Hardware Is Powering the AI Future and 6G The era of simply training bigger AI models is ...