OpenAI Codex Provider
Monitor and analyze your OpenAI Codex coding sessions with GuideMode.
What is OpenAI Codex?
Section titled “What is OpenAI Codex?”OpenAI Codex is the AI model behind GitHub Copilot, available through the OpenAI API for:
- Code completion - Intelligent code suggestions
- Code generation - Create code from descriptions
- Code translation - Convert between languages
- Bug fixing - Automated error detection and fixes
Requirements
Section titled “Requirements”OpenAI API Access
Section titled “OpenAI API Access”You need:
- OpenAI Account - Sign up at platform.openai.com
- API Key - Generate from your OpenAI dashboard
- Codex CLI/Integration - Tool that uses Codex
Install Codex CLI
Section titled “Install Codex CLI”# Example installation (varies by tool)npm install -g openai-codex-cli
# Or use a specific Codex integrationConfiguration
Section titled “Configuration”Configure your Codex tool with OpenAI API key:
# Set environment variableexport OPENAI_API_KEY=your_api_key
# Or configure via tool-specific configcodex config set-key your_api_keyFile Locations
Section titled “File Locations”Codex integrations typically store data at:
macOS & Linux
Section titled “macOS & Linux”~/.codex/├── config.toml├── sessions/│ └── session-id.json└── projects/ └── project-data/Windows
Section titled “Windows”%USERPROFILE%\.codex\└── ... (same structure)Setting up capture
Section titled “Setting up capture”Install the CLI and run setup:
npm install -g guidemodeguidemode setupCodex sessions are read from ~/.codex and converted to GuideMode’s canonical format,
the same one Claude Code sessions use, so the analytics are identical either way.
Control which repositories sync with guidemode enable / guidemode disable, or set a
deny-by-default policy at setup. See Controlling what syncs.
Session Detection
Section titled “Session Detection”What Gets Captured
Section titled “What Gets Captured”Codex sessions track:
- Prompts: Code generation requests
- Completions: Generated code
- Context: Surrounding code and files
- Model: Which Codex model was used
- Tokens: API usage
Metrics
Section titled “Metrics”- Token consumption
- Completion quality
- Response time
- Cost tracking
