Skip to main content

Models Used

Kodus uses the following language models for code analysis:
  • GPT-4o and derivatives (OpenAI)
  • Gemini 1.5 Pro and derivatives (Google)
  • Claude 3.5 Sonnet and derivatives (Anthropic)

Data Handling

Your code is processed temporarily and never used for training:
  • Data retained only during the review session
  • Immediately discarded after completion
  • Never used to train or improve models
  • Privacy maintained per provider agreements

Terms of Use for Each Model

Security Measures

  • Encryption: Data encrypted in transit and at rest
  • Data Isolation: Models don’t store or retain data after processing
  • Controlled Access: Strict access controls for authorized personnel only (see Workspace Roles)
  • Regular Audits: Periodic security audits for compliance
  • Security Updates: Regular patches and updates
Questions? Contact our support team or join Discord.