Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.kodus.io/llms.txt

Use this file to discover all available pages before exploring further.

​
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

​
Self-hosted telemetry

If you run Kodus self-hosted, each instance sends one anonymous daily heartbeat to telemetry.kodus.io with aggregated counters and runtime metadata — never code, identities, or anything that could trace back to your users. You can inspect the exact payload with yarn telemetry:preview or disable it with KODUS_TELEMETRY_DISABLED=true. Full schema, retention policy, and source code links are documented in Anonymous Telemetry. Questions? Contact our support team or join Discord.