Question 1

How much does GitDebug cost?

Accepted Answer

Nothing. GitDebug itself is free forever. You bring your own OpenAI API key during onboarding and only pay OpenAI for the tokens your analyses consume. No platform subscription, no trial expiry, no credit card required.

Question 2

Why bring my own OpenAI API key?

Accepted Answer

It keeps GitDebug free and gives you direct control: you set spend limits in your OpenAI account, see exact usage in their dashboard, and can rotate or revoke the key any time from GitDebug Settings.

Question 3

Is my code stored or used for AI training?

Accepted Answer

No. Code snippets are sent only to OpenAI for analysis using your own key. GitDebug retains only the results (issues, summaries, scores) needed to render the dashboard. Your code is never used for AI model training under OpenAI's enterprise data terms.

Question 4

Which programming languages does GitDebug support?

Accepted Answer

60+ programming languages auto-detected per file. Includes TypeScript, JavaScript, Python, Go, Rust, Java, C#, C/C++, Ruby, PHP, Swift, Kotlin, Scala, Dart, Solidity, SQL, GraphQL, Bash, PowerShell, Lua, Elixir, Haskell, R, Julia, Terraform, Dockerfile, YAML, Vue, Svelte, and more.

Question 5

How long does a code review take?

Accepted Answer

A typical PR analysis completes in 25–35 seconds end-to-end. Cached prompts return instantly with zero additional token spend.

Question 6

Can I use GitDebug with private repositories?

Accepted Answer

Yes. GitDebug uses standard GitHub OAuth with read-only repository access. You pick exactly which repos to monitor and can revoke access from GitHub at any time.

Question 7

What scanners does GitDebug run on every PR?

Accepted Answer

Six layers per analysis: bug detection (logic errors, null pointers, race conditions), security scanning (OWASP Top 10 with CWE references), dependency CVE audit (via GitHub Advisory Database), secret leak detection, performance analysis (O(n²), N+1, memory leaks), and code quality scoring (cyclomatic complexity, duplication, SOLID violations). Each PR also gets an AI summary with merge recommendation.