Kombai indexes your codebase to understand your team’s specific tech stack, coding patterns, and component structure. This helps Kombai to generate code that matches your conventions and fits perfectly into the existing codebase.
Kombai indexes your existing components to reuse them in generated code, rather than creating duplicates from scratch. By indexing these components, Kombai learns the function of each component and intelligently reuses them in the generated code as needed.
When you use Kombai in a repository for the first time, the indexing process runs automatically to detect the tech stack in use. Kombai then shows a Proposed tech stack box that groups detected technologies by category. For example, React under Project Type, shadcn under Component Library, and Redux Toolkit under State Management.
If your project has changed significantly since the last time you used Kombai in this repo (for example, major architectural changes or a tech stack migration), the initial indexing may no longer be accurate. In those cases, ask Kombai to scan the codebase again to find the updated tech stack. Kombai will rescan the repository and show the Proposed tech stack again based on what it detects.
Kombai actively searches your repository to find the files most relevant to the task you assign. By reading your files, it builds a deeper understanding of your specific component structure and coding patterns. This allows Kombai to reuse existing logic and generate new code that follows the same standards.Under the hood, Kombai uses tools like grep, list directory, and read to access relevant code.
