been using cursor heavily but it still loses context on larger codebases sometimes. does this index the entire project locally or just active files? curious about the memory footprint.
As far as I understood, it creates an AST from the whole project and stores it in a sqlite db. Not just the active files. Tries to be a bridge between file system operations of llm models and the disk.
tho, I don't think this will help on context-wise persistence. This is basically a AST wrapper around io operations on disk.
been using cursor heavily but it still loses context on larger codebases sometimes. does this index the entire project locally or just active files? curious about the memory footprint.
As far as I understood, it creates an AST from the whole project and stores it in a sqlite db. Not just the active files. Tries to be a bridge between file system operations of llm models and the disk.
tho, I don't think this will help on context-wise persistence. This is basically a AST wrapper around io operations on disk.