Hi 👋
We've built this CLI because I was tired of watching my API costs spiral while working on large-scale industrial projects. Most tools send way more context than necessary, leading to "token bloat" and slower response times.
The problem: High token consumption isn't just expensive; it hits context limits faster, making it harder to work on complex codebases.
Our approach: We developed a specialized filtering logic that isolates only the essential code fragments needed for the task. The result? A 90% reduction in token consumption without losing the accuracy of the output.
I’d love to hear your thoughts on how this fits into your workflow. I'll be here all day to answer questions!
Replies
Archimyst