How I reduced AI coding costs by 94% — and built a CLI to do it automatically

Every time you ask Claude or ChatGPT about your code, it reads everything. Your entire codebase. Every single query. On a 44-file Python project that's 41,160 tokens per query. At GPT-4o prices ($2.50/1M tokens) - $0.10 every time you ask a question. At 50 queries a day,that's $147/month. Per developer. I got tired of this and built. What it does Kodara scans your repo once, builds a dependency graph and architectural memory, then returns only the 2-8 files actually relevant to your question.