Codedict – a no-AI code index that cut my Claude Code tokens by 63%

Codedict is a local, no-AI index that parses a project once with tree-sitter and stores functions, classes, routes, SQL tables and call relationships in a SQLite file, then hands relevant results to the AI alongside the question via a Claude Code hook. In a benchmark of 12 real sessions per side, it reported a 63% token reduction (4,543,176 to 1,666,033), 75% fewer turns (138 to 34), a 26% cost drop (US$5.76 to US$4.27) and 12/12 correct answers on both sides. It supports Python, JavaScript, TypeScript/TSX, C#, Java, Go, SQL/T-SQL and Razor/Blazor, and can also connect to other AIs through an MCP server or RAG mode.