A reference implementation of a local-first AI-powered analytics assistant, demonstrating best practices for MCP integration, dbt semantic bridging, and extending data pipeline infrastructure using DuckDB, dlt, dbt, and Ibis.
1 file for Claude Code: local-ai-analyst CLAUDE.md — 2,076 tokens loaded in every session.
CLAUDE.md C 2,076 tok These files are sbdk-dev/local-ai-analyst's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.