A system for agentic LLM-powered data processing and ETL
Appears on
Quick read
Latest capture 2026-10-17 04:10
Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.
4 paths
Agent instructions and tool configuration found in this repository.
Agent instructions
Claude Code 3
139 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +378
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Get your documents ready for gen AI
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
ETL / ELT / Reverse ETL Framework powered by DuckDB, designed to seamlessly integrate and process data from diverse sources. It leverages Markdown as a configuration medium, where YAML blocks define metadata for each data source, and embedded SQL blocks specify the extraction, transformation, and loading logic.
Structured Outputs
Toolkit for linearizing PDFs for LLM datasets/training
DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！
