data2prompt
An open-source CLI that helps data scientists, analysts, and AI builders package repositories, CSVs, and notebooks into prompts or context bundles for LLM workflows.
Tool overview
If your goal is to feed data-heavy project materials into an LLM more cleanly, data2prompt looks worth trying; based on current evidence, though, it should be treated as a niche open-source utility rather than a broadly validated standard tool. That adoption judgment comes mainly from the official GitHub positioning. Heat proof is weak: only a small number of X mentions with low engagement, which shows awareness, not maturity or reliability.
Its practical role is not model training, not a RAG platform, and not a chat app that analyzes CSVs for you. A better comparison is a repo-to-prompt or context-packaging CLI for data-science projects. The GitHub repo explicitly says it compiles data-heavy projects into prompt-ready packages, and the social mention specifically highlights CSV and ipynb-style files as useful inputs before handing them to an attachment-reading agent. In other words, it prepares context; it does not produce the final analysis by itself.
On cost and setup, the evidence only supports that it is an open-source CLI. That conservatively suggests the software itself is likely self-runnable, but this is not the same as an official zero-cost promise.