Large Language Model tools for R

Author

Luis D. Verde Arregoitia

Published

April 24, 2026

Esta guía está disponible en español Leer en español
Busca el botón de idioma en la barra de navegación en el resto de la guía para cambiar de idioma en otras páginas.

Welcome

Screencaps from The Simpsons (Fox)

👋 Hello! This is an ongoing roundup of useful developments in the LLM/genAI space, with a specific focus on R.

Latest updates (April 2026):

13 new packages!

  • LLM agent orchestration for workflows with checkpoints and human-in-the-loop review (puppeteeR)
  • Skills and instruction files for R package–focused AI coding agents (pkgskills)
  • AST-based analysis of R code to manage agent context and dependencies (saber)
  • Text-based summaries and analysis tools for profvis output in terminal workflows (debrief)
  • Detection and suggested fixes messy data frames using LLMs (llmclean)
  • A lightweight, minimal-dependency LLM chat interface with multi-provider support and streaming (llm.api)
  • Integration with Goose AI for automation and data science project management (gooseR🦆)
  • Title/abstract screening support for systematic literature reviews (AIscreenR)
  • A context-aware multi-provider assistant for RStudio (including git) with a safety-first, approval-based design (ravel)
  • Production-grade AI Software Development Kit (SDK) for R with structured outputs, tool calling, and multi-agent orchestration (aisdk)
  • A lightweight interface to the OpenAI ChatGPT API in the console (gptr)
  • Wrappers for writing tests, translating code, refactoring, validating R code, and more using OpenAI models (TheOpenAIR)
  • AI-assisted qualitative coding for large datasets with audit trails, validations, and reproducibility support (quallmer)

For teaching purposes and to help me keep track of what’s happening, I’ve put together this draft listing of relevant LLM+R resources. This was initially a post on my blog from late 2024, but this book format should be easier to navigate. I will update the content periodically when new tools come out and/or when people bring them to my attention.

The field is very fast moving so providers, software names, APIs, and overall functions are subject to change. I’ll do my best to keep this guide updated and mention key changes and news.

The logos below link to each tool’s official site.

created with hexsession

Feel free to send feedback or to edit this content via pull requests.

About me

I am a mammal macroecologist and biodiversity data scientist. Check out my personal page for other content and more details.

Citation

If you use this resource, please cite it as:

Verde Arregoitia, L.D. (2026). Large Language Model tools for R. https://luisdva.github.io/llmsr-book. DOI: 10.5281/zenodo.19260391

BibTeX:

@book{verdearregoitia2026llmsr,
  author  = {Verde Arregoitia, Luis D.},
  title   = {Large Language Model tools for R},
  year    = {2026},
  url     = {https://luisdva.github.io/llmsr-book},
  doi     = {10.5281/zenodo.19260391}
}