LLMAgentR: Language Model Agents in R for AI Workflows and Research (original) (raw)
Provides modular, graph-based agents powered by large language models (LLMs) for intelligent task execution in R. Supports structured workflows for tasks such as forecasting, data visualization, feature engineering, data wrangling, data cleaning, 'SQL', code generation, weather reporting, and research-driven question answering. Each agent performs iterative reasoning: recommending steps, generating R code, executing, debugging, and explaining results. Includes built-in support for packages such as 'tidymodels', 'modeltime', 'plotly', 'ggplot2', and 'prophet'. Designed for analysts, developers, and teams building intelligent, reproducible AI workflows in R. Compatible with LLM providers such as 'OpenAI', 'Anthropic', 'Groq', and 'Ollama'. Inspired by the Python package 'langagent'.
| Version: | 0.3.0 |
|---|---|
| Depends: | R (≥ 4.1.0) |
| Imports: | plotly, stats, utils, DBI, RSQLite, dplyr, glue, httr, officer, purrr, timetk, pdftools, parsnip, recipes, workflows, rsample, modeltime.ensemble, modeltime, xml2 |
| Suggests: | testthat (≥ 3.0.0), roxygen2, jsonlite, magrittr, rlang, tidyr, ggplot2, usethis, prophet, forcats, kernlab, xgboost, xfun, modeltime.resample, tidymodels, tibble, lubridate, methods, tesseract, rvest, fastDummies, stringr |
| Published: | 2025-05-20 |
| DOI: | 10.32614/CRAN.package.LLMAgentR |
| Author: | Kwadwo Daddy Nyame Owusu Boakye [aut, cre] |
| Maintainer: | Kwadwo Daddy Nyame Owusu Boakye <kwadwo.owusuboakye at outlook.com> |
| BugReports: | https://github.com/knowusuboaky/LLMAgentR/issues |
| License: | MIT + file |
| URL: | https://github.com/knowusuboaky/LLMAgentR,https://knowusuboaky.github.io/LLMAgentR/ |
| NeedsCompilation: | no |
| Materials: | README, NEWS |
| CRAN checks: | LLMAgentR results |
Documentation:
Downloads:
Linking:
Please use the canonical formhttps://CRAN.R-project.org/package=LLMAgentRto link to this page.