The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

rlmstudio: Access and Control LM Studio

Run local Large Language Models (LLMs) over many texts from 'R' without sending data to a third party. A community-maintained wrapper for the 'LM Studio' command line interface and API that provides functions to manage the local daemon and server, download and load models, and score, label, or generate text at scale.

Version: 0.3.0
Depends: R (≥ 4.1.0)
Imports: cli, httr2, jsonlite, processx, utils
Suggests: httptest2, httpuv, knitr, mockery, rmarkdown, testthat (≥ 3.3.0), withr
Published: 2026-10-02
DOI: 10.32614/CRAN.package.rlmstudio
Author: Jeffrey Girard ORCID iD [aut, cph, cre]
Maintainer: Jeffrey Girard <me at jmgirard.com>
BugReports: https://github.com/jmgirard/rlmstudio/issues
License: MIT + file LICENSE
URL: https://jmgirard.github.io/rlmstudio/, https://github.com/jmgirard/rlmstudio
NeedsCompilation: no
Materials: README, NEWS
CRAN checks: rlmstudio results

Documentation:

Reference manual: rlmstudio.html , rlmstudio.pdf
Vignettes: Chat Options, Conversations, and Errors (source)
Getting Started with LM Studio in R (source)
Using LM Studio Without the Desktop App (source)
Text Analysis with LM Studio in R (source)

Downloads:

Package source: rlmstudio_0.3.0.tar.gz
Windows binaries: r-devel: rlmstudio_0.2.2.zip, r-release: rlmstudio_0.2.2.zip, r-oldrel: rlmstudio_0.3.0.zip
macOS binaries: r-release (arm64): rlmstudio_0.3.0.tgz, r-oldrel (arm64): rlmstudio_0.3.0.tgz, r-release (x86_64): rlmstudio_0.3.0.tgz, r-oldrel (x86_64): rlmstudio_0.3.0.tgz
Old sources: rlmstudio archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=rlmstudio to link to this page.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.