ai-agent

Ellmer

Call LLM APIs from R
611 stars137 forksRUpdated 8/17/2026100% free · open source
What it does

Ellmer allows you to call Large Language Model (LLM) APIs directly from R, enabling you to leverage AI capabilities in your data analysis and modeling workflows.

When to use it
  • When you need to integrate natural language processing tasks into your R projects
  • For generating text, summarizing content, or translating text as part of your data processing pipeline
  • To leverage pre-trained LLMs for tasks like text classification, sentiment analysis, or question-answering in your R applications
Ready-to-paste prompt
ellmer_predict("Write a product description for a new smartwatch.")
Heads up: You need to have an API key and secret from a supported LLM provider, such as OpenAI or Hugging Face, to use ellmer, and you must set these credentials using ellmer_api_key() and ellmer_api_secret() before making API calls
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/ellmer && curl -fsSL https://workflowstacks.com/api/skills/ellmer/claude-skill -o ~/.claude/skills/ellmer/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Ellmer works
Codeflow
Free to inspect

Ellmer is a large R project (~15k lines across 75 code files, plus 67 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Large codebase
~15k lines · 75 code files · ~2 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
R
No API keys detected
R 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
What's in each folder
R/Folder75 files
man/Folder68 files
vignettes/Folder45 files
pkgdown/Folder14 files
inst/Folder9 files
revdep/Folder5 files
data-raw/Folder4 files
tests/Tests — proof it works176 files
READMEHas testsDocumentedCI checksOther licenseUpdated this month
Quick Actions
Details
Creator
tidyverse
Language
R
Category
ai-agent
Published
8/27/2024

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.