<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CRAN on cornball.ai</title><link>https://cornball.ai/tags/cran/</link><description>Recent content in CRAN on cornball.ai</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>2024</copyright><lastBuildDate>Thu, 23 Apr 2026 17:09:44 -0500</lastBuildDate><atom:link href="https://cornball.ai/tags/cran/index.xml" rel="self" type="application/rss+xml"/><item><title>R as CLI Agent Harness</title><link>https://cornball.ai/posts/r-as-agent-runtime/</link><pubDate>Thu, 23 Apr 2026 00:00:00 +0000</pubDate><guid>https://cornball.ai/posts/r-as-agent-runtime/</guid><description>One line:
1corteza::chat() That starts an AI agent in your R console. It can read files, run shell commands, query git, search the web (with a free Tavily API key). And because it&amp;rsquo;s running in your R session, it can see your data frames, your fitted models, your loaded packages. No subprocess, no serialization boundary. It evals R code directly in .GlobalEnv.
When you want to check its work, /r df drops you back to regular R.</description></item></channel></rss>