- RoboRuby
- Posts
- Ruby AI News - March 31st, 2025
Ruby AI News - March 31st, 2025
Model Context Protocol comes to Rails
Welcome to the second edition of the Ruby AI newsletter! In this edition we look a the top LLMs for Ruby code generation, a look at why Ruby is poised to thrive in the AI era, and the influx of Model Context Protocol (MCP) servers for working with Rails applications.
Contents
Top Stories
Top LLM Models for Ruby
Symflower published Deep dives from the DevQualityEval v1.0, evaluating the best LLM models across different programming languages. The top 3 models for Ruby are from OpenAI: o1-preview, GPT-4o, and o3-mini. Shared on X by Ahmed Benh.
The Future of AI is Ruby on Rails
Sean Goedecke published a piece on The future of AI is Ruby on Rails, discussing Ruby’s advantages with large language models.
Model Context Protocol comes to Rails
Stan Lo created a proof of concept Ruby MCP server powered by Ruby LSP to interact with the Cursor Agent.
Mario Alberto Chávez created a Rails MCP server gem containing a set of tools that allow Claude to interact directly with Rails projects.
Abdelkader Boudih created a minimal Rails API template for creating MCP servers with tool execution capabilities and examples.

Events
ArtificialRuby is hosting a meetup in NYC on April 9th, however there is currently a waitlist.
However, there may still be spots open to present:

Open Source Updates
Alex Rudall updated the ruby-openai gem to version 8.1, adding support for OpenAI’s vector store search endpoint.
Nate Berkopec released a helper utility for next-actionizing Todoist tasks, consisting of a set of command-line utilities that integrate with Todoist and OpenAI to help implement the Getting Things Done (GTD) methodology.
Carmine Paolino released RubyLLM 1.0.1 along with VCR support to better facilitate testing against different LLM providers.
Landon Gray announced Dashi: A Streamlit like Framework for Rubyists. Code examples, a demo video, and waitlist are available at DashiRB.com.
Miles Georgi created LLMBackedCommand, a gem to write a command without having to write an execute method.
Gill Abarbanel open sourced Cafeznik - Code2Prompt, a tool to automate loading local and remote code files into the clipboard to easily feed into LLMs.
Cirdes Henrique published Beyond Autocomplete: How Cursor AI is Helping Standardize and Write Ruby on Rails Code.
Giménez Silva Germán Alberto published an article Supercharging Trix Editor with Rails Generators and AI. This is the first in a three part series that covers Trix Genius, a Rails gem designed to bring AI-powered enhancements to the Trix Editor.
Donn Felker discusses how to use an llm-context.md file to make LLM assisted coding sessions a more productive.
Rich Steinmetz published How I use AI coding tools as a Rails dev, covering the tools and strategies tested integrating AI into a coding workflow.
DriftingRuby published an episode on Classification Models.
Jobs & Opportunities
That’s all for this edition! Be sure to reach out if you have any stories, content, jobs, or events you want featured in the newsletter.
Social Media