One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.
RubyLLM is a Ruby gem that provides a unified interface for calling over 800 AI models across providers including Anthropic (Claude), OpenAI, Google Gemini, Mistral, DeepSeek, Ollama, and others through a single consistent API. Developers access Claude through the standard Anthropic API integration, configuring an API key and selecting any Claude model such as claude-sonnet-4 via the `RubyLLM.chat` interface or the `acts_as_chat` Rails model concern. The library supports chat, image analysis, PDF and document parsing, audio transcription via `RubyLLM.transcribe`, image generation via `RubyLLM.paint`, embeddings, content moderation, streaming responses, structured JSON output via `RubyLLM::Schema`, and tool use through a `RubyLLM::Tool` base class that lets Claude call arbitrary Ruby methods. Reusable agents with persistent instructions and tool sets are defined by subclassing `RubyLLM::Agent`. A Rails generator scaffolds database-backed chat persistence and a ready-to-use chat UI at `/chats`. The standout detail is that the entire framework ships with only three dependencies: Faraday, Zeitwerk, and Marcel. Ruby and Rails developers building AI-backed applications benefit most.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/crmne/ruby_llm && cp ruby_llm/*.md ~/.claude/agents/Subagents overview
What people ask about ruby_llm
What is crmne/ruby_llm?
+
crmne/ruby_llm is subagents for the Claude AI ecosystem. One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code. It has 4k GitHub stars and was last updated today.
How do I install ruby_llm?
+
You can install ruby_llm by cloning the repository (https://github.com/crmne/ruby_llm) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is crmne/ruby_llm safe to use?
+
Our security agent has analyzed crmne/ruby_llm and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains crmne/ruby_llm?
+
crmne/ruby_llm is maintained by crmne. The last recorded GitHub activity is from today, with 86 open issues.
Are there alternatives to ruby_llm?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy ruby_llm to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/crmne-ruby-llm)<a href="https://claudewave.com/repo/crmne-ruby-llm"><img src="https://claudewave.com/api/badge/crmne-ruby-llm" alt="Featured on ClaudeWave: crmne/ruby_llm" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.