# crmne/ruby_llm

One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.

Repository: https://github.com/crmne/ruby_llm
Canonical: https://ross.abutalabs.com/products/ruby_llm
Homepage: https://rubyllm.com/
Language: Ruby
License: MIT
License Family: permissive
Topics: llm, ruby, ai, anthropic, chatgpt, claude, embeddings, gemini, image-generation, openai, rails, deepseek, mistral, ollama, openrouter, perplexity, vertex-ai, gpustack, xai, agents
Last push: 2026-08-26T22:14:40+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 87, longevity 41
- inputs: {"age_days": 580, "days_push": 7, "days_rel": 85, "gap_med": 5.0, "n_releases_24m": 35}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4322, forks 487 (observed 2026-08-28T04:08:41.946944+00:00)

## What it is
RubyLLM is a Ruby framework providing a unified, expressive interface to all major AI providers (OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible API). It supports chat, streaming, tool calling, image/video generation, embeddings, transcription, moderation, RAG, and agentic workflows with Rails integration.

## Use cases
- build a chatbot in Ruby with one API across providers
- switch LLM providers without rewriting code
- add AI chat features to a Rails app with database-backed conversations
- analyze images, PDFs, audio, and video with multimodal models
- generate images from text prompts
- create embeddings for search or RAG
- let the AI call Ruby code via tools
- stream LLM responses in real time

## When to choose
- you're building AI features in Ruby or Rails
- you want one consistent interface across multiple LLM providers
- you need chat, tools, RAG, and multimodal support in a single gem
- you want minimal dependencies and Rails-friendly persistence generators

## When to avoid
- your stack is Python, Node, or another non-Ruby language
- you need provider-specific features not exposed by the unified API
- you need a standalone inference server rather than a client library

## Facets
- artifact type: framework
- maturity: active
- function: llm-inference, agent-framework, rag, chatbot, sdk, http-client, image-processing, speech-recognition
- domain: large-language-models, artificial-intelligence, chatbots, web-development, developer-tools
- platform: ruby, cross-platform
- tags: multi-provider, openai, anthropic, gemini, ollama, streaming, tools, multimodal, image-generation, embeddings, rails-integration, ai-agents, retrieval-augmented-generation, rails

## Member repositories
- crmne/ruby_llm (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:41.946944+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:42.993285+00:00, confidence not recorded.
  - readme: https://github.com/crmne/ruby_llm (fetched 2026-08-28T04:08:41.946944+00:00, sha a5c5351bae32)
  - homepage: https://rubyllm.com/ (fetched 2026-08-29T09:10:43.477893+00:00, sha 4cfe9d913cfc)
  - site_page: https://rubyllm.com/getting-started (fetched 2026-08-29T09:10:43.480570+00:00, sha 68e9cbbf1183)
- Data as of 2026-08-30T08:39:29.467469+00:00.