# Shopify/roast

Structured AI workflows made easy

Repository: https://github.com/Shopify/roast
Canonical: https://ross.abutalabs.com/products/roast
Language: Ruby
License: MIT
License Family: permissive
Last push: 2026-08-10T23:11:39+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 90, longevity 36
- inputs: {"age_days": 511, "days_push": 23, "days_rel": 68, "gap_med": 8, "n_releases_24m": 24}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1210, forks 74 (observed 2026-08-28T04:04:00.082168+00:00)

## What it is
Roast is a Ruby-based domain-specific language for building structured AI workflows from composable building blocks called cogs. It orchestrates LLM calls, local coding agents, shell commands, and Ruby code with control flow like conditionals, iteration, and parallel map operations.

## Use cases
- orchestrate multi-step LLM workflows in Ruby
- run coding agents locally to review changed files
- chain AI steps where output flows to the next step
- process collections with AI in serial or parallel
- automate codebase analysis and summarization
- build reusable parameterized AI workflow components

## When to choose
- you want a declarative Ruby DSL for AI automation pipelines
- you need to mix LLM calls, shell commands, and custom code in one workflow
- you want to run local coding agents like Claude Code or Pi CLI with filesystem access
- you're a Ruby team integrating AI into developer tooling

## When to avoid
- your stack is Python or JavaScript and you prefer native SDKs
- you need a visual workflow builder or GUI
- you only need simple single-prompt LLM calls
- you require non-Ruby runtime environments

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, workflow-automation, sdk
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: ruby, cli, cross-platform
- tags: dsl, ai-workflows, llm-orchestration, coding-agents, ruby-gem, ai-agents, automation

## Member repositories
- Shopify/roast (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:00.082168+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 2026-08-30T06:18:09.554175+00:00, confidence not recorded.
  - readme: https://github.com/Shopify/roast (fetched 2026-08-28T04:04:00.082168+00:00, sha 08172ac4cb35)
- Data as of 2026-08-30T08:39:29.467469+00:00.