Shopify/roast

Structured AI workflows made easy

What it solves

Roast is a Ruby-based domain-specific language (DSL) designed to simplify the creation of structured AI workflows. It allows developers to orchestrate complex AI-powered automation by combining modular building blocks called "cogs" to handle LLM interactions, code execution, and data processing.

How it works

Users write declarative Ruby syntax to define workflows. These workflows are composed of "cogs" that can be chained together, where the output of one cog flows into the next.

Key cogs include:

  • chat: Interacts with cloud LLMs like OpenAI, Anthropic, Perplexity, and Gemini.
  • agent: Runs local coding agents (such as Pi CLI or Claude Code CLI) with direct filesystem access.
  • ruby: Executes custom Ruby code.
  • cmd: Runs shell commands and captures their output.
  • map: Processes collections of data in serial or parallel execution.
  • repeat: Iterates until specific conditions are met.
  • call: Invokes reusable, parameterized workflow scopes.

Who it’s for

Ruby developers who want to build AI-powered automation and agentic workflows without writing boilerplate orchestration logic.

Highlights

  • Declarative Ruby Syntax: Uses a simple DSL for defining AI steps.
  • Local Agent Integration: Supports local coding agents with full filesystem access.
  • Multi-Provider Support: Compatible with multiple LLM providers (OpenAI, Anthropic, Perplexity, Gemini).
  • Intelligent Control Flow: Includes built-in support for iteration, conditional execution, and parallel processing via the map cog.

Related

  • Project
    crmne/ruby_llm

    A Ruby-native AI framework that provides a consistent API for building chats, agents, and multimodal features across multiple AI providers in Ruby and Rails applications.

  • Project
    Dicklesworthstone/pi_agent_rust

    A native Rust-based AI coding agent CLI that provides a high-performance, secure, and lightweight alternative to runtime-dependent AI assistants.

  • Project
    aaif-goose/goose

    An open-source, general-purpose AI agent available as a desktop app, CLI, and API that handles coding, research, and automation tasks.

  • Project
    graniet/llm

    A Rust library providing a unified API to interact with multiple LLM backends, enabling multi-step chains, agentic workflows, and a standardized REST API.

  • Project
    Abraxas-365/langchain-rust

    A Rust implementation of the LangChain framework for building composable LLM applications with support for various models, vector stores, and agents.