← Browse tools

Agent frameworks

Roast

Shopify’s Ruby toolkit for composing structured AI workflows from reusable steps, including model conversations, agent calls, code and command execution.

1,216 stars

Overview

Research summary

Roast provides a Ruby-oriented way to describe and execute structured AI workflows. Instead of putting an entire task into one unstructured conversation, developers compose reusable steps and control how information moves between them. The toolkit supports different kinds of work, including model interactions, agent invocations, application code, and shell commands, with composition patterns for sequential, conditional, and parallel execution.

Integrations can reuse existing coding-agent tools rather than require a single proprietary model backend. This makes Roast a workflow-building component rather than a ready-made replacement for every coding assistant. Operators are responsible for the credentials, filesystem access, command permissions, and isolation available to their workflows.

The MIT-licensed Ruby implementation can be extended within an application, while any model providers or invoked agents retain their own terms and behavior.

Repository summary

Stars
1,216
Open issues
Unavailable
Last push
2026-08-10
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Implementation

Recorded implementation details and interfaces for Roast.

Implementation details

Ruby workflow DSL and execution toolkit

Languages
Ruby
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

Shopify/roast ↗

Stars
1,216
Open issues
Unavailable
Last push
2026-08-10
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06
Stars source
Recorded fallback
Last push source
Recorded fallback

Documentation

Recorded references and research provenance for this entry.

Recorded sources 5

Research metadata

Research date
2026-09-16
Catalogue snapshot
2026-10-06

Community & social 1 channels

Communities