Harness Hub
All open source

BMAD Method

Breakthrough Method for Agile AI Driven Development

bmad-code-org/BMAD-METHOD

Maintained by bmad-code-org

BMAD Method (Breakthrough Method for Agile AI Driven Development) is an open-source framework from BMad Code, LLC. It structures AI-driven development as agile, agent-based workflows. It is MIT licensed.

View on GitHub

Pros & cons

Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.

Pros

  • DocsA structured agile workflow with PM, architect, developer and UX personas that make assumptions explicit before code is written.[1]
  • User reportsA user has onboarded several SaaS projects into it and credits its tech specs and repeated rounds of eliciting requirements with catching edge cases early.[1][2]
  • DocsFree, with no paywalled workflows; installs via npx, the Skills CLI or a Claude Code plugin marketplace.[1]

Cons

  • User reportsCritics call it 'Waterfall for Agents', heavy on ceremony and capitalized jargon.[1]
  • User reportsEach story means running create, develop, test, review, fix and status-update steps, so an 8-story epic can take 40+ manual commands; users wrote wrappers to automate this.[1]
  • DocsTwo release lines are in flux: v6.12 is frozen except for bug fixes, and the v7 alpha changes skills, install path and docs often.[1]
  • MetadataThe code is MIT, but every casing and variant of 'BMad' is trademarked, so forks must ship under a different name.[1]
Best for
Teams that want spec-first, persona-driven planning around Claude Code or similar agents on greenfield products.
Watch out for
Process overhead can outweigh the benefit on small changes, and the move from v6 to v7 changes commands.

Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction

People

Featured

openclaw/openclaw

The viral open-source personal AI assistant that really does things.

Maintained by OpenClaw Foundation

4 pros · 4 cons

obra/superpowers

An agentic skills framework and software methodology that works.

Maintained by Jesse Vincent (obra)

4 pros · 4 cons

mattpocock/skills

Small, composable agent skills for real engineering work.

Maintained by Matt Pocock (AI Hero)

4 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Maintained by · 1

  • bmad-code-orgOrganisation

Similar entries · 2

Sources

  1. GitHub repo