Agentic Coding Comparison Map

wb-flow operates in a complex landscape of agentic tools, frameworks, and code assistants. This page maps out where wb-flow fits and how it differs from others.

Category Map (2D Landscape)

HIGH COGNITIVE / PRODUCT DEPTH
         ↑
   BMAD  │
         │     wb-flow
   Kiro  │
 Spec Kit│
OpenSpec │      GSD
 Superpowers
         └────────────────→ HIGH EXECUTION ORCHESTRATION

Player	Strongest toward	Tier
BMAD	Human / product / architecture cognition; specialized roles	Tier A
GSD	Context-fresh, dependency-aware wave execution	Tier A
Spec Kit	Standardized specification methodology and supporting ecosystem	Tier A
OpenSpec	Lightweight brownfield deltas (ADDED/MODIFIED/REMOVED)	Tier A
Superpowers	Minimal disciplined agent (TDD, review, low ceremony)	Tier A
Kiro	Integrated IDE experience	Tier B
Tessl	Specs as infrastructure	Tier B
wb-flow	Unifying planning + cognition (--as) + waves + validation + artifact graph + model routing	Tier A

Tier A pages compare one architectural dimension at a time. Tier B and Tier C entries provide context, not a ranked league table.

Hosts are not competitors

Coding agents like Cursor, Claude Code, or Codex are the execution environment. wb-flow orchestrates them; it does not replace them.

Comparisons

• wb-flow vs GSD
• wb-flow vs BMAD
• wb-flow vs Spec Kit
• wb-flow vs OpenSpec
• wb-flow vs Superpowers

Tier C

For Conductor, Spec Kitty, and MoAI-ADK, these tools represent experimental or specialized approaches that are out of scope for our primary comparisons.