Summary

This project integrates the BMad Method as a plugin for the OpenClaw AI-driven development framework. It addresses the need for structured, AI-assisted software development by orchestrating specialist agents through the entire lifecycle—analysis, planning, solutioning, and implementation—offering a benefit of organized and potentially more efficient development processes for technical users.

How It Works

The core architecture employs a top-level "BMad Master" agent that spawns dedicated specialist sub-agents for distinct development phases (e.g., Analyst, PM, Architect). This design prevents context bleeding between workflows, ensuring each agent operates with fresh context. The system offers two execution modes: "YOLO" for autonomous, continuous execution, and "Interactive" for user review and feedback at each step, relaying input via sessions_send.

Quick Start & Requirements

• Installation: Clone the repository into OpenClaw extensions (git clone https://github.com/ErwanLorteau/BMAD_Openclaw.git ~/.openclaw/extensions/bmad-method) and run npm install within the extension directory.
• Configuration: Update ~/.openclaw/openclaw.json to load the plugin path and enable the bmad-method entry. Configure the bmad-master agent to allow bmad-method tools.
• Execution: Create a master workspace (mkdir -p ~/.openclaw/workspace-bmad) and restart the OpenClaw gateway.
• Prerequisites: Node.js (implied by npm).
• Development: npm install, npm test, npm run typecheck.

Highlighted Details

• Structured AI-driven development workflows.
• Dedicated specialist agents with isolated context for distinct roles.
• Orchestration of the full software development lifecycle: analysis → planning → solutioning → implementation.
• Autonomous (YOLO) and interactive execution modes.

Maintenance & Community

The project's architecture has evolved through V1 (abandoned due to complexity) and V2 (abandoned due to context bleeding) to the current V3. No specific community links (Discord, Slack) or notable contributors/sponsorships are detailed in the README.

Licensing & Compatibility

• License: MIT.
• Compatibility: The MIT license permits commercial use and integration into closed-source projects.

Limitations & Caveats

Previous architectural approaches (V1, V2) were abandoned due to significant challenges with complexity and context bleeding, suggesting potential areas of fragility or ongoing refinement in the current V3 implementation. The README does not detail specific unsupported platforms or known bugs.