🚀 BMAD+ — Augmented Multi-Agent AI Framework

56+ agents · 9 modular packs · Autopilot mode · Parallel execution · 143 tests Smart fork of BMAD-METHOD — Self-activating agents with 3-level context detection, GRC compliance (Shield), full SDLC pipeline (Dev Studio), OSINT intelligence, SEO audit, persistent cross-session memory, and a 10-language CLI installer.

📋 Table of Contents

• Why BMAD+?
• Quick Start
• Architecture
• The 56+ Agents
• Pack System
• Innovations
• Supported IDEs
• Project Structure
• Configuration
• Version History
• License

💡 Why BMAD+?

BMAD-METHOD is an excellent framework with 9 specialized agents. But for a solo developer or a small team, 9 agents is too fragmented. BMAD+ solves this problem:

| BMAD-METHOD | BMAD+ | |---|---| | 9 specialized agents | 56+ agents across 9 packs | | Manual activation only | Intelligent auto-activation at 3 levels | | No automated pipeline | Autopilot Mode: idea → delivery | | Sequential execution | Supervised parallelism | | No persistent memory | Cross-session brain with project scanner | | 1-2 IDEs supported | 5 IDEs with auto-detection | | 1 module | 9 modular packs (Core, OSINT, Shield, Dev Studio, SEO, Memory...) |

⚡ Quick Start

Installation in an existing project

npx bmad-plus install

The installer:

1. Automatically detects installed IDEs (Claude Code, Gemini CLI, Codex, etc.)
2. Offers packs to install (Core, OSINT, Maker, Audit)
3. Generates adapted configuration files
4. Creates artifact folders

Usage after installation

💬 Who to talk to?

📊 Strategy & Discovery

| You want to... | Talk to | Example | |---|---|---| | Brainstorm a project idea | Atlas 🎯 | Atlas, I have a project idea: a billing SaaS | | Market/domain research | Atlas 🎯 | Atlas, analyze the market for AI note-taking apps | | Create a PRD / Product Brief | Atlas 🎯 | Atlas, create the PRD for my project | | Design UX wireframes | Atlas 🎯 | Atlas, design the UX for the onboarding flow |

🏗️ Architecture & Development

| You want to... | Talk to | Example | |---|---|---| | Design technical architecture | Forge 🏗️ | Forge, propose an architecture for the app | | Implement a user story | Forge 🏗️ | Forge, implement story AUTH-001 | | Write/update documentation | Forge 🏗️ | Forge, document the API | | Quick hotfix or small change | Forge 🏗️ | Forge, quick dev: add a loading spinner |

🔍 Quality & Review

| You want to... | Talk to | Example | |---|---|---| | Code review | Sentinel 🔍 | Sentinel, review the auth module | | Write tests (unit/E2E) | Sentinel 🔍 | Sentinel, write E2E tests for checkout | | UX/accessibility audit | Sentinel 🔍 | Sentinel, review the UX of the dashboard |

🎼 Project Management

| You want to... | Talk to | Example | |---|---|---| | Plan a sprint | Nexus 🎼 | Nexus, create epics and stories for the MVP | | Automate everything (A to Z) | Nexus 🎼 | autopilot then describe your project | | Run tasks in parallel | Nexus 🎼 | parallel — auto-detects independent tasks | | Sprint retrospective | Nexus 🎼 | Nexus, run a retrospective on Sprint 3 |

🕵️ Intelligence & Specialized Packs

| You want to... | Talk to | Example | |---|---|---| | Investigate a person (OSINT) | Shadow 🕵️ | Shadow, investigate John Doe | | Create a new BMAD+ agent | Maker 🧬 | Maker, create a customer support agent | | Recall past decisions/context | Zecher 🧠 | Zecher, what did we decide about the auth strategy? | | Session handoff summary | Zecher 🧠 | Zecher, create a handoff for the next session |

🚀 Typical Workflow (manual mode)

1. "Atlas, brainstorm on my [project] idea"
   → Atlas analyzes, asks questions, proposes angles

2. "Atlas, create the product brief"
   → Deliverable: _bmad-output/discovery/product-brief.md

3. "Atlas, write the PRD"
   → Deliverable: _bmad-output/discovery/prd.md

4. "Forge, propose the architecture"
   → Deliverable: _bmad-output/discovery/architecture.md

5. "Nexus, break down into epics and stories"
   → Deliverable: _bmad-output/build/stories/

6. "Forge, implement story [X]"
   → Code generated + tests

7. "Sentinel, test and review"
   → QA report + suggestions

⚡ Automatic Workflow (autopilot mode)

> autopilot
> "A billing SaaS for SMBs with quote management"

Nexus automatically orchestrates everything with checkpoints for your approval.

💬 Key Commands

| Command | Description | |----------|-------------| | bmad-help | View all available agents and skills | | autopilot | Nexus takes control of the complete pipeline | | parallel | Launch multi-agent execution in parallel |

🔧 CLI Commands

| Command | Description | |---------|-------------| | npx bmad-plus install | Interactive installer with pack selection and IDE detection | | npx bmad-plus scan [path] | Discover and index projects in the global brain | | npx bmad-plus memory status | Memory health report (project + global brain) | | npx bmad-plus memory export | Export brain as portable Markdown archive | | npx bmad-plus doctor | Check installation integrity | | npx bmad-plus update | Update agents and skills (preserves config) | | npx bmad-plus uninstall | Remove BMAD+ from current project | | npx bmad-plus autoconfig | Smart project bootstrap — auto-detect, install, and configure |

🔬 Advanced Install Options

# Non-interactive install — all packs, auto-detect IDEs
npx bmad-plus install --packs all --yes

# Install without overwriting IDE configs (CLAUDE.md, GEMINI.md, etc.)
npx bmad-plus install --tools none

# Install specific packs only
npx bmad-plus install --packs core,memory,osint

# Install in a different directory
npx bmad-plus install --directory /path/to/project

💡 Dogfooding tip: Use --tools none when installing BMAD+ into a project that already has manually maintained IDE config files. This installs agents, skills, and memory without overwriting your existing CLAUDE.md, GEMINI.md, or AGENTS.md.

🔍 Scan Options

# Scan a drive or directory for projects
npx bmad-plus scan D:\DEV

# Custom thresholds for project status
npx bmad-plus scan . --active-days 7 --paused-days 90

# Auto-index all without prompting
npx bmad-plus scan D:\DEV --yes --depth 6

Status legend: 🟢 active (modified < 30 days), 🟡 paused (30–180 days), ⚪ archived (> 180 days). Thresholds are customizable with --active-days and --paused-days.

🏗️ Architecture

graph TB
    subgraph Core["⚙️ Core Pack"]
        AT["Atlas 🎯"]
        FG["Forge 🏗️"]
        SN["Sentinel 🔍"]
        NX["Nexus 🎼"]
    end

    subgraph Packs["📦 Modular Packs"]
        SH["Shadow 🕵️ OSINT"]
        MK["Maker 🧬"]
        ZC["Zecher 🧠 Memory"]
        SD["Shield 🛡️ GRC 38 agents"]
        DS["Dev Studio 🏗️ SDLC 6 agents"]
        SEO["SEO Engine 🔎 3 agents"]
        BK["Backup 🗂️"]
        AN["Animated 🎬"]
    end

    subgraph Skills["⚡ Core Skills"]
        AP[Autopilot]
        PL[Parallel]
    end

    NX -->|orchestrates| AT
    NX -->|orchestrates| FG
    NX -->|orchestrates| SN
    NX -->|invokes| SH
    NX -->|invokes| MK
    NX --> AP
    NX --> PL
    ZC -.->|context| NX

🎭 The 56+ Agents

Atlas — Strategist 🎯

Fuses: Analyst (Mary) + Product Manager (John)

| Role | Specialty | Auto-activation | |------|-----------|-----------------| | Analyst | Market research, SWOT, benchmarks, domain expertise | "analyze", "market", "benchmark", new project | | Product Manager | PRD, product briefs, user stories, roadmaps | "PRD", "roadmap", "MVP", planning phase |

Capabilities: Brainstorming (BP), Market Research (MR), Domain Research (DR), Technical Research (TR), Product Brief (CB), PRD (PR), UX Design (CU), Document Project (DP)

Forge — Architect-Dev 🏗️

Fuses: Architect (Winston) + Developer (Amelia) + Tech Writer (Paige)

| Role | Specialty | Auto-activation | |------|-----------|-----------------| | Architect | Technical design, API, scalability, stack choice | "architecture", "API", "schema", +5 files modified | | Developer | TDD implementation, code review, story execution | "implement", "code", "fix", post-architecture | | Tech Writer | Documentation, Mermaid diagrams, changelogs | "document", "README", post-implementation |

Capabilities: Architecture (CA), Implementation Readiness (IR), Dev Story (DS), Code Review (CR), Quick Spec (QS), Quick Dev (QD), Document Project (DP)

Critical actions (Dev role):

• Read the ENTIRE story BEFORE implementation
• Execute tasks IN ORDER
• 100% passing tests BEFORE moving on
• NEVER lie about tests

Sentinel — Quality 🔍

Fuses: QA Engineer (Quinn) + UX Designer (Sally)

| Role | Specialty | Auto-activation | |------|-----------|-----------------| | QA Engineer | API/E2E tests, edge cases, coverage, code review | "test", "QA", "bug", post-implementation | | UX Reviewer | UX evaluation, accessibility, interaction design | "UX", "interface", "responsive", frontend changes |

Capabilities: QA Tests (QA), Code Review (CR), UX Design (CU)

Nexus — Orchestrator 🎼

Fuses: Scrum Master (Bob) + Quick-Flow Solo Dev (Barry) + Autopilot (new) + Parallel Supervisor (new)

| Role | Specialty | Auto-activation | |------|-----------|-----------------| | Scrum Master | Sprint planning, stories, retros, course correction | "sprint", "planning", "backlog" | | Quick Flow | Quick specs, hotfixes, minimum ceremony | "quick", "hotfix", "small fix" | | Autopilot | Pipeline automated idea→delivery with checkpoints | "autopilot", "manage everything", autopilot mode | | Parallel Supervisor | Concurrent multi-agent, conflict detection, reallocation | "parallel", independent tasks detected |

Capabilities: Sprint Planning (SP), Create Story (CS), Epics & Stories (ES), Retrospective (ER), Course Correction (CC), Sprint Status (SS), Quick Spec (QS), Quick Dev (QD), Autopilot (AP), Parallel (PL)

Shadow — OSINT Intelligence 🔍 (OSINT Pack)

Complete OSINT investigation agent.

| Capability | Description | |-----------|-------------| | INV | Complete investigation Phase 0→6 with scored dossier | | QS | Quick multi-engine search | | LI/IG/FB | LinkedIn, Instagram, Facebook scraping | | PP | MBTI / Big Five psychoprofile | | CE | Contact enrichment (email, phone) | | DG | Diagnostic of available tools/APIs |

Stack: 55+ Apify actors, 7 search APIs, 100% Python stdlib, confidence grades A/B/C/D

Maker — Agent Creator 🧬 (Maker Pack)

Meta-agent that creates other agents. Give it a description → it generates a complete package.

| Code | Description | |------|-------------| | CA | Create Agent — guided creation in 4 phases | | QA | Quick Agent — fast creation with sensible defaults | | EA | Edit Agent — modify an existing SKILL.md | | VA | Validate Agent — check BMAD+ compliance | | PA | Package Agent — generate the integration folder |

Pipeline: Discovery → Design (user validation) → Generation → Validation Output: _bmad-output/ready-to-integrate/ — ready to copy into BMAD+

📦 Pack System

BMAD+ uses a modular pack system. Core is always installed, additional packs are optional.

npx bmad-plus install

🎛️  Which packs to install?
   Core (Atlas, Forge, Sentinel, Nexus) is always included.

   🔍 OSINT — Shadow (investigation, scraping, psychoprofiling)
   🧬 Agent Creator — Maker (design, build, package)
   🛡️ Shield GRC — 38 compliance agents (GDPR, ISO 27001, SOC 2, HIPAA...)
   🏗️ Dev Studio — 6 SDLC agents (full lifecycle: design to deploy)
   🔎 SEO Engine — Scout, Chief, Judge (6-phase audit, PageSpeed)
   🧠 Memory — Zecher (persistent brain, session handoffs)
   🗂️ Backup — Smart archive with versioning
   🎬 Animated — Scroll-driven animated websites
   🤖 Install everything
   None — Core only

| Pack | Agents | Description | Status | |------|--------|-------------|--------| | ⚙️ Core | Atlas, Forge, Sentinel, Nexus | Strategy, dev, QA, orchestration | ✅ Stable | | 🔍 OSINT | Shadow | OSINT intelligence, 55+ Apify actors, 7 APIs | ✅ Stable | | 🧬 Maker | Maker | Design, build, validate new BMAD+ agents | ✅ Stable | | 🛡️ Shield | 38 GRC agents | GDPR, ISO 27001, SOC 2, HIPAA, EU AI Act | ✅ Stable | | 🏗️ Dev Studio | 6 SDLC agents | Full lifecycle: design to deploy | ✅ Stable | | 🔎 SEO | Scout, Chief, Judge | 6-phase audit, PageSpeed loop, Google APIs | ✅ Stable | | 🧠 Memory | Zecher | Cross-session brain, decision recall, handoffs | ✅ Stable | | 🗂️ Backup | Backup Agent | Smart archive with versioning | ✅ Stable | | 🎬 Animated | Creative Agent | Scroll-driven animated websites | ✅ Stable |

Each pack defines:

• Its agents and skills
• Its required/optional API keys
• Its external package (if applicable)

✨ Innovations

1. 3-Level Intelligent Auto-Activation

Each agent can automatically switch roles when the context requires it:

| Level | Mechanism | Example | |--------|-----------|---------| | 🔤 Pattern | Keywords in the request | "review" → QA activated | | 🌐 Contextual | Domain detected during work | Financial calculations → QA auto-activated after code | | 🧠 Reasoning | Logic chain during execution | Architecture inconsistency → Architect auto-activated |

The agent announces its auto-activations: "💡 I'm switching to QA mode — financial calculations detected. Say 'skip' to stay in current mode."

Configuration: src/bmad-plus/data/role-triggers.yaml

2. Autopilot Mode

Give a project idea → Nexus orchestrates the complete pipeline:

📋 Discovery (Atlas)
  └→ Brainstorming → Product Brief → PRD → UX Design
  🔴 CHECKPOINT: PRD Approval

🏗️ Build (Forge + Sentinel)
  └→ Architecture → Epics → Stories → Sprint
  🔴 CHECKPOINT: Architecture Approval
  └→ For each story: Code → Tests → (retry if failed, max 3)
  🟡 NOTIFY: Story status

🚀 Ship (Sentinel + Forge)
  └→ Code Review → UX Review → Documentation → Retro
  🔴 CHECKPOINT: Final approval

Configurable checkpoints:

• require_approval (🔴) — Pause, wait for approval
• notify_only (🟡) — Notification, continues unless intervened
• auto (🟢) — Continues automatically

3. Supervised Parallel Execution

The Orchestrator detects independent tasks and launches them in parallel:

| Parallelizable ✅ | Sequential 🚫 | |---|---| | Stories without dependencies | Same file modified | | Research + tech audit | Story B depends on Story A | | Tests + documentation | Architecture before code |

Supervision actions: Launch, Monitor, Stop, Restart, Reallocate, Escalate (3 failures → human notification)

🖥️ Supported IDEs

The installer automatically detects IDEs and generates configs:

| IDE | Config File | Detection | |-----|---------------|-----------| | Claude Code | CLAUDE.md | .claude/ folder | | Gemini CLI | GEMINI.md | .gemini/ folder | | Antigravity | .gemini/ + .agents/ | Antigravity Extension | | Codex CLI | AGENTS.md | .codex/ folder | | OpenCode | OPENCODE.md | opencode config |

📁 Project Structure

BMAD+/
├── README.md                      ← This file (English)
├── readme-international/          ← Translated READMEs (fr, es, de)
├── CHANGELOG.md                   ← Version history
├── CLAUDE.md                      ← Claude Code Config
├── GEMINI.md                      ← Gemini CLI Config
├── AGENTS.md                      ← Codex CLI / OpenCode Config
├── .gitignore
│
├── src/
│   └── bmad-plus/                 ⭐ CUSTOM MODULE
│       ├── module.yaml            ← Module + packs config
│       ├── module-help.csv        ← Contextual help
│       ├── agents/
│       │   ├── agent-strategist/  ← Atlas (analyst + pm)
│       │   ├── agent-architect-dev/ ← Forge (architect + dev + tw)
│       │   ├── agent-quality/     ← Sentinel (qa + ux)
│       │   ├── agent-orchestrator/ ← Nexus (sm + qf + autopilot + parallel)
│       │   ├── agent-maker/       ← Maker (meta-agent) [pack: maker]
│       │   └── agent-shadow/      ← Shadow (osint) [pack: osint]
│       ├── skills/
│       │   ├── bmad-plus-autopilot/ ← Automated pipeline
│       │   └── bmad-plus-parallel/  ← Parallel execution
│       └── data/
│           └── role-triggers.yaml ← Auto-activation rules
│
├── tools/
│   └── cli/                       🛠️ NPX INSTALLER
│       └── install.js             ← npx bmad-plus install
│
├── osint-agent-package/           🔍 OSINT PACKAGE
│   ├── agents/                    ← Shadow Agent (OSINT investigator)
│   ├── skills/                    ← 55+ Apify actors
│   └── install.ps1                ← Installation script
│
└── upstream/                      📦 UPSTREAM REFERENCE
    └── (clone of BMAD-METHOD)     ← Excluded from repo (.gitignore)

⚙️ Configuration

Module variables (module.yaml)

| Variable | Description | Values | |----------|-------------|---------| | project_name | Project name | Auto-detected | | user_skill_level | Dev level | beginner, intermediate, expert | | execution_mode | Execution mode | manual, autopilot, hybrid | | auto_role_activation | Role auto-switch| true, false | | parallel_execution | Parallelism | true, false | | install_packs | Installed packs | core, osint, maker, audit, all |

API Keys (depending on packs)

| Key | Pack | Usage | |-----|------|-------| | APIFY_API_TOKEN | OSINT | Social media scraping | | PERPLEXITY_API_KEY | OSINT | Enriched search |

📜 Version History

| Version | Date | Description | |---------|------|-------------| | 0.1.0 | 2026-03-17 | 🎉 Foundation — 56+ agents (Atlas, Forge, Sentinel, Nexus, Shadow, Maker), 3 skills, pack system, multi-IDE support | | 0.2.0 | 2026-03-18 | 🔀 Oveanet Fusion — 3 new utility packs: SEO Audit 360, Universal Backup, Animated Website | | 0.3.0 | 2026-03-19 | 🚀 SEO Engine v2.0 — 3 multi-role agents, 4 Python scripts, 6-phase workflow, PageSpeed loop, GEO analysis | | 0.4.0 | 2026-03-19 | 🏢 SEO Engine v2.1 — SKILL.md orchestrator, Google APIs, HTML reports, competitor benchmark, 50 tests, GSC + GA4 extensions | | 0.4.1 | 2026-03-19 | | 0.4.2 | 2026-03-19 | Public packs SEO/Backup/Animated agents now in npm package | 🌐 10-language CLI, CI/CD pipeline, .npmignore, /deploy workflow, security hardening | | 0.4.3 | 2026-05-17 | 🔧 update + doctor commands, i18n complete, credits fix | | 0.4.4 | 2026-05-17 | 🔧 UTF-8 encoding fix, complete i18n 10 languages, 62 unit tests | | 0.5.0 | 2026-05-17 | 🛡️ Pack Shield — 38 GRC compliance agents, 7 categories, 25+ frameworks (GDPR, ISO 27001, SOC 2, EU AI Act...) | | 0.6.0 | 2026-05-17 | 🏗️ Pack Dev Studio — 6 SDLC agents (Miriam, Yosef, Bezalel...) + 30 SDLC workflows, BWML DSL | | 0.9.0 | 2026-06-24 | 🚀 Augmented & Secure — 3 new packs (animated, backup, seo), P0 security remediation, 143/143 tests | | 0.8.0 | 2026-06-24 | 🚀 Augmented & Secure — 3 new packs (animated, backup, seo), P0 security remediation, 143/143 tests |

See CHANGELOG.md for full details.

📄 License

MIT — Based on BMAD-METHOD (MIT)

Credits

Creator

• BMAD+ Created by Laurent Rochetta (LinkedIn)

Original Packs (created by Laurent Rochetta)

• Dev Studio — 6 specialized SDLC agents: Miriam (business analyst), Huldah (tech writer), Yosef (product manager), Rachel (UX designer), Bezalel (system architect), Oholiab (senior engineer) — 44 workflows covering the full lifecycle from brainstorming to deployment
• SEO Engine — 3 agents (Scout, Chief, Judge), 6-phase audit pipeline, PageSpeed perfection loop, Google Search Console & GA4 integrations
• Memory Pack — Zecher agent for persistent cross-session brain with project scanner

External Sources & Inspirations

• BMAD-METHOD by bmad-code-org — Original multi-agent methodology (MIT)
• Shield GRC — 38 compliance agents built on public regulatory texts (GDPR, ISO 27001, SOC 2, HIPAA, EU AI Act, DORA, NIST, CMMC, etc.)
• OSINT Pipeline based on smixs/osint-skill (MIT)
• Apify Actor Runner integrated from apify/agent-skills (MIT)
• Karpathy Guardrails adapted from Andrej Karpathy (MIT) — Behavioral rules for Memory Pack

Tools & Infrastructure

• Evolution API — WhatsApp notifications for upstream monitoring
• Gemini API — AI analysis for upstream change classification