aizen-gate

⛩️ Aizen-Gate: The Premier AI-Orchestration & Specification Shield

🆕 Implemented Features (Elite Swarm Upgrade)

All optimization and autonomous protection phases are active:

Phase	Feature	Description	Status
10-11	Recursive Mesh	Multi-agent neural mesh with Quantum Token Compression.	✅ OK
12-14	Neural Memory	Forgetting (Soft Pruning) & Dreaming (Knowledge Consolidation).	✅ OK
15-16	Self-Healing	Immune System (Auto-Repair) & Swarm Consensus Voting.	✅ OK
17	Safety Fuse	Infinite Loop Prevention & Emergency Kill-Switch.	✅ OK
18	Elite FBA	Workspace Ergonomics & Structural Refactoring (Clean Root).	✅ OK
31	Advanced RAG	Multi-Query Expansion, Semantic Re-ranking, Contextual Chunker.	✅ OK
32	Elite Brainstorm	12-Section Industry Master PRD & Expert Panel Challenger Mode.	✅ OK

New CLI Commands

npx aizen-gate specify    # Discovery wizard with AI suggestions
npx aizen-gate plan        # Architectural blueprint design
npx aizen-gate tasks       # Work package decomposition
npx aizen-gate auto        # Autonomous execution loop
npx aizen-gate status      # View Scrum Board & Memory
npx aizen-gate dashboard  # Real-time progress (port 6420)

New Elite Hierarchy (FBA)

aizen-gate/
├── bin/                # CLI Entrances (npx entry points)
├── src/                # Core Logic & Source (The Brain)
├── docs/               # Documentation Archives & ADRs
├── infrastructure/     # Agents Infra, Rules, Logs, & Templates
├── aizen-gate/         # Core Persistent Mesh Data
├── kanban/             # Swarm Execution Board
├── shared/             # Cross-Agent State Mesh
└── skills/             # 1200+ Atomic Agent Skills

Documentation

For detailed documentation, see:

• AIZEN.md - Agent configuration and identity
• ONBOARDING.md - Setup guide for new users
• AGENTS.md - Agent system documentation

🏛️ What is Aizen-Gate?

Aizen-Gate is a high-tier AI-Orchestration framework (Elite AI-SDLC) that transforms standard AI interactions into a professional, multi-agent Software Development Life Cycle (SDLC) execution.

It is not just a set of instructions; it is a "Gate" that ensures every line of code written by an AI follows high-quality standards, remains documented, and operates within a razor-sharp contextual memory.

[!IMPORTANT] Aizen-Gate is more than a chatbot. It is an operating system for AI Agents, managing specifications, planning, and implementation in one seamless workflow.

🎯 Why Aizen-Gate?

When developing applications with AI, we often face three major hurdles:

• Context Rot: AI begins to forget initial instructions or hallucinates as project complexity grows.
• Standard Leakage: AI-generated code lacks architectural consistency or aesthetic standards.
• Task Fragmentation: Managing complex features in parallel without breaking the main codebase is difficult.

Aizen-Gate eliminates these gaps by providing a "Shield" that guarantees project integrity from start to finish.

💻 Tech Stack & Architecture

Aizen-Gate is built on a modern foundation for maximum performance and security:

• Core Engine: 100% TypeScript with ESM modules for type safety and long-term maintainability.
• Embedded Intelligence: node-llama-cpp hosting qwen2.5-0.5b locally for zero-latency distillation and task planning (No Ollama required!).
• Unified Memory: Synchronous better-sqlite3 backend with the 12-Core Intelligence Tiering (Working, Semantic, Episodic, Procedural, etc.).
• Logic Recall: @xenova/transformers (BGE-Micro-V2) for ultra-lightweight semantic indexing.
• Addressing: Built on the OpenViking URI Protocol (agent://space/agent/topic) for deterministic logic routing.
• Vanilla CSS with a premium, responsive minimalist editorial style.

⛩️ New in v2.3.0

🔍 Phase 31: Advanced RAG Optimization

Maximize memory retrieval fidelity with hybrid intelligence:

• Multi-Query Expansion: Generates technical variations of queries to broaden recall.
• Semantic Re-Ranking: Uses cross-match heuristics to prioritize most relevant memories.
• Contextual Chunker: Structural code boundary detection for higher-integrity memory fragments.

🧠 Phase 32: Elite Brainstorming v2.0

Transform LLMs into a relentless Expert Panel:

• 12-Section Master PRD: Enterprise-grade blueprint covering Security, i18n, Analytics, and Rollback plans.
• Consensus Meter: Visual real-time tracking of AI expert agreement level.
• Conflict Resolution: Logic-driven synthesis of opposing architect/PM views.

🏗️ Core Components & Features

Aizen-Gate consolidates powerful tools into a unified ecosystem:

Component	Utility
specify Wizard	An interactive interview process that turns abstract ideas into bullet-proof spec.md files.
Kanban Agent	Physical state mapping using /kanban directories (backlog, dev, test, done).
AI Context Bridge	Auto-generated CURRENT_SPRINT.md that keeps AI agents aligned with active tasks.
12-Core Fusion	A neural-backed memory system that distills raw text into logic nuggets.
Immune System	Self-healing memory logic that deprioritizes "BROKEN" reasoning paths.
Autonomous Loop	Executes implementations in isolated Git Worktrees per task.

🚀 Installation Guide

You can install Aizen-Gate globally or run it directly via NPX.

1. Global Installation

npm install -g aizen-gate

2. Initialize the Shield in Your Workspace

Navigate to your project directory and run:

aizen-gate install

This prepares the aizen-gate/ folder structure, installs the constitution.md, and configures local persistent memory.

🛠️ Elite Workflow (How to Start)

Follow the 7-phase dominance pipeline for zero-defect results:

• Discovery:

  npx aizen-gate specify
  

  Launch the PM wizard to build the implementation spec.

• Planning:

  npx aizen-gate plan
  

  The Lead Architect designs the architectural blueprint.

• Tasking:

  npx aizen-gate tasks
  

  Decompose the plan into Work Packages (WPs) with clear dependencies.

• Execution:

  npx aizen-gate auto
  

  Trigger the autonomous loop. AI agents start working in parallel isolated branches.

• Monitoring:

  npx aizen-gate dashboard
  

  Visualize real-time pulse and progress in your browser (port 6420).

🧪 CLI Commands Reference

Workflow & Orchestration

npx aizen-gate research   # Parallel technical deep-dives
npx aizen-gate review     # Perform QA review on finished work
npx aizen-gate merge      # Final branch merging and cleanup
npx aizen-gate quick      # Fast-track a small feature or bug fix

Intelligence & Diagnostics

npx aizen-gate status     # View Scrum Board & Memory state
npx aizen-gate kanban init # Bootstrap Kanban environment
npx aizen-gate kanban sync # Refresh AI context manifest
npx aizen-gate tokens     # View token usage & efficiency report

💎 How Aizen-Gate Empowers Development

Aizen-Gate shifts your workflow from "Writing Code" to "Directing Vision":

• Cost Efficiency: Local embeddings and context distillation significantly cut down API token costs.
• Safe Isolation: Every task is executed in a separate "Worktree." A failure in one feature never corrupts another.
• Elite Quality: With Athena Quality Gates, every completed task is audited by a QA agent before merging is allowed.
• Scalability: Manage massive projects with thousands of files while keeping the AI's understanding razor-sharp.

⛩️ [Aizen] Shield System Active. Ready to build the future.
"Every gap has been eliminated. Welcome to the elite tier of AI development."