JSPM

@bonginkan/maria

2.0.0-alpha.1.202508220416
  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 391
  • Score
    100M100P100Q122227F
  • License MIT

🧠 MARIA Platform v2.0.0 Memory Intelligence Edition - Revolutionary Dual-Layer Memory System with Complete Local AI Integration (Ollama + vLLM + LM Studio), Context-Aware Learning, 50+ Cognitive Modes, and Enterprise-Grade Development Intelligence

Package Exports

  • @bonginkan/maria
  • @bonginkan/maria/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@bonginkan/maria) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

πŸ€– MARIA Platform v1.8.6 "Quality Assured Edition"

TypeScript Node.js npm Downloads Tests License Quality Cognitive Modes Memory System Commands

πŸŽ‰ MARIA Platform v1.8.6 - Enterprise AI Development CLI with 100% Tested Commands, Revolutionary Dual-Layer Memory System, Complete Local LLM Integration (Ollama, vLLM, LM Studio), Context-Aware Intelligence, 40+ Interactive Commands, and Personalized Learning Capabilities!

πŸ–₯️ Beautiful CLI Interface

MARIA CLI Startup

MARIA's beautiful startup interface with automatic AI service initialization and local LLM detection

🌟 Key Features - Local AI & Privacy-First Development

🧠 NEW: Revolutionary Dual-Layer Memory System

  • System 1 (Fast/Intuitive): Instant pattern recognition and cache-based responses
  • System 2 (Deliberate/Analytical): Deep reasoning traces and decision trees
  • Context-Aware Intelligence: Every command learns from your patterns
  • Personalized Experience: Adapts to your coding style and preferences
  • 60% Faster Startup: Lazy loading with <50ms memory operations

🏠 Complete Local LLM Integration

  • Automatic Detection & Setup: Auto-configures Ollama, vLLM, LM Studio
  • Privacy-First Development: All processing runs locally on your machine
  • Zero Cloud Dependencies: Work offline with full AI capabilities
  • Multi-Model Support: Seamlessly switch between 20+ local models
  • One-Command Setup: maria setup-ollama / maria setup-vllm for instant configuration

πŸ€– Enterprise AI Development

  • Memory-Enhanced Commands: All core commands now learn from usage
  • Autonomous Coding Agent: Complete project development from requirements
  • Real-time Code Analysis: Live quality feedback with historical context
  • Multi-Provider Support: OpenAI, Anthropic, Google, Groq + Local LLMs
  • Interactive Commands: 40+ slash commands for development workflow
  • Professional Engineering Modes: 50+ specialized AI cognitive states

πŸš€ Instant Setup & Usage

npm install -g @bonginkan/maria
maria setup-ollama          # Auto-install local AI
maria                        # Start interactive development

Core Capabilities:

  • βœ… Local AI Models: Complete offline development environment
  • βœ… Code Generation: AI-powered development assistance
  • βœ… Quality Analysis: Real-time code review and optimization
  • βœ… Multi-Language: Support for all major programming languages
  • βœ… Enterprise Ready: Professional development workflows

🎯 Key Features

  • Interactive Learning: Hands-on algorithm education with visualization
  • Performance Analysis: Real-time performance metrics and optimization
  • Professional Engineering: Industry-standard development practices
  • Visual Progress: Beautiful CLI interface with progress tracking
  • Autonomous Execution: Complete task automation from requirements

πŸ€– Intelligent Router - Natural Language Command System

  • 🌍 5-Language Support: Native understanding in English, Japanese, Chinese, Korean, Vietnamese
  • Intent Recognition: "write code" β†’ /code automatic execution (95%+ accuracy)
  • Contextual Understanding: Smart parameter extraction from natural conversation
  • Learning Engine: Adapts to user patterns for personalized experience

Multi-Language Examples:

English:    "write code"          β†’ /code
Japanese:   "コードを書いて"        β†’ /code
Chinese:    "写代码"              β†’ /code
Korean:     "μ½”λ“œλ₯Ό μž‘μ„±ν•΄"        β†’ /code
Vietnamese: "viαΊΏt code"           β†’ /code

πŸ—οΈ Autonomous Development Ecosystem (/vibe, /paper, /agentic)

  • Paper-to-Code Transformation: Research papers β†’ production implementations using DeepCode architecture
  • SOW-Driven Development: Complete software solutions from high-level requirements
  • Multi-Agent Orchestration: 8+ specialized agents for complex task coordination
  • Agent Builder: Automated AGENT.md generation and custom AI agent creation

🎨 Multimodal Content Generation

  • Advanced Media Creation: AI-powered image, video, and presentation generation
  • Google Workspace Integration: Direct export to Google Docs and Slides
  • ASCII Avatar Interface: Interactive visual dialogue system
  • Voice Integration: Multimodal communication capabilities

🧠 Advanced Intelligence Systems

  • 50 Internal Modes: Real-time cognitive state adaptation (✽ Thinking…, ✽ Debugging…, etc.)
  • Cross-Session Learning: Knowledge transfer and skill progression tracking
  • Predictive Analytics: ML-powered user intent prediction and workflow optimization
  • Context Preservation: Deep semantic compression with knowledge graph construction

🏒 Enterprise-Grade Infrastructure

  • Zero-Error Policy: Automated quality enforcement with 0 warnings/errors
  • CodeRAG System: Semantic code search with graph-based dependency analysis
  • MCP Protocol Integration: Standardized tool communication across platforms
  • Real-time Collaboration: Team workspaces with live collaboration sessions

πŸ” Enterprise Code Quality Analysis Platform (Phase 6 - COMPLETE!)

Industry-First Comprehensive Analysis Suite with AI-Powered Insights

πŸ› Bug Detection System (/bug)

  • 40+ Pattern Recognition: Memory leaks, race conditions, type safety violations, performance bottlenecks
  • AI-Powered Fix Suggestions: Intelligent resolution with confidence scoring
  • Real-time Processing: <200ms analysis response time
  • Security Analysis: XSS, SQL injection, CSRF vulnerability detection

πŸ”§ Advanced Lint Analysis (/lint)

  • ESLint Integration: 10+ comprehensive code quality checks
  • Auto-Fix Engine: Intelligent resolution of fixable issues
  • Quality Metrics: 94/100 baseline standard with detailed reporting
  • Custom Rules: Extensible rule system for enterprise standards

πŸ›‘οΈ TypeScript Type Safety (/typecheck)

  • Compiler Integration: Complete TypeScript compiler integration
  • Coverage Tracking: 87% baseline with improvement monitoring
  • Strict Mode Analysis: Complete compliance checking
  • Type Assertion Detection: Dangerous any/unknown usage identification

πŸ” Security Vulnerability Assessment (/security-review)

  • OWASP Compliance: Complete OWASP Top 10 coverage (8/10 baseline)
  • Security Score: 89/100 enterprise standard
  • CWE Classification: Common Weakness Enumeration integration
  • Dependency Audit: npm audit integration with 127+ package validation

πŸ“Š Performance Metrics: 4/4 commands (100% implementation), 16 sub-commands, zero-error policy enforced

🀝 Human-in-the-Loop Approval System (Phase 8 - IMPLEMENTING!)

  • Theme-Level Approval: Strategic confirmation at architecture/implementation/security levels
  • Quick Decision Shortcuts: Shift+Tab, Ctrl+Y/N/T/R for instant workflow approval
  • Progressive Trust Building: 5-stage evolution from novice to autonomous operation
  • Risk-Aware Processing: AI identifies optimal approval points automatically
  • Learning Partnership: Adapts to user patterns while maximizing safety and efficiency

Quick Start

Installation

# πŸš€ Latest Version (Recommended) - Memory System Enabled
npm install -g @bonginkan/maria@latest

# πŸ”„ Update Existing Installation
npm update -g @bonginkan/maria

# 🎯 Alpha Version (Latest Features)
npm install -g @bonginkan/maria@alpha

# πŸ“Œ Specific Version (Production Use)
npm install -g @bonginkan/maria@2.0.0

# βœ… Verify Installation
maria --version
# Output: MARIA Platform v2.0.0 "Memory Intelligence Edition"

# 🧠 Setup Local AI Models (Optional)
maria setup-ollama    # Install and configure Ollama
maria setup-vllm      # Install and configure vLLM

# πŸš€ Start Interactive Mode
maria

Package Information

  • NPM Package: @bonginkan/maria
  • Latest Version: 1.8.3 (Updated: August 22, 2025)
  • Total Downloads: 500+ (and growing!)
  • Organization: bonginkan

Alternative Installation Methods

# Using yarn
yarn global add @bonginkan/maria@latest

# Using pnpm  
pnpm add -g @bonginkan/maria@latest

# Check all available versions
npm view @bonginkan/maria versions --json

πŸ–₯️ Live CLI Session Example

MARIA CLI Startup

Terminal Output:

πŸš€ Initializing AI Services...

Local AI Services:
LM Studio    [●●●●●●●●●●●●●●●●●●●] 0% βš™οΈ Checking availability...
Ollama       [●●●●●●●●●●●●●●●●●●●] 0% βš™οΈ Checking availability...
vLLM         [●●●●●●●●●●●●●●●●●●●] 0% βš™οΈ Checking availability...

πŸš€ Initializing AI Services...

> _

Natural language interaction (no commands needed!):

You: "write code for me"     # β†’ Automatically triggers /code
You: "create a React app"    # β†’ Intelligent routing to /code
You: "analyze this bug"      # β†’ Auto-switches to /bug mode
You: "implement research"    # β†’ Triggers /paper for paper-to-code

🌍 Multi-Language Support (5 Languages):

English:  "write code"       # β†’ /code
Japanese: "コードを書いて"     # β†’ /code
Chinese:  "写代码"           # β†’ /code
Korean:   "μ½”λ“œλ₯Ό μž‘μ„±ν•΄"     # β†’ /code
Vietnamese: "viαΊΏt code"      # β†’ /code

🧠 NEW: Memory-Enhanced Commands (v1.8.5):

> /memory status            # View dual-layer memory statistics
> /memory preferences       # Display learned coding preferences
> /memory context          # Show current project context
> /code "create API"       # Uses your patterns & preferences
> /bug analyze             # Recalls previous bug fixes
> /lint check             # Applies your style preferences

Advanced Code Quality Analysis Commands:

> /lint check               # Now with memory - learns your style
> /typecheck analyze         # Tracks type coverage over time
> /security-review scan      # Remembers vulnerability patterns
> /bug fix "null pointer"    # Suggests fixes from past resolutions

Traditional slash commands (34+ available):

/code     # AI-powered code generation
/paper    # Research paper β†’ code transformation
/vibe     # Autonomous development from requirements
/agentic  # Custom AI agent builder
/bug      # Comprehensive bug analysis & auto-fix
/image    # AI image generation
/video    # AI video generation with Google export
/model    # Switch between cloud and local models
/help     # Full command reference

Alternative Installation Methods

# Using yarn
yarn global add @bonginkan/maria

# Using pnpm
pnpm add -g @bonginkan/maria

🎯 Usage Examples

Basic Interactive Mode

# Start MARIA interactive CLI
maria

# Available commands in interactive mode:
> /help                          # Show all commands
> /agent execute "create API"    # Autonomous coding agent
> /agent demo                   # Demo autonomous capabilities
> /code "hello world function"  # AI code generation
> /status                       # System status
> /exit                         # Exit

Algorithm Education Commands

# Start MARIA and use algorithm education slash commands
maria
> /sort quicksort --visualize     # Interactive sorting visualization
> /learn algorithms               # Complete CS curriculum
> /benchmark sorting              # Performance analysis
> /algorithm complexity           # Big O notation tutorials
> /code "merge sort implementation" # AI-generated algorithms

36+ Interactive Slash Commands

# All commands are slash commands within interactive mode
maria
> /help                          # Show all 36+ commands
> /model                         # AI model selection
> /sort quicksort               # Algorithm education
> /code "function"              # AI code generation
> /bug analyze                  # Bug detection
> /lint check                   # Code quality
> /status                       # System status
> /mode internal                # 50 cognitive AI modes
> /exit                         # Exit MARIA

🎨 Key Features

πŸ€– Autonomous Coding Agent

  • Complete SOW Generation: Automatic Statement of Work creation
  • Visual Mode Display: Real-time progress with beautiful UI
  • Active Reporting: Progress tracking and status updates
  • Self-Evolution: Learning engine that improves over time
  • 120+ Engineering Modes: Professional development patterns

πŸ“Š Algorithm Education Platform

  • Interactive QuickSort: Step-by-step algorithm visualization
  • Performance Benchmarking: Compare algorithm efficiency
  • Memory Profiling: Analyze memory usage patterns
  • Educational Tools: Computer science curriculum support
  • Sorting Algorithms: Complete collection with analysis

πŸ”§ Development Tools

  • AI Code Generation: Multi-language code creation
  • Intelligent Assistance: Context-aware development help
  • Project Analysis: Codebase understanding and insights
  • Quality Assurance: Automated testing and validation
  • Version Control: Git integration and workflow support

🌍 Supported Platforms

  • Node.js: 18.0.0 - 22.x
  • Operating Systems: macOS, Linux, Windows
  • Terminals: All major terminal applications
  • Shells: bash, zsh, fish, PowerShell

πŸ“š Documentation

Command Reference

  • Interactive Mode: maria (starts directly)
  • All Commands: /help within interactive mode
  • Algorithm Education: /sort, /learn, /algorithm commands
  • AI Development: /code, /bug, /lint, /model commands
  • System Status: /status command

Examples and Tutorials

  • Getting Started: Run maria and type /help
  • Algorithm Learning: Use /sort quicksort --visualize for interactive tutorials
  • Development Workflow: AI-assisted coding with /code commands
  • Performance Analysis: Built-in benchmarking with /benchmark commands

πŸ”§ Configuration

MARIA works out of the box with no configuration required. For advanced features:

# Start interactive mode (default)
maria

# Check system status
> /status

# Configure AI providers
> /model  # Select from 22+ AI models (GPT, Claude, Gemini, Local LLMs)

# Algorithm education
> /sort quicksort --visualize  # Interactive learning

🀝 Contributing

We welcome contributions to MARIA! Please check our contribution guidelines.

Development Setup

# Clone the repository
git clone https://github.com/bonginkan/maria.git
cd maria

# Install dependencies
npm install

# Build the project
npm run build

# Run locally
./bin/maria

πŸ“„ License

MIT License - see LICENSE for details.

🎯 What Makes MARIA Special

Revolutionary AI Development

  • First Autonomous AI: Complete software development from requirements
  • Visual Progress: Beautiful CLI with real-time feedback
  • Educational Focus: Algorithm learning with interactive visualization
  • Professional Quality: Industry-standard engineering practices

Cutting-Edge Technology

  • Advanced AI Integration: Multiple AI model support
  • Intelligent Automation: Self-learning and adaptation
  • Modern CLI Experience: Beautiful, responsive interface
  • Cross-Platform: Works everywhere Node.js runs

Perfect for:

  • Students: Learn algorithms with interactive visualization
  • Developers: Accelerate development with AI assistance
  • Teams: Collaborative development with autonomous agents
  • Educators: Teach computer science with hands-on tools

Experience the Algorithm Education Revolution with MARIA Platform v1.6.4

πŸš€ Start your journey: npm install -g @bonginkan/maria@latest && maria

πŸ“¦ Package: npmjs.com/package/@bonginkan/maria | 🏒 Organization: npmjs.com/org/bonginkan

release/v1.6.0