@bonginkan/maria 2.1.5 → 2.1.7

package/README.md

@@ -1,94 +1,39 @@
-# 🤖 MARIA Platform v2.1.4 "ML Intelligence Edition"
+# 🤖 MARIA Platform v2.1.7 "Linux Command Intelligence Edition"
 
 [![TypeScript](https://img.shields.io/badge/TypeScript-5.0%2B-blue)](https://www.typescriptlang.org/)
 [![Node.js](https://img.shields.io/badge/Node.js-18%2B-green)](https://nodejs.org/)
 [![npm](https://img.shields.io/npm/v/@bonginkan/maria?label=npm%20package)](https://www.npmjs.com/package/@bonginkan/maria)
 [![Downloads](https://img.shields.io/npm/dt/@bonginkan/maria)](https://www.npmjs.com/package/@bonginkan/maria)
-[![License](https://img.shields.io/badge/License-MIT-blue)](https://github.com/bonginkan/maria/blob/main/LICENSE)
+[![License](https://img.shields.io/badge/License-Dual--License-blue)](https://github.com/bonginkan/maria/blob/main/LICENSE)
 [![Quality](https://img.shields.io/badge/Code%20Quality-100%25-brightgreen)](https://github.com/bonginkan/maria)
-[![Cognitive Modes](https://img.shields.io/badge/Cognitive%20Modes-60-purple)](https://github.com/bonginkan/maria)
-[![Memory System](https://img.shields.io/badge/Memory%20System-Enhanced-orange)](https://github.com/bonginkan/maria)
-[![ML Commands](https://img.shields.io/badge/ML%20Commands-5%20New-red)](https://github.com/bonginkan/maria)
-[![AI Self-Improvement](https://img.shields.io/badge/AI%20Self--Improvement-Active-gold)](https://github.com/bonginkan/maria)
+[![Cognitive Modes](https://img.shields.io/badge/Cognitive%20Modes-50-purple)](https://github.com/bonginkan/maria)
+[![Memory System](https://img.shields.io/badge/Memory%20System-Dual--Layer-orange)](https://github.com/bonginkan/maria)
 
-> 🤖 **MARIA Platform v2.1.4** - Machine Learning Intelligence Edition with **AI Self-Improvement Cycle**, **5 New ML Commands** (/train /eval /rlhf /self_play /auto_tune), **Hyperparameter Optimization**, **Synthetic Data Generation**, plus **Research Paper System**, **Memory Intelligence**, and **GraphRAG Analysis**!
+> 🎉 **MARIA Platform v2.1.7** - **Autonomous Linux System Administration** + Enterprise AI Development CLI with **100% Tested Linux Command Intelligence**, **Smart Command Execution**, **Risk Assessment & Safety Validation**, **Learning Engine & Workflow Automation**, **Revolutionary Dual-Layer Memory System**, **Complete Local LLM Integration** (Ollama, vLLM, LM Studio), 50+ Interactive Commands, and **Privacy-First Development** Environment!
 
 ## 🖥️ **MARIA CODE CLI Interface**
 
-![MARIA CLI Startup](./CLI_visual.png)
+![MARIA CLI Startup](./images/CLI_visual.png)
 
 _MARIA's beautiful startup interface with automatic AI service initialization and local LLM detection_
 
-## 🌟 Key Features - Local AI & Privacy-First Development
-
-### 🧠 **Revolutionary Dual-Layer Memory System (v2.0.7)**
-
-- **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
-
-### 🤔 **Self-Questioning Internal Mode (Auto-Active)**
-
-MARIA起動後に、自動で待機する内部モードとして、Self-Questioning内部モードを追加しました。このモードは以下の機能を提供します：
-
-- **文脈推測**: 理解困難・矛盾・不明瞭な入力でも文脈から意図を自動推測
-- **Ultrathink発動**: 複雑な場合に深層思考モードで多角的分析を実行
-- **矛盾解析**: 相反する要求の根本原因を探り優先順位仮説を構築
-- **推測根拠明示**: 推測内容と信頼度（0.1-1.0）を透明化して提示
-- **柔軟適応**: 推測が外れても修正可能な回答構造を自動維持
-
-### 🆕 **New in v2.1.4: Machine Learning Intelligence Edition**
-
-**🤖 5 New ML Commands - AI Self-Improvement Cycle:**
-- **/train**: Complete model training and fine-tuning with progress visualization
-  - Local & S3 dataset support with hyperparameter configuration
-  - Real-time progress display and ASCII learning curves
-  - Automatic model checkpointing and comprehensive training reports
-- **/eval**: Model evaluation and benchmarking with multiple metrics
-  - Performance analysis (accuracy, F1, BLEU, latency)
-  - Confusion matrix visualization and category-wise analysis
-  - Automatic improvement suggestions and detailed evaluation reports
-- **/rlhf**: Reinforcement Learning from Human Feedback
-  - Feedback data analysis and reward model training
-  - Policy optimization (PPO) with improvement visualization
-- **/self_play**: AI self-dialogue for synthetic data generation
-  - Task-specific dialogue generation (bug_fixing, code_review, qa_generation)
-  - High-quality synthetic datasets in JSONL format
-- **/auto_tune**: Automated hyperparameter optimization
-  - Grid, random, and Bayesian search strategies
-  - Parameter importance analysis and optimal configuration discovery
-
-**🔄 Complete AI Self-Improvement Pipeline:**
-1. **🎯 Auto-Training**: `/train` learns from datasets
-2. **📊 Performance Evaluation**: `/eval` measures objective performance  
-3. **🔄 Feedback Integration**: `/rlhf` incorporates human feedback
-4. **🎮 Data Expansion**: `/self_play` generates additional training data
-5. **⚡ Parameter Optimization**: `/auto_tune` discovers optimal settings
-
-### 🆕 **Enhanced Research & Memory Intelligence**
-
-**🔬 Research Paper Generation System:**
-- **/paper**: Complete research workflow from theme to published paper
-  - 6-stage research process (Theme → Literature Review → Design → Analysis → Paper)
-  - Bilingual support (Japanese/English)
-  - GraphRAG & Agentic RAG specialized knowledge
-  - Auto-citation and reference management
-  - Organized research papers folder structure
-
-**🧠 Enhanced Memory System:**
-- **/memory**: Advanced context preservation and learning
-  - Dual-layer memory architecture
-  - Cross-session learning persistence  
-  - Project-specific context management
-  - Personalized response pattern learning
-
-**🏗️ Microservice Architecture:**
-- **SlashCommandManager**: Phase-based migration system
-- **PaperResearchService**: Dedicated research workflow service
-- **BaseCommandService**: Extensible service framework
-- Full TypeScript strict mode compliance
+## 🌟 Key Features - Autonomous Linux Administration & AI Development
+
+### 🤖 **Linux Command Intelligence System (v2.1.7) - NEW!**
+
+- **Phase 1 - Intelligence Layer**: Real-time context analysis and command intent recognition (14 intent types)
+- **Phase 2 - Autonomous Execution**: Smart command executor with 5-level risk assessment and safety validation
+- **Phase 3 - Advanced Operations**: Infrastructure management, file system intelligence, container integration
+- **Phase 4 - Learning & Adaptation**: Machine learning engine, workflow automation, anomaly detection
+- **100% Integration Tested**: All 4 phases validated on macOS with complete system compatibility
+
+### 🧠 **Revolutionary Dual-Layer Memory System (Enhanced v2.1.7)**
+
+- **System 1 (Fast/Intuitive)**: Instant pattern recognition with Linux command awareness
+- **System 2 (Deliberate/Analytical)**: Deep reasoning with system administration context
+- **Intelligence Integration**: Memory system now learns from Linux command patterns
+- **Autonomous Learning**: Adapts to your system administration and coding patterns
+- **Enhanced Performance**: 60% faster startup with intelligent command caching
 
 ### 🏠 **Complete Local LLM Integration**
 
@@ -98,33 +43,69 @@ MARIA起動後に、自動で待機する内部モードとして、Self-Questio
 - **Multi-Model Support**: Seamlessly switch between 20+ local models
 - **One-Command Setup**: `maria setup-ollama` / `maria setup-vllm` for instant configuration
 
-### 🤖 **Enterprise AI Development**
+### 🤖 **Enterprise AI Development + System Administration**
 
-- **Memory-Enhanced Commands**: All core commands now learn from usage
+- **Autonomous Linux Administration**: Complete system management with intelligent command execution
+- **Safety-First Operations**: Pre-execution validation with automatic backup and rollback capabilities
+- **Learning System Administration**: AI learns your server management patterns and optimizes workflows
+- **Memory-Enhanced Commands**: All core commands learn from usage with Linux command intelligence
 - **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
+- **Interactive Commands**: 50+ slash commands including system administration tools
+- **Professional Engineering Modes**: 50+ specialized AI cognitive states for development and ops
 
 ### 🚀 **Instant Setup & Usage**
 
 ```bash
 npm install -g @bonginkan/maria
 maria setup-ollama          # Auto-install local AI
-maria                        # Start interactive development
+maria                        # Start interactive development + Linux intelligence
 ```
 
-**Core Capabilities:**
+**Linux Command Intelligence Capabilities (NEW in v2.1.7):**
+
+- ✅ **Autonomous Linux Administration**: Smart command execution with risk assessment
+- ✅ **Safety Validation**: Pre-execution checks with automatic backup creation
+- ✅ **Learning Engine**: AI learns your system administration patterns
+- ✅ **Workflow Automation**: Complex task orchestration with cron scheduling
+- ✅ **Anomaly Detection**: Real-time system monitoring and security analysis
+- ✅ **100% Integration Tested**: Complete validation across all 4 intelligence phases
+
+**Core Development Capabilities:**
 
 - ✅ **Local AI Models**: Complete offline development environment
-- ✅ **Code Generation**: AI-powered development assistance
-- ✅ **Machine Learning**: 5 ML commands for AI self-improvement cycle
+- ✅ **Code Generation**: AI-powered development assistance with system context
 - ✅ **Quality Analysis**: Real-time code review and optimization
 - ✅ **Multi-Language**: Support for all major programming languages
-- ✅ **Enterprise Ready**: Professional development workflows
+- ✅ **Enterprise Ready**: Professional development workflows with system administration
+
+### 🤖 Linux Command Intelligence System
+
+#### **Phase 1: Intelligence Layer** 
+- **Context Analysis Engine**: Real-time system state monitoring with user intent recognition
+- **Command Knowledge Base**: Comprehensive Linux command database with risk classification
+- **Intent Recognition**: 14 command intent types (FILE_OPERATION, SERVICE_CONTROL, PERFORMANCE_OPTIMIZATION, etc.)
+- **Risk Assessment**: 5-level classification system (SAFE → CRITICAL) for command safety
 
-### 🎯 Key Features
+#### **Phase 2: Autonomous Execution Framework**
+- **Smart Command Executor**: Context-aware command processing with intelligent parameter suggestion
+- **Safety Validator**: Pre-execution validation with automatic backup creation and rollback planning
+- **Progress Tracking**: Real-time execution monitoring with detailed progress reports
+- **Dry-run Mode**: Safe command testing without actual system changes
+
+#### **Phase 3: Advanced Operations Integration**  
+- **Infrastructure Management**: Service orchestration and process monitoring capabilities
+- **File System Intelligence**: Smart file operations with metadata analysis and security checks
+- **Network Analysis**: Comprehensive networking diagnostics and troubleshooting
+- **Container Integration**: Docker/Podman support for containerized environment management
+
+#### **Phase 4: Learning & Adaptation System**
+- **Machine Learning Engine**: User behavior analysis and command sequence optimization
+- **Workflow Automation**: Complex multi-step operations with cron scheduling and error handling
+- **Anomaly Detection**: Real-time security and performance monitoring with intelligent alerting
+- **Adaptive Intelligence**: Self-improving system that learns from user patterns and optimizes workflows
+
+### 🎯 Development Features
 
 - **Interactive Learning**: Hands-on algorithm education with visualization
 - **Performance Analysis**: Real-time performance metrics and optimization
@@ -218,12 +199,15 @@ Vietnamese: "viết code"           → /code
 ### 💡 **Why Engineers & Researchers Choose MARIA**
 
 ```bash
-# Natural language commands for complex tasks:
+# Natural language commands for development & system administration:
 "Create a React component for user authentication"
 "Fix this TypeScript error in my API"  
 "Generate comprehensive tests for my algorithm"
 "Set up Ollama with local LLM models"
-"Switch to thinking mode for complex debugging"
+"Check system performance and optimize"
+"Create automated backup workflow"
+"Analyze disk usage and clean up files"
+"Monitor services and restart if needed"
 ```
 
 **Real developer feedback:**
@@ -242,19 +226,21 @@ npm install -g @bonginkan/maria
 
 # Verify installation
 maria --version
-# Output: MARIA Platform v2.1.4 "ML Intelligence Edition"
+# Output: MARIA Platform v2.1.7 "Linux Command Intelligence Edition"
 
 # Setup local AI models (optional)
 maria setup-ollama    # Install and configure Ollama
 maria setup-vllm      # Install and configure vLLM
 
-# Start interactive mode with natural language
+# Start interactive mode with Linux Command Intelligence
 maria
+# Linux Command Intelligence System initializes automatically
+# All system administration commands now benefit from AI intelligence
 ```
 
 ### 🖥️ **Live CLI Session Example**
 
-![MARIA CLI Startup](./CLI_visual.png)
+![MARIA CLI Startup](./images/CLI_visual.png)
 
 **Terminal Output:**
 
@@ -281,16 +267,6 @@ vLLM         [●●●●●●●●●●●●●●●●●●●] 0% ⚙
 /paper <query>    # Transform research papers into working code
 ```
 
-**🤖 Machine Learning Commands (AI Self-Improvement):**
-
-```bash
-/train <dataset> <model>     # Train/fine-tune models with progress visualization
-/eval <model> <test-data>    # Evaluate model performance with metrics
-/rlhf <model> <feedback>     # Reinforcement learning from human feedback
-/self_play <model> <tasks>   # Generate synthetic training data via AI dialogue
-/auto_tune <model> <data>    # Optimize hyperparameters automatically
-```
-
 **🏠 Local AI Integration (Privacy-First Development):**
 
 ```bash
@@ -433,7 +409,6 @@ maria
 - **All Commands**: `/help` within interactive mode
 - **Algorithm Education**: `/sort`, `/learn`, `/algorithm` commands
 - **AI Development**: `/code`, `/bug`, `/lint`, `/model` commands
-- **Machine Learning**: `/train`, `/eval`, `/rlhf`, `/self_play`, `/auto_tune` commands
 - **System Status**: `/status` command
 
 ### Examples and Tutorials
@@ -484,10 +459,13 @@ npm run build
 
 ## 📄 License
 
-**MIT License**: Free and open-source for all users
+**Dual-License Model**: Personal Use (Free) / Enterprise (Paid)
 
-This project is licensed under the MIT License - see the [LICENSE](./LICENSE) file for details.
+- **Personal Use**: Free for individuals, students, and startups (<10 employees, <$1M ARR)
+- **Enterprise**: Commercial license required for larger organizations
+- **Contact**: enterprise@bonginkan.ai for enterprise licensing
 
+See [LICENSE](https://github.com/bonginkan/maria/blob/main/LICENSE) for complete terms.
 
 ## 🔗 Links
 
@@ -521,7 +499,7 @@ This project is licensed under the MIT License - see the [LICENSE](./LICENSE) fi
 
 ---
 
-**Experience the Machine Learning Intelligence Revolution with MARIA Platform v2.1.4**
+**Experience the Algorithm Education Revolution with MARIA Platform v1.6.4**
 
 🚀 Start your journey: `npm install -g @bonginkan/maria && maria`
 

package/dist/bin/maria.d.ts

@@ -0,0 +1,2 @@
+
+export {  }