@bonginkan/maria 2.1.2 → 2.1.5

package/README.md

@@ -1,19 +1,21 @@
-# 🤖 MARIA Platform v2.1.2 "Extended Command & Mode Edition"
+# 🤖 MARIA Platform v2.1.4 "ML 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-Dual--License-blue)](https://github.com/bonginkan/maria/blob/main/LICENSE)
+[![License](https://img.shields.io/badge/License-MIT-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-50-purple)](https://github.com/bonginkan/maria)
-[![Memory System](https://img.shields.io/badge/Memory%20System-Dual--Layer-orange)](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)
 
-> 🎉 **MARIA Platform v2.1.2** - Enterprise AI Development CLI with **60 Internal Modes**, **5 New Slash Commands** (workspace, db, api, deploy, monitor), **2 New Internal Modes** (Focus, Learning), **Revolutionary Dual-Layer Memory System**, **Complete Local LLM Integration**, and **Privacy-First Development** Environment!
+> 🤖 **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 CODE CLI Interface**
 
-![MARIA CLI Startup](./images/CLI_visual.png)
+![MARIA CLI Startup](./CLI_visual.png)
 
 _MARIA's beautiful startup interface with automatic AI service initialization and local LLM detection_
 
@@ -37,18 +39,56 @@ MARIA起動後に、自動で待機する内部モードとして、Self-Questio
 - **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 v2.1.2: Extended Commands & Modes**
-
-**5 New Slash Commands:**
-- **/workspace**: Project workspace management with session isolation
-- **/db**: Database schema generation, migration, and query optimization
-- **/api**: RESTful API development with OpenAPI generation and mock servers
-- **/deploy**: Multi-environment deployment automation with rollback support
-- **/monitor**: Real-time system monitoring with metrics and alerts
-
-**2 New Internal Modes:**
-- **Focus Mode** (`/focus`): Distraction-free coding with time-boxed sessions
-- **Learning Mode** (`/learn`): Educational assistance with multi-level explanations
+### 🆕 **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
 
 ### 🏠 **Complete Local LLM Integration**
 
@@ -79,6 +119,7 @@ maria                        # Start interactive development
 
 - ✅ **Local AI Models**: Complete offline development environment
 - ✅ **Code Generation**: AI-powered development assistance
+- ✅ **Machine Learning**: 5 ML commands for AI self-improvement cycle
 - ✅ **Quality Analysis**: Real-time code review and optimization
 - ✅ **Multi-Language**: Support for all major programming languages
 - ✅ **Enterprise Ready**: Professional development workflows
@@ -201,7 +242,7 @@ npm install -g @bonginkan/maria
 
 # Verify installation
 maria --version
-# Output: MARIA Platform v2.0.7 "Memory Intelligence Edition"
+# Output: MARIA Platform v2.1.4 "ML Intelligence Edition"
 
 # Setup local AI models (optional)
 maria setup-ollama    # Install and configure Ollama
@@ -213,7 +254,7 @@ maria
 
 ### 🖥️ **Live CLI Session Example**
 
-![MARIA CLI Startup](./images/CLI_visual.png)
+![MARIA CLI Startup](./CLI_visual.png)
 
 **Terminal Output:**
 
@@ -240,6 +281,16 @@ 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
@@ -382,6 +433,7 @@ 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
@@ -432,13 +484,10 @@ npm run build
 
 ## 📄 License
 
-**Dual-License Model**: Personal Use (Free) / Enterprise (Paid)
+**MIT License**: Free and open-source for all users
 
-- **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
+This project is licensed under the MIT License - see the [LICENSE](./LICENSE) file for details.
 
-See [LICENSE](https://github.com/bonginkan/maria/blob/main/LICENSE) for complete terms.
 
 ## 🔗 Links
 
@@ -472,7 +521,7 @@ See [LICENSE](https://github.com/bonginkan/maria/blob/main/LICENSE) for complete
 
 ---
 
-**Experience the Algorithm Education Revolution with MARIA Platform v1.6.4**
+**Experience the Machine Learning Intelligence Revolution with MARIA Platform v2.1.4**
 
 🚀 Start your journey: `npm install -g @bonginkan/maria && maria`
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@bonginkan/maria",
-  "version": "2.1.2",
-  "description": "🧠 MARIA Platform v2.1.2 Extended Command & Mode Edition - 5 New Slash Commands (workspace, db, api, deploy, monitor) + 2 New Internal Modes (Focus, Learning) + Enhanced Memory Intelligence with Multi-Source Deep Analysis and Advanced Knowledge Base Integration",
+  "version": "2.1.5",
+  "description": "🔬 MARIA Platform v2.1.3 Research & Memory Intelligence Edition - AI-Powered Research Paper Generation (/paper) + Enhanced Memory System (/memory) + GraphRAG Analysis + Bilingual Academic Papers + Microservice Architecture + Advanced Context Preservation",
   "keywords": [
     "ai",
     "cli",

package/dist/bin/maria.d.ts

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