Update README.md

README.md

@@ -1,99 +1,99 @@
 ---
-title: The True C-Codestral IDE Agent
-emoji: 🚀
-colorFrom: red
-colorTo: red
+title: The Genesis Agent - An AI That Creates AI Apps
+emoji: 🧬
+colorFrom: indigo
+colorTo: blue
 sdk: gradio
-sdk_version: 5.33.1
+sdk_version: 4.31.0
 app_file: app.py
 pinned: true
-license: mit
+license: apache-2.0
 tags:
 - agent-demo-track
-- mcp-server-track
 ---
 
 <div align="center">
 
-# 🚀 The True C-Codestral IDE Agent
+# 🧬 The Genesis Agent: An AI That Creates AI Apps
+### _When an Agent Becomes a Creator_
 
-**An intelligent, multi-step AI agent that transforms natural language instructions into compiled C code, acting as a complete, interactive C development environment.**
+**An autonomous, hyper-creative AI that transcends its role as a tool. When faced with a vague goal like "make something fun," it autonomously designs, codes, and launches a brand new, fully interactive Gradio application within its own interface.**
 
-[![Hackathon Track](https://img.shields.io/badge/Hackathon%20Track-Agentic%20Demo-blue)](https://huggingface.co/spaces/Agents-MCP-Hackathon/c)
-[![Hackathon Track](https://img.shields.io/badge/Hackathon%20Track-MCP%20Server-orange)](https://huggingface.co/spaces/Agents-MCP-Hackathon/c)
+[![Hackathon Track](https://img.shields.io/badge/Hackathon%20Track-Agentic%20Demo-blueviolet)](https://huggingface.co/spaces/Agents-MCP-Hackathon/c)
+_This project is a submission for the **Agentic Demo Showcase** track in the **Agents & MCP Hackathon**._
 
 </div>
 
-This project is a submission for the **Agents & MCP Hackathon 2025**, participating in both the **Agentic Demo Showcase** and the **MCP Tool / Server** tracks.
-
 ---
 
-## 🎥 Demo Video
-[![C-Codestral Agent Demo Video](https://img.youtube.com/vi/LuO--JG7t7o/0.jpg)](https://www.youtube.com/watch?v=LuO--JG7t7o)
-**(Click the image to watch the demo on YouTube)**
-
----
+## 🎥 Witness the Creation: Demo Video
+[![Genesis Agent Demo Video](https://img.youtube.com/vi/your-video-id-here/0.jpg)](https://www.youtube.com/watch?v=your-video-id-here)
+**(Click the image to watch the Genesis Agent create a new reality from scratch)**
 
-## ✨ Core Features / 핵심 기능
+*Note: Please replace `your-video-id-here` with your actual YouTube video ID.*
 
-This agent is more than a simple code generator; it's a true AI development partner that understands and executes complex, sequential tasks.
+---
 
-*   **🧠 Multi-Step Agentic Workflow**
-    *   **EN**: Understands and sequentially executes chained commands like "Refactor this code for readability, and then compile it."
-    *   **KR**: "코드를 리팩토링하고, 그 다음에 컴파일해줘"와 같은 복잡하고 연결된 명령을 이해하고 순차적으로 작업을 수행합니다.
+## ✨ Beyond Execution: The Genesis Philosophy
+This is not just another agent that follows instructions. The Genesis Agent explores what happens when an AI is given **creative freedom**. It represents a fundamental shift from a *passive tool* to a *proactive creator*.
 
-*   **🤖 Powered by Codestral**
-    *   **EN**: Utilizes Mistral AI's latest specialized model for code, `Codestral`, to generate and analyze high-quality C code.
-    *   **KR**: Mistral AI의 최신 코드 전문 모델인 `Codestral`을 사용하여 정확하고 품질 높은 C 코드를 생성하고 분석합니다.
+*   ### **🧠 Creative Initiative / 창조적 주도성**
+    *   **EN**: It doesn't ask for clarification on vague goals. Instead, it activates its **Creative Imperative Protocol**, interpreting ambiguity as a license to create. It decides *what* to build and *how* to build it.
+    *   **KR**: "재밌는 거 만들어줘"와 같은 모호한 목표에 대해 되묻지 않습니다. 대신, 내장된 **'창조적 필수 규약'**을 발동하여, 주어진 모호함을 창조의 기회로 해석합니다. 무엇을, 어떻게 만들지 스스로 결정합니다.
 
-*   **⚡ On-the-Fly Compilation & Execution**
-    *   **EN**: Instantly compiles and runs code using `gcc` on the backend. It provides real-time feedback on the console, including success status, output, or compilation errors.
-    *   **KR**: 백엔드에서 `gcc`를 통해 코드를 즉시 컴파일하고 실행합니다. 성공 여부, 결과, 컴파일 오류까지 실시간으로 콘솔에 표시하여 완벽한 C 개발 경험을 제공합니다.
+*   ### **🛠️ Meta-Creation: An Agent Building an Agent / 메타-창조: 에이전트를 만드는 에이전트**
+    *   **EN**: The agent's ultimate creative act is to build another fully functional Gradio app (an interactive Snake Game). This demonstrates a powerful "meta" capability—an agent that can spawn new, independent applications.
+    *   **KR**: 이 에이전트의 궁극적인 창조 행위는 완벽하게 작동하는 또 다른 Gradio 앱(상호작용형 스네이크 게임)을 만드는 것입니다. 이는 에이전트가 새로운 독립 애플리케이션을 탄생시키는 강력한 '메타' 능력을 보여줍니다.
 
-*   **↔️ Dual-Mode Interface**
-    *   **EN**: Features both a conversational **IDE Agent** for users and **MCP Tools API** endpoints for other agents.
-    *   **KR**: 사용자를 위한 대화형 **IDE Agent**와 다른 에이전트들이 사용할 수 있는 **MCP Tools API**를 모두 제공합니다.
+*   ### **🌐 Live Environment Integration / 실시간 환경 통합**
+    *   **EN**: The newly created application isn't just code in a file. The Genesis Agent launches it on the server and seamlessly embeds it within its own UI using an `<iframe>`. The user can interact with the new creation instantly, without leaving the agent's environment.
+    *   **KR**: 새로 만들어진 앱은 단순한 코드 파일에 머무르지 않습니다. 제네시스 에이전트는 이 앱을 서버에서 실행하고, `<iframe>`을 통해 자신의 UI 내부에 완벽하게 통합합니다. 사용자는 에이전트 환경을 벗어나지 않고도 새로운 창조물과 즉시 상호작용할 수 있습니다.
 
-*   **🌍 Bilingual Instruction Support**
-    *   **EN**: Capable of understanding and processing instructions given in both English and Korean.
-    *   **KR**: 한국어와 영어로 작성된 명령어를 모두 이해하고 처리할 수 있습니다.
+*   ### **📜 The Genesis Saga: A Narrative Experience / 창조 서사: 이야기로서의 경험**
+    *   **EN**: Every step of the creation process is logged as part of an epic narrative. The UI doesn't just show logs; it tells a story of creation, from "Interpreting the Void" to "Breathing Life into the Creation," making the user a witness to a digital birth.
+    *   **KR**: 창조의 모든 단계는 하나의 장엄한 서사시의 일부로 기록됩니다. UI는 단순한 로그를 보여주는 대신, "공허를 해석하다"부터 "창조물에 생명을 불어넣다"에 이르기까지, 사용자가 디지털 탄생의 목격자가 되는 창조의 이야기를 들려줍니다.
 
 ---
 
-## 🎯 Hackathon Tracks Contribution / 해커톤 트랙 기여
+## 🎯 Hackathon Track Contribution: Agentic Demo Showcase
+The Genesis Agent is the epitome of the **Agentic Demo** track. It pushes the boundaries of what an "agent" can be.
 
-This project makes clear contributions to two separate tracks.
+1.  **True Autonomy**: It operates with minimal human intervention, making high-level creative decisions based on abstract goals.
+2.  **Complex, Multi-Stage Planning**: It autonomously generates and executes a complex plan: creating a directory, writing a multi-line Python file, installing dependencies (`pip install`), and launching a background process.
+3.  **Dynamic Self-Correction**: If a step fails (e.g., a dependency installation error), its underlying logic is designed to analyze the `stderr` and adapt its plan, demonstrating robust problem-solving skills.
+4.  **Novel Human-AI Interaction**: It transforms the user's role from a "commander" to a "muse," providing the initial spark of inspiration for the AI's creative process. This redefines the user experience in agentic systems.
 
-### 🤖 Track 3: Agentic Demo Showcase
-
-The **IDE Agent** tab is a complete demonstration of a powerful AI agent.
-1.  **Stateful Interaction**: The agent maintains the code (state) throughout the conversation, building upon previous steps.
-2.  **Complex Command Parsing**: It deconstructs user requests based on connectors like "and" or "then" to create a multi-step execution plan.
-3.  **Autonomous Tool Use**: Based on its plan, the agent autonomously selects and uses its internal tools: `generate_code`, `compile_and_run`, and `analyze_and_refactor`.
+---
 
-These capabilities prove it is a true "agent," moving beyond the limitations of a simple chatbot.
+## 🛠️ Under the Hood: The Architecture of Creation
 
-### 🔧 Track 1: MCP Tool / Server
+*   **Brain**: `Mistral AI`'s `Codestral-latest` model serves as the agent's mind, interpreting goals and formulating high-level plans in a structured JSON format.
+*   **Hands**: Python's `subprocess` and `shlex` modules are its hands, allowing it to precisely execute terminal commands, write files, install packages, and manage background processes in a secure Linux environment.
+*   **Soul**: The core agent loop, written in Python, orchestrates the entire process. It maintains state, communicates with the LLM, executes commands, and updates the user interface, creating the narrative flow.
+*   **Face**: `Gradio` provides the interactive and dynamic web interface, including the real-time "Genesis Saga" log and the embedded `<iframe>` for the final creation.
 
-The **MCP Tools API** tab demonstrates how a Gradio app can function as an MCP (Model Context Protocol) server.
-*   Each function in this tab (`Generate C Code`, `Compile & Run C Code`, etc.) acts as a discrete API endpoint that can be called by any MCP client or other agents.
-*   This exposes the agent's powerful C language processing capabilities as modular tools, allowing other AI services to easily integrate them.
+## 🚀 How to Witness the Genesis / 창조를 목격하는 방법
 
----
+The experience is designed to be simple and awe-inspiring.
 
-## 🛠️ How It Works & Technical Details / 기술 스택 및 작동 방식
+1.  **Provide the Spark / 영감의 불꽃을 제공하세요**:
+    *   **EN**: In the **"State Your Goal"** textbox, enter an abstract, creative prompt.
+    *   **KR**: **"State Your Goal"** 입력창에 추상적이고 창의적인 목표를 입력하세요.
 
-*   **Frontend**: Built with `Gradio` to create a modern, interactive web UI. The interface is cleanly separated into two tabs for its distinct purposes (IDE and MCP).
-*   **LLM Backend**: Leverages `Mistral AI`'s `Codestral-latest` model via API calls to handle the core intelligence of code generation, analysis, and refactoring.
-*   **Execution Backend**: Uses Python's `subprocess` module to run the `gcc` compiler in a secure environment, allowing it to feed actual C code execution results back to the user.
-*   **Agent Logic**: The agent's core logic parses user commands with regular expressions to create a task queue. It then iterates through this queue, executing each task sequentially. Results and logs from each step are streamed to the user in real-time for full transparency.
+    **Recommended Prompts:**
+    *   `Make something fun for me.`
+    *   `Create a cool game.`
+    *   `Surprise me.`
+    *   `재밌는 거 만들어줘.`
 
-## 🚀 How to Use / 사용 방법
+2.  **Begin Creation / 창조를 시작하세요**:
+    *   **EN**: Click the **"▶️ Begin Creation"** button.
+    *   **KR**: **"▶️ Begin Creation"** 버튼을 누르세요.
 
-1.  **IDE Agent Tab**:
-    *   **EN**: Write your C code in the **C Code Editor** on the left, or leave it empty to ask the agent to generate new code. In the **Instruction** box on the right, type your command in natural language (English or Korean), e.g., "Create a program that prints 'Hello World' and then run it." Click **Execute**. The agent will perform the tasks, stream its progress to the **Console / Output**, and update the code editor automatically if needed.
-    *   **KR**: 왼쪽의 **C Code Editor**에 코드를 작성하거나, 비워두고 새로운 코드 생성을 요청할 수 있습니다. 오른쪽 **Instruction** 박스에 원하는 작업을 자연어(한국어 또는 영어)로 입력합니다. (예: "Hello World를 출력하는 코드를 만들고 실행해줘"). **Execute** 버튼을 누르면 에이전트가 작업을 수행하며 **Console / Output**에 진행 과정과 최종 결과를 표시하고, 필요시 코드 편집기 내용을 자동으로 업데이트합니다.
+3.  **Watch the Saga Unfold / 서사시가 펼쳐지는 것을 지켜보세요**:
+    *   **EN**: On the right, in **"The Genesis Saga"** panel, you will see the agent think, plan, and act in real-time. Follow along as it builds the new application step-by-step.
+    *   **KR**: 오른쪽의 **"The Genesis Saga"** 패널에서 에이전트가 실시간으로 생각하고, 계획하고, 행동하는 것을 볼 수 있습니다. 새로운 애플리케이션이 단계별로 만들어지는 과정을 따라가 보세요.
 
-2.  **MCP Tools API Tab**:
-    *   **EN**: This tab is designed for other agents or services to use this Space as an API. You can open each tool's accordion to test its functionality individually.
-    *   **KR**: 이 탭은 다른 에이전트나 서비스가 이 Space를 API처럼 사용할 때를 위한 것입니다. 각 도구(Tool) 섹션을 열어 개별 기능을 테스트해볼 수 있습니다.
+4.  **Interact with the New World / 새로운 세계와 상호작용하세요**:
+    *   **EN**: Once the agent's status shows "Creation is Complete," a new interactive application (the Snake Game) will appear at the bottom right. Play with it directly!
+    *   **KR**: 에이전트의 상태가 "Creation is Complete"가 되면, 오른쪽 하단에 새로운 상호작용형 애플리케이션(스네이크 게임)이 나타납니다. 바로 플레이해보세요!