Switch from Modal to Hugging Face Spaces deployment

- Remove modal_app.py and GitHub Actions workflow
- Update README with HF Spaces frontmatter
- Clean up requirements.txt

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.github/workflows/deploy.yml

@@ -1,32 +0,0 @@
-name: Deploy to Modal
-
-on:
-  push:
-    branches:
-      - main
-
-jobs:
-  deploy:
-    name: Deploy
-    runs-on: ubuntu-latest
-    env:
-      MODAL_TOKEN_ID: ${{ secrets.MODAL_TOKEN_ID }}
-      MODAL_TOKEN_SECRET: ${{ secrets.MODAL_TOKEN_SECRET }}
-
-    steps:
-      - name: Checkout Repository
-        uses: actions/checkout@v4
-
-      - name: Install Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-
-      - name: Install Modal
-        run: |
-          python -m pip install --upgrade pip
-          pip install modal
-
-      - name: Deploy to Modal
-        run: |
-          modal deploy modal_app.py

README.md

@@ -1,3 +1,17 @@
+---
+title: Explainor
+emoji: 🎭
+colorFrom: purple
+colorTo: orange
+sdk: gradio
+sdk_version: 5.0.0
+app_file: app.py
+pinned: false
+license: mit
+tags:
+  - mcp-in-action-track-creative
+---
+
 # 🎭 Explainor
 
 > **Learn anything through the voice of your favorite characters!**
@@ -6,8 +20,6 @@
 [![Track](https://img.shields.io/badge/Track-MCP%20in%20Action-blue)](https://huggingface.co/MCP-1st-Birthday)
 [![Category](https://img.shields.io/badge/Category-Creative-green)](https://huggingface.co/MCP-1st-Birthday)
 
-**Tags:** `mcp-in-action-track-creative`
-
 ---
 
 ## 🌟 What is Explainor?
@@ -23,10 +35,6 @@ Explainor is an AI agent that takes any topic you want to learn about and explai
 | 🏄 **Surfer Dude** | "Brooo", chill vibes, wave metaphors |
 | 🧙 **Yoda** | Inverted syntax, wise, Force references |
 
-## 🎬 Demo
-
-[Demo Video Placeholder]
-
 ## 🛠️ How It Works
 
 1. **Enter a topic** - Anything from "Quantum Computing" to "How do volcanoes work?"
@@ -48,94 +56,13 @@ Make the explanation even more tailored by choosing your audience:
 | 👵 My confused grandmother | Extra simple, patient |
 | 🤖 A skeptical robot | Logical, evidence-based |
 | 👽 An alien visiting Earth | Explain Earth concepts |
-| 🧟 A zombie | Very short, simple words |
-| 🦊 A very smart fox | Clever, quick |
-| 👔 A stressed CEO | Bottom-line focused |
-| 🎮 A distracted gamer | Keep it engaging |
-
-## 🔌 MCP Server Integration
-
-This app is a **real MCP server**! When running, it exposes its functionality as tools that other AI agents can call via the Model Context Protocol.
-
-**MCP Endpoint:** `http://localhost:7860/gradio_api/mcp/`
-
-This means:
-- Other AI agents can use Explainor as a tool
-- Enables agent-to-agent communication
-- Part of the growing MCP ecosystem
 
 ## 🚀 Tech Stack
 
-- **MCP**: Model Context Protocol - App exposes itself as an MCP server
 - **LLM**: [Nebius AI](https://nebius.com) - Llama 3.3 70B for intelligent explanations
 - **TTS**: [ElevenLabs](https://elevenlabs.io) - Realistic voice synthesis with character-matched voices
 - **Web Search**: DuckDuckGo API for topic research
 - **Frontend**: [Gradio](https://gradio.app) with MCP integration
-- **Deployment**: [Modal](https://modal.com) - Serverless infrastructure
-
-## 💻 Local Development
-
-### Prerequisites
-
-- Python 3.11+
-- Nebius API key
-- ElevenLabs API key
-
-### Setup
-
-```bash
-# Clone the repository
-git clone https://huggingface.co/spaces/MCP-1st-Birthday/explainor
-
-# Install dependencies
-pip install -r requirements.txt
-
-# Set up environment variables
-cp .env.example .env
-# Edit .env with your API keys
-
-# Run locally
-python app.py
-```
-
-### Environment Variables
-
-```bash
-NEBIUS_API_KEY=your_nebius_api_key_here
-ELEVENLABS_API_KEY=your_elevenlabs_api_key_here
-```
-
-## 🌐 Deployment
-
-### Modal Deployment
-
-```bash
-# Set up Modal secrets
-modal secret create nebius-api-key NEBIUS_API_KEY=your_key
-modal secret create elevenlabs-api-key ELEVENLABS_API_KEY=your_key
-
-# Deploy
-modal deploy modal_app.py
-```
-
-### Hugging Face Spaces
-
-This app is designed to run on Hugging Face Spaces with the Gradio SDK.
-
-## 📁 Project Structure
-
-```
-explainor/
-├── app.py              # Main Gradio application
-├── modal_app.py        # Modal deployment config
-├── requirements.txt    # Python dependencies
-├── src/
-│   ├── __init__.py
-│   ├── personas.py     # Persona definitions & voice mappings
-│   ├── agent.py        # Agent logic & web search
-│   └── tts.py          # ElevenLabs integration
-└── README.md
-```
 
 ## 🏆 Hackathon Submission
 

modal_app.py

@@ -1,171 +0,0 @@
-"""Modal deployment configuration for Explainor.
-
-Deploy with: modal deploy modal_app.py
-Run locally: modal serve modal_app.py
-"""
-
-import modal
-
-# Define the Modal app
-app = modal.App("explainor-v6")
-
-# Create image with dependencies
-image = (
-    modal.Image.debian_slim(python_version="3.11")
-    .pip_install(
-        "gradio==4.44.1",  # Use older stable version without aggressive SSE
-        "elevenlabs>=1.0.0",
-        "httpx>=0.25.0",
-        "python-dotenv>=1.0.0",
-        "fastapi",
-        "uvicorn",
-    )
-    .add_local_dir("src", remote_path="/app/src", copy=True)
-)
-
-
-@app.function(
-    image=image,
-    secrets=[
-        modal.Secret.from_name("nebius-api-key"),
-        modal.Secret.from_name("elevenlabs-api-key"),
-    ],
-    timeout=600,
-    scaledown_window=300,
-)
-@modal.web_server(port=7860, startup_timeout=120)
-def serve():
-    """Serve the Gradio app via web_server."""
-    import subprocess
-    import sys
-    import os
-
-    os.chdir("/app")
-    sys.path.insert(0, "/app")
-
-    # Write a standalone gradio script
-    script = '''
-import sys
-sys.path.insert(0, "/app")
-
-import os
-import tempfile
-import gradio as gr
-from src.personas import get_persona_names, get_persona
-from src.agent import run_agent
-from src.tts import generate_speech
-
-def format_sources(sources):
-    if not sources:
-        return "*No external sources used*"
-    md = ""
-    for i, src in enumerate(sources, 1):
-        if src.get("url"):
-            md += f"{i}. [{src['title']}]({src['url']})\\n"
-        else:
-            md += f"{i}. {src['title']} ({src.get('source', 'General')})\\n"
-    return md
-
-def format_mcp_tools(tools):
-    if not tools:
-        return "*No tools used*"
-    md = "**Agent Tool Calls:**\\n\\n"
-    for tool in tools:
-        md += f"| {tool['icon']} | `{tool['name']}` | {tool['desc']} |\\n"
-    return md
-
-def explain_topic(topic, persona_name, audience=""):
-    import traceback
-    if not topic.strip():
-        return "Please enter a topic!", "", "", ""
-    if not persona_name:
-        persona_name = "5-Year-Old"
-
-    # Check API key
-    nebius_key = os.getenv("NEBIUS_API_KEY")
-    if not nebius_key:
-        available_keys = [k for k in os.environ.keys() if "KEY" in k or "API" in k or "NEBIUS" in k]
-        return f"Error: NEBIUS_API_KEY not found. Available: {available_keys}", "", "", ""
-
-    steps_log = []
-    explanation = ""
-    sources = []
-    mcp_tools = []
-    try:
-        for update in run_agent(topic, persona_name, audience):
-            if update["type"] == "step":
-                steps_log.append(f"**{update['title']}**\\n{update['content']}")
-                if update["step"] == "research_done" and "sources" in update:
-                    sources = update["sources"]
-            elif update["type"] == "result":
-                explanation = update["explanation"]
-                sources = update.get("sources", sources)
-                mcp_tools = update.get("mcp_tools", [])
-    except Exception as e:
-        return f"Error: {str(e)}\\n\\n{traceback.format_exc()}", "", "\\n\\n---\\n\\n".join(steps_log), ""
-    return explanation, format_sources(sources), "\\n\\n---\\n\\n".join(steps_log), format_mcp_tools(mcp_tools)
-
-def generate_audio(explanation, persona_name):
-    if not explanation or not explanation.strip():
-        return None
-    if not persona_name:
-        persona_name = "5-Year-Old"
-    try:
-        persona = get_persona(persona_name)
-        audio_bytes = generate_speech(explanation, persona["voice_id"], persona.get("voice_settings"))
-        with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as f:
-            f.write(audio_bytes)
-            return f.name
-    except Exception as e:
-        raise gr.Error(f"Audio generation failed: {str(e)}")
-
-# Get persona names as a static list
-persona_names = list(get_persona_names())
-
-with gr.Blocks(title="Explainor") as demo:
-    gr.Markdown("# Explainor\\n### Learn anything through the voice of your favorite characters!")
-    with gr.Row():
-        topic_input = gr.Textbox(label="Topic", placeholder="e.g., Quantum Computing")
-        persona_dropdown = gr.Dropdown(choices=persona_names, value="5-Year-Old", label="Persona")
-    audience_dropdown = gr.Dropdown(
-        choices=["Just me", "Confused grandmother", "Skeptical robot", "Alien"],
-        value="Just me",
-        label="Audience"
-    )
-    explain_btn = gr.Button("Explain!", variant="primary")
-    explanation_output = gr.Textbox(label="Explanation", lines=6)
-    read_aloud_btn = gr.Button("Read Aloud")
-    audio_output = gr.Audio(label="Listen", type="filepath", autoplay=True)
-    with gr.Accordion("Tools", open=False):
-        mcp_output = gr.Markdown("")
-    with gr.Accordion("Sources", open=False):
-        sources_output = gr.Markdown("")
-    with gr.Accordion("Trace", open=False):
-        steps_output = gr.Markdown("")
-
-    def do_explain(topic, persona, audience):
-        aud = "" if "Just me" in audience else audience
-        return explain_topic(topic, persona, aud)
-
-    explain_btn.click(
-        fn=do_explain,
-        inputs=[topic_input, persona_dropdown, audience_dropdown],
-        outputs=[explanation_output, sources_output, steps_output, mcp_output],
-    )
-    read_aloud_btn.click(
-        fn=generate_audio,
-        inputs=[explanation_output, persona_dropdown],
-        outputs=[audio_output],
-    )
-
-if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)
-'''
-
-    # Write to file and run
-    with open("/app/run_gradio.py", "w") as f:
-        f.write(script)
-
-    # Run the script with environment variables
-    env = os.environ.copy()
-    subprocess.Popen([sys.executable, "/app/run_gradio.py"], env=env)

requirements.txt

@@ -1,6 +1,4 @@
 gradio[mcp]>=5.0.0
 elevenlabs>=1.0.0
-openai>=1.0.0
 httpx>=0.25.0
 python-dotenv>=1.0.0
-modal>=0.64.0