bhaveshgoel07 commited on
Commit
35aaea9
Β·
1 Parent(s): 29bd116

Docs: Update README for MCP Hackathon submission with tags and sponsor info

Browse files
Files changed (1) hide show
  1. README.md +87 -59
README.md CHANGED
@@ -4,98 +4,126 @@ emoji: 🧠
4
  colorFrom: blue
5
  colorTo: purple
6
  sdk: gradio
7
- sdk_version: 6.0.1
8
  app_file: app.py
9
  pinned: false
10
  license: mit
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  # 🧠 NeuroAnim - AI-Powered Educational Animation Generator
14
 
15
- NeuroAnim is an AI-powered system that automatically generates educational STEM animations with narration and quiz questions. Simply enter a topic, and watch as AI creates a complete animated video!
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
  ## 🎯 Features
18
 
19
- - **🎨 Automatic Animation Generation**: Creates professional Manim animations from topic descriptions
20
- - **πŸ—£οΈ AI Narration**: Generates educational narration scripts tailored to your audience
21
- - **πŸ”Š Text-to-Speech**: Converts narration to high-quality audio
22
- - **πŸ“Ή Video Production**: Renders and merges video with synchronized audio
23
- - **❓ Quiz Generation**: Creates assessment questions to test understanding
24
- - **πŸŽ“ Multi-Level Support**: Content appropriate for elementary through PhD levels
25
 
26
  ## πŸš€ How to Use
27
 
28
- 1. **Enter a Topic**: Type any STEM concept (e.g., "Pythagorean Theorem", "Photosynthesis", "Newton's Laws")
29
- 2. **Select Audience**: Choose the appropriate education level
30
- 3. **Set Duration**: Pick animation length (0.5-10 minutes)
31
- 4. **Choose Quality**: Select video quality (higher = slower but better)
32
- 5. **Generate**: Click the button and wait for your animation!
33
 
34
- ## πŸ’‘ Example Topics
35
 
36
- - **Mathematics**: Pythagorean Theorem, Quadratic Formula, Circle Area Derivation
37
- - **Physics**: Newton's Laws, Laws of Motion, Wave Properties
38
- - **Biology**: Photosynthesis, Cell Division, DNA Structure
39
- - **Computer Science**: Binary Numbers, Sorting Algorithms, Data Structures
40
 
41
- ## πŸ”§ Technology Stack
 
42
 
43
- - **Manim Community Edition**: Mathematical animation engine
44
- - **Hugging Face Models**: AI-powered content generation
45
- - **ElevenLabs**: High-quality text-to-speech synthesis
46
- - **Blaxel**: Cloud-based secure rendering
47
- - **Gradio**: Interactive web interface
48
 
49
- ## πŸ”‘ Setup Requirements
 
 
 
50
 
51
- To run this space, you need:
52
 
53
- 1. **Hugging Face API Key**: For AI content generation (required)
54
- 2. **ElevenLabs API Key**: For high-quality TTS (optional, falls back to HF TTS)
55
- 3. **Blaxel API Key**: For cloud rendering (optional, can use local rendering)
56
 
57
- Set these as **Secrets** in your Hugging Face Space settings:
58
- - `HUGGINGFACE_API_KEY`
59
- - `ELEVENLABS_API_KEY` (optional)
60
- - `BLAXEL_API_KEY` (optional)
61
- - `MANIM_SANDBOX_IMAGE` (optional, for Blaxel cloud rendering)
62
 
63
  ## πŸ“ Tips for Best Results
64
 
65
- - **Be Specific**: Instead of "math", try "solving linear equations" or "area of a circle"
66
- - **Choose Right Audience**: Match the complexity level to your target viewers
67
- - **Optimal Duration**: 1.5-3 minutes works best for most concepts
68
- - **Review Generated Content**: Check the narration and code tabs to see what was created
69
-
70
- ## 🎬 How It Works
71
-
72
- 1. **Concept Planning**: AI analyzes your topic and creates an educational plan
73
- 2. **Script Writing**: Generates age-appropriate narration aligned with learning objectives
74
- 3. **Code Generation**: Creates Manim Python code for visual representation
75
- 4. **Rendering**: Executes Manim to produce the base animation
76
- 5. **Audio Synthesis**: Converts narration to speech using TTS
77
- 6. **Final Production**: Merges video and audio into complete animation
78
- 7. **Assessment**: Generates quiz questions for the content
79
 
80
  ## πŸ“š Use Cases
81
 
82
- - **Teachers**: Create engaging lesson materials
83
- - **Students**: Visualize complex concepts for better understanding
84
- - **Content Creators**: Produce educational YouTube/social media content
85
- - **Tutors**: Generate custom explanations for specific topics
86
- - **Course Developers**: Build comprehensive educational video libraries
87
 
88
  ## 🀝 Contributing
89
 
90
- NeuroAnim is open source! Visit the [GitHub repository](https://github.com/yourusername/manim-agent) to:
91
- - Report bugs or suggest features
92
- - Submit pull requests with improvements
93
- - Share your generated animations
94
 
95
  ## πŸ“„ License
96
 
97
- MIT License - Free to use for educational and commercial purposes
98
 
99
  ---
100
 
101
- Made with ❀️ for educational content creation
 
4
  colorFrom: blue
5
  colorTo: purple
6
  sdk: gradio
7
+ sdk_version: 5.0.0
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
+ tags:
12
+ - building-mcp-track-creative
13
+ - mcp-in-action-track-creative
14
+ - agent-course
15
+ - agents
16
+ - manim
17
+ - education
18
+ - mcp
19
  ---
20
 
21
  # 🧠 NeuroAnim - AI-Powered Educational Animation Generator
22
 
23
+ **NeuroAnim** is an autonomous AI agent that generates professional-quality educational STEM animations. It orchestrates multiple AI models and tools using the **Model Context Protocol (MCP)** to plan, script, code, render, and narrate educational videos automatically.
24
+
25
+ ---
26
+
27
+ ## πŸ† Hackathon Submission
28
+
29
+ This project is submitted to the **MCP Hackathon** under the following tracks:
30
+
31
+ ### πŸ”§ Track 1: Building MCP (Creative)
32
+ **Tag:** `building-mcp-track-creative`
33
+ We built two custom MCP servers that extend LLM capabilities:
34
+ 1. **`mcp-renderer`**: A specialized server for Manim code generation, validation, and secure sandboxed rendering using **Blaxel**.
35
+ 2. **`mcp-creative`**: A creative server for educational concept planning, scriptwriting, and quiz generation using **Hugging Face** models.
36
+
37
+ ### πŸ€– Track 2: MCP in Action (Creative)
38
+ **Tag:** `mcp-in-action-track-creative`
39
+ NeuroAnim is a complete autonomous agent that:
40
+ - **Plans**: Deconstructs complex STEM topics into teachable concepts.
41
+ - **Reasons**: Decides on the best visual metaphors and analogies for the target audience.
42
+ - **Executes**: Writes Python code, renders video, generates audio, and merges assets into a final product.
43
+
44
+ ### 🏒 Sponsor Integrations
45
+ - **Blaxel**: Used for secure, scalable cloud rendering of Manim animations (Blaxel Choice Award).
46
+ - **ElevenLabs**: Used for high-quality, life-like narration (ElevenLabs Category Award).
47
+ - **Hugging Face**: Hosted on Spaces, utilizing HF Inference API for reasoning and generation.
48
+
49
+ ---
50
+
51
+ ## πŸ”— Submission Links
52
+
53
+ - **Social Media Post**: [LINK_TO_SOCIAL_MEDIA_POST] (e.g., X/Twitter, LinkedIn)
54
+ - **Demo Video**: [LINK_TO_DEMO_VIDEO] (YouTube/Loom)
55
+
56
+ ---
57
+
58
+ ## πŸ‘₯ Team Members
59
+
60
+ - **[Your_HF_Username]**
61
+ - *[Add other team members here]*
62
+
63
+ ---
64
 
65
  ## 🎯 Features
66
 
67
+ - **🎨 Automatic Animation Generation**: Creates professional Manim animations from topic descriptions.
68
+ - **πŸ—£οΈ AI Narration**: Generates educational narration scripts tailored to your audience.
69
+ - **πŸ”Š Text-to-Speech**: Converts narration to high-quality audio using **ElevenLabs** (or HF fallback).
70
+ - **☁️ Cloud Rendering**: Uses **Blaxel** sandboxes for secure and fast video rendering.
71
+ - **❓ Quiz Generation**: Creates assessment questions to test understanding.
72
+ - **πŸŽ“ Multi-Level Support**: Content appropriate for elementary through PhD levels.
73
 
74
  ## πŸš€ How to Use
75
 
76
+ 1. **Enter a Topic**: Type any STEM concept (e.g., "Pythagorean Theorem", "Photosynthesis", "Newton's Laws").
77
+ 2. **Select Audience**: Choose the appropriate education level.
78
+ 3. **Set Duration**: Pick animation length (0.5-10 minutes).
79
+ 4. **Generate**: Click the button and watch the agent work!
 
80
 
81
+ ## πŸ”§ Technology Stack & Architecture
82
 
83
+ NeuroAnim uses a modular agentic architecture built on **MCP**:
 
 
 
84
 
85
+ ### 1. The Orchestrator (Agent)
86
+ The central brain that coordinates the workflow. It connects to MCP servers to execute tasks.
87
 
88
+ ### 2. Renderer MCP Server (`mcp-servers/renderer.py`)
89
+ - **Tools**: `write_manim_file`, `render_manim_animation`, `merge_video_audio`
90
+ - **Tech**: **Blaxel** (Sandboxed Execution), **FFmpeg**, **Manim Community**
91
+ - **Innovation**: Solves the "arbitrary code execution" risk by running generated Python code in secure Blaxel sandboxes.
 
92
 
93
+ ### 3. Creative MCP Server (`mcp-servers/creative.py`)
94
+ - **Tools**: `plan_concept`, `generate_narration`, `generate_manim_code`, `generate_quiz`
95
+ - **Tech**: **Hugging Face Inference API** (Qwen/Llama models), **ElevenLabs API**
96
+ - **Innovation**: Uses chain-of-thought prompting to ensure educational accuracy and visual creativity.
97
 
98
+ ## πŸ”‘ Setup Requirements
99
 
100
+ To run this space, you need to configure the following **Secrets** in your Space settings:
 
 
101
 
102
+ 1. `HUGGINGFACE_API_KEY` (Required): For AI content generation.
103
+ 2. `ELEVENLABS_API_KEY` (Optional): For high-quality narration (highly recommended).
104
+ 3. `BLAXEL_API_KEY` (Optional): For cloud rendering (recommended for speed/security).
105
+ 4. `MANIM_SANDBOX_IMAGE` (Optional): Custom Blaxel image for Manim.
 
106
 
107
  ## πŸ“ Tips for Best Results
108
 
109
+ - **Be Specific**: Instead of "math", try "solving linear equations" or "area of a circle".
110
+ - **Choose Right Audience**: Match the complexity level to your target viewers.
111
+ - **Optimal Duration**: 1.5-3 minutes works best for most concepts.
 
 
 
 
 
 
 
 
 
 
 
112
 
113
  ## πŸ“š Use Cases
114
 
115
+ - **Teachers**: Create engaging lesson materials.
116
+ - **Students**: Visualize complex concepts for better understanding.
117
+ - **Content Creators**: Produce educational YouTube/social media content.
 
 
118
 
119
  ## 🀝 Contributing
120
 
121
+ NeuroAnim is open source! We welcome contributions to extend the MCP capabilities or add new visualization styles.
 
 
 
122
 
123
  ## πŸ“„ License
124
 
125
+ MIT License - Free to use for educational and commercial purposes.
126
 
127
  ---
128
 
129
+ *Made with ❀️ for the MCP Hackathon*