🚀 Solara Skill Builder

Multi-agent AI that generates personalized learning paths for digital careers.

Solara Skill Builder uses a team of specialized AI agents powered by Google's Gemini models to create customized, structured learning paths based on your goals, experience, and available time.

---

✨ Features

• Personalized Learning Paths — Tailored to your target role, timeframe, and weekly availability
• Multi-Agent Architecture — Four specialized agents collaborate to build your curriculum:
  • 🗺️ Planner Agent — Breaks down your goal into competency blocks with dependencies
  • 🔍 Resource Researcher Agent — Uses Tavily web search to find real, verified learning resources
  • 📚 Curriculum Synthesizer Agent — Assembles a week-by-week or modular learning path
  • ✅ Evaluation Module — Scores and critiques the path for quality assurance
• Real Web Search — Resources are grounded in actual URLs via Tavily API, not hallucinated links
• URL Validation — Automatic detection of invalid or placeholder URLs with quality penalties
• Automatic Refinement — If the evaluation score is below 0.8, the path is automatically refined
• Regenerate Resources — Keep your competency plan and regenerate just the resources and curriculum
• Export to JSON — Download your learning path for use in other tools or notebooks

---

🖥️ Screenshots

The app provides a clean Streamlit interface where you:

1. Enter your learner profile (target role, timeframe, hours/week, prior experience)
2. Generate a structured learning path with modules, resources, and practice tasks
3. View evaluation scores and comments for transparency

---

🛠️ Installation

Prerequisites

• Python 3.10+
• A Google AI Studio API key for Gemini
• A Tavily API key for web search

Setup

1. Clone the repository:

   git clone https://github.com/therightjon/Solara-Labs-Skill-Builder.git
   cd Solara-Labs-Skill-Builder

2. Create a virtual environment (recommended):

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate

3. Install dependencies:

   pip install -r requirements.txt

4. Configure your API keys:

   Create a .env file in the project root:

   GEMINI_API_KEY=your_gemini_api_key_here
   TAVILY_API_KEY=your_tavily_api_key_here

---

🚀 Usage

Run the Streamlit App

streamlit run streamlit_app.py

The app will open in your browser. Fill in your learner profile and click "Generate Learning Path".

Run the Backend Directly (CLI Test)

python agents.py

This runs a sanity check with a sample learner profile and prints the JSON result.

---

📁 Project Structure

Solara-Labs-Skill-Builder/
├── streamlit_app.py      # Streamlit frontend — UI and display logic
├── agents.py             # Multi-agent backend — all agent logic and orchestration
├── requirements.txt      # Python dependencies
├── .env                  # Environment variables (GEMINI_API_KEY) — not committed
├── .github/
│   └── copilot-instructions.md  # AI coding agent instructions
└── README.md             # This file

---

🧠 Architecture

┌─────────────────────────────────────────────────────────────────────┐
│                        generate_learning_path()                     │
│                           (Orchestrator)                            │
└─────────────────────────────────────────────────────────────────────┘
                                   │
         ┌─────────────────────────┼─────────────────────────┐
         ▼                         ▼                         ▼
┌─────────────────┐    ┌─────────────────────┐    ┌─────────────────────┐
│  Planner Agent  │───▶│ Resource Researcher │───▶│ Curriculum Synth.   │
│                 │    │       Agent         │    │       Agent         │
└─────────────────┘    │    + Tavily Search  │    └─────────────────────┘
                       │    + URL Validation │              │
                       └─────────────────────┘              ▼
                                                 ┌─────────────────────┐
                                                 │  Evaluation Module  │
                                                 │  + URL Penalty      │
                                                 └─────────────────────┘
                                                            │
                                           (if score < 0.8) │
                                                            ▼
                                                 ┌─────────────────────┐
                                                 │   Refinement Step   │
                                                 └─────────────────────┘

All agents use the centralized call_llm() function which:

• Wraps Google's Gemini API (gemini-2.5-flash)
• Enforces JSON output via response_mime_type="application/json"
• Handles parsing and error recovery

---

🔧 Configuration

Environment Variable	Description	Required
GEMINI_API_KEY	Your Google AI Studio API key	Yes
TAVILY_API_KEY	Your Tavily API key for web search	Yes

---

📦 Dependencies

• streamlit — Web UI framework
• google-genai — Google Generative AI SDK for Gemini
• python-dotenv — Environment variable management
• tavily-python — Web search API for grounding resources in real URLs

Install all dependencies:

pip install -r requirements.txt

---

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

---

📄 License

This project is licensed under the Apache License 2.0 — see the LICENSE file for details.

---

🙏 Acknowledgments

• Built with Streamlit
• Powered by Google Gemini
• Web search by Tavily
• Inspired by the need for accessible, personalized tech education