title	emoji	colorFrom	colorTo	sdk	pinned	app_port
Power Grids Conference Dashboard	⚡	green	blue	docker	false	8080

AI-GridConf ⚡

AI-powered conference deadline tracker for power systems and grid modernization research

A modern web application and AI agent system that automatically discovers, validates, and tracks submission deadlines for top-tier power systems, transmission, distribution, and energy transition conferences including IEEE PESGM, CIGRE, and IEEE PowerTech.

✨ Features

• 🤖 AI-Powered Updates: Autonomous agents using Claude Sonnet 4 and Exa AI automatically find and validate conference deadlines
• 📅 Real-time Tracking: Never miss a submission deadline with countdown timers and calendar views
• 🔍 Smart Search: Filter conferences by tags, location, or upcoming deadlines
• 🌍 Global Coverage: Tracks major power systems conferences worldwide
• 🚀 Open Source: Built in public to help the research community

🎯 Why AI-GridConf?

Researchers and engineers in power systems, smart grids, and energy transition face a constant challenge: tracking submission deadlines across dozens of conferences. AI-GridConf solves this with:

1. Automated Discovery: AI agents search the web for conference announcements
2. Intelligent Extraction: LLMs extract structured deadline information
3. Continuous Validation: Agents verify data quality and flag issues
4. Automatic PRs: New conferences are submitted as pull requests for review

See the agents folder for technical details on the AI system.

🚀 Quick Start

Prerequisites

• Node.js (v18 or higher)
• npm or bun

Installation

# Clone the repository
git clone https://github.com/schuttpj/ai-gridconf.git
cd ai-gridconf

# Install dependencies
npm install

# Start development server
npm run dev

Open http://localhost:8080 to view the app.

🤖 AI Agent System

The project includes a sophisticated multi-agent system that autonomously maintains conference data:

# Set up Python environment
cd agents
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .

# Configure API keys
cp ../.env.example ../.env
# Edit .env and add your ANTHROPIC_API_KEY, EXA_API_KEY, and GH_TOKEN

# Run the agent
uv run python agent.py "CIGRE Canada 2025"

See agents/README.md for architecture details.

📚 Project Structure

This project is adapted from the AI Deadlines project, customized for power systems with AI agent automation. Built with Lovable and Cursor.

For adaptation instructions, see ADAPTATION_GUIDE.md.

🤝 Contributing

Contributions are very welcome! We focus on top-tier conferences in power systems, transmission, distribution, smart grids, renewable energy, and energy transition.

Adding a Conference

You can add conferences manually or let the AI agent do it for you:

Option 1: Manual Contribution

1. Fork the repository
2. Add a conference entry to src/data/conferences/
3. Follow the schema in CONTRIBUTING.md
4. Submit a pull request

Option 2: AI Agent (Recommended)

1. Run uv run python agents/agent.py "Conference Name Year"
2. The agent will search, extract, validate, and create a PR automatically

See CONTRIBUTING.md for detailed guidelines.

How to run locally

If you want to work locally using your own IDE, you can clone this repo and push changes.

The only requirement is having Node.js & npm installed - install with nvm

Follow these steps:

# Step 1: Clone the repository using the project's Git URL.
git clone https://github.com/huggingface/ai-deadlines

# Step 2: Navigate to the project directory.
cd ai-deadlines

# Step 3: Install the necessary dependencies.
npm i

# Step 4: Start the development server with auto-reloading and an instant preview.
npm run dev

This runs the app at http://localhost:8080/.

Deploy with Docker

First build the Docker image as follows: 🛠️ Development

Frontend Development

# Clone and setup
git clone https://github.com/schuttpj/ai-gridconf.git
cd ai-gridconf
npm install

# Start dev server
npm run dev  # Runs at http://localhost:8080

Agent Development

# Setup Python environment
cd agents
uv venv
source .venv/bin/activate
uv pip install -e .

# Run tests
pytest tests/

# Demo the agent
python scripts/demo_agent.py
python scripts/demo_architecture.py

gcloud auth login
gcloud auth application-default login
gcloud run deploy --source .

Technologies used

This project is built with:

• Vite
• TypeScript
• React
• shadcn-ui
• Tailwind CSS

License

This project is licensed under MIT.

Maintainers

Feel free to just open an issue. Otherwise contact @nielsrogge🛠️ Tech Stack

Frontend

• Framework: React + TypeScript + Vite
• UI: shadcn/ui + Tailwind CSS
• State: React hooks
• Deployment: Docker, Vercel

AI Agent System

• LLM: Claude Sonnet 4 (Anthropic)
• Search: Exa AI
• Runtime: Python 3.12 with uv
• Validation: Pydantic
• Architecture: Skills-based agent system

📊 Agent Architecture

User Query → Orchestrator → Skills → Output
              ↓
         ┌────────┴────────┐
         ↓                 ↓
    SearchSkill       GitSkill
    ExtractionSkill   ValidationSkill
    YAMLSkill

Each skill handles a specific task:

• SearchSkill: Find conference info using Exa AI
• ExtractionSkill: Extract structured data with Claude
• ValidationSkill: Validate schema and data quality
• YAMLSkill: Generate conference files
• GitSkill: Create branches, commits, and PRs

🚀 Deployment

Docker

docker build -t ai-gridconf .
docker run -p 8080:8080 ai-gridconf

Cloud Run

gcloud auth login
gcloud run deploy --source .

See Deploy on the cloud section above for details.

📝 License

This project is licensed under MIT.

🙏 Acknowledgments

• Adapted from AI Deadlines by HuggingFace
• Built with Lovable and Cursor
• Powered by Anthropic Claude and Exa AI

👥 Maintainers

• @schuttpj

📬 Contact

Feel free to open an issue or reach out via GitHub discussions.

---

Building in public 🚀 | AI-powered 🤖 | Community-driven 🤝