A chatbot assistant designed to help create high-quality bug reports. Vydra provides guidance and feedback throughout the bug report creation process, ensuring the reports include all the critical information developers need.

• Interactive chat interface for bug report creation
• Import existing bug reports from files or GitHub issues
• LLM-powered suggestions based on bug report best practices
• Support for multiple LLM models
• Chat history

• Node.js 18+ and npm
• Ollama with LLM models installed (default: llama3.1:8b)
• Redis (optional, falls back to in-memory storage)
• GitHub token (optional, for importing issues)

1. Clone the repository:

git clone https://github.com/Adrian2901/vydra.git
cd vydra

2. Install dependencies:

npm install

3. Configure environment variables by creating a .env.local file:

GITHUB_TOKEN=your_github_token_here  # Optional
REDIS_URL=your_redis_url_here        # Optional
MOCK_DB=false
MOCK_LLM=false

4. Make sure Ollama is running with your preferred model:

ollama run llama3.1:8b

Development mode:

npm run dev

Open http://localhost:3000 in your browser.

This project is licensed under the MIT License.

Adrian Hassa, Ionel Pop, Teodora Portase