riskbench-suite 0.1.0

A comprehensive toolkit for end-to-end risk-aware benchmarking of autonomous agents

RiskBench Suite

A comprehensive toolkit for end-to-end risk-aware benchmarking of autonomous agents.

Features

• 🔍 Task specification and execution
• 📊 Risk metrics calculation and monitoring
• 🌐 Interactive web dashboard
• 🐳 Docker support
• 📈 Prometheus metrics integration

Quick Start

# Install from PyPI
pip install riskbench-suite

# Or with Poetry
poetry add riskbench-suite

Usage

1. Define a task:

name: MyTask
description: A sample task
environment:
  type: SeleniumEnv
  config:
    url: https://example.com
success_criteria:
  - type: ElementPresent
    selector: "#success-message"
risk_metrics:
  - type: CVaR
    alpha: 0.9
    threshold: 100.0

2. Run the task:

riskbench run task.yaml

3. View results in the dashboard:

riskbench dashboard
# Open http://localhost:8000

Documentation

Full documentation is available at docs/.

Contributing

We welcome contributions! Please see our Contributing Guide.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If you use RiskBench Suite in your research, please cite:

@software{riskbench_suite,
  title = {RiskBench Suite},
  author = {Your Name},
  year = {2025},
  url = {https://github.com/yourusername/riskbench-suite}
}