Giskard Library

Giskard Library is a Python package for testing and evaluating AI applications. It provides a solid foundation for developers to ensure quality and reliability in LLM-based systems, RAG applications, and AI agents.

The library is available on GitHub and formed the basis for the Red Teaming LLM Applications course on DeepLearning.AI.

Giskard v3 is a major rewrite and includes new features such as Checks.

Note

Looking for Giskard v2 features? Scan is available in v3 through the scan extra: install pip install --pre "giskard[scan]". RAGET is not available in v3 yet — use the Giskard v2 documentation ↗ if you need it, and follow the v3 roadmap ↗ for progress.

Resources and support

• Documentation: Explore the Checks documentation for detailed guides
• Agent Skills: Install Giskard Agent Skills to give Claude Code, Cursor, and other coding agents drop-in workflows for Giskard tasks
• Contributing: See Contribute to Giskard for the official guide, AI-agent notes, and repos to star
• Examples: Check our GitHub repository ↗ for more examples
• Community: Join our Discord ↗ for support and discussions