Shypd.aiThe largest open index of AI toolsgiskard-oss is an open-source evaluation and testing library for LLM agents. It provides tools for red teaming, vulnerability scanning, and RAG evaluation to ensure AI system reliability.
Trending
About
giskard-oss is an open-source Python library designed for comprehensive evaluation and testing of agentic AI systems, including LLM agents. The latest v3 rewrite focuses on modularity and efficiency, offering a lightweight framework for dynamic, multi-turn testing. Key features include Giskard Checks for creating and applying evaluations, such as LLM-as-judge assessments, to catch regressions, validate RAG quality, and enforce safety rules. It also includes an agent vulnerability scanner for red teaming and prompt injection detection, and planned capabilities for RAG evaluation and synthetic data generation. The library supports testing various AI components, from LLMs to black-box agents and multi-step pipelines.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
