# Giskard

> Open-source Python library for testing agentic systems: scenario-based checks and LLM-as-judge evals (giskard-checks) plus a vulnerability scanner for red teaming (giskard-scan).

- id: `giskard`
- category: Evals & Observability (`evals-observability`)
- url: https://www.giskard.ai/
- repo: https://github.com/Giskard-AI/giskard-oss
- docs: https://docs.giskard.ai/oss
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: evals, red-teaming, llm-as-judge, testing, python, open-source
- llms.txt: https://docs.giskard.ai/llms.txt
- related: DeepEval (https://indexagentica.com/entries/deepeval/); DeepTeam (https://indexagentica.com/entries/deepteam/); Promptfoo (https://indexagentica.com/entries/promptfoo/); Ragas (https://indexagentica.com/entries/ragas/); Inspect (https://indexagentica.com/entries/inspect-ai/)
- sources: https://github.com/Giskard-AI/giskard-oss , https://docs.giskard.ai/oss , https://pypi.org/project/giskard/
- added: 2026-10-20
- updated: 2026-10-20
- last verified: 2026-10-20
- featured in: Open-source red-teaming tools for LLM apps and agents (https://indexagentica.com/compare/llm-red-teaming-tools/)
- maintainer: Giskard
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/giskard/
- json: https://indexagentica.com/api/entries/giskard.json

Giskard v3 is a modular rewrite for dynamic, multi-turn testing of AI agents: `pip install giskard` for checks, `giskard[scan]` for the scanner (prompt injection, jailbreaks, harmful content, RAG and quality evaluation), plus provider extras for LLM judges. Requires Python 3.12+. Optional aggregated telemetry sends no prompts or outputs and is turned off with `DO_NOT_TRACK=1` or `GISKARD_TELEMETRY_DISABLED=1`. Giskard v2 remains available but is no longer actively maintained.