AI Potluck
Product / UX / Safety & Guardrails

Giskard

Giskard

Python library for testing and red-teaming LLM and agentic systems. Giskard Scan automatically probes an application for vulnerabilities including prompt injection, harmful output and hallucination, and Giskard Checks runs scenario-based evaluations including multi-turn agent validation.

Giskard's v3 line is a rewrite aimed at dynamic, multi-turn testing of agents; the v2 Scan is now vulnerability_scan, shipped in giskard-scan alongside knowledge-base and RAG evaluation. The repo is Giskard-AI/giskard-oss, which the old Giskard-AI/giskard path redirects to. Verified 2026-08-13 via GitHub.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public
self-host
yes
service
none(per the repo)
core-gated
ungated

Fully open source: an Apache-2.0 Python library, self-hostable, with no commercial tier mentioned on the repo. The repo now lives at Giskard-AI/giskard-oss and the project has shipped a v3 rewrite; neither moves the score.

  • https://github.com/Giskard-AI/giskard recorded 2026-08-13

    Redirects to Giskard-AI/giskard-oss, whose metadata records license spdxId - Apache-2.0. The README installs the whole thing with pip and documents running it locally; the only paid-adjacent ask on the page is GitHub sponsorship, and there is no enterprise directory, commercial edition or license key, so nothing is withheld from the published source.

Adoption

2 low confidence
2.0

5,748 stargazers, which bands at 1K-10K stars, level 2, and a stars proxy never rises above 3 because a star is not a use. A download route does exist and was checked rather than assumed away: the giskard package on PyPI shows 24,423 downloads in the trailing 30 days, also level 2 on the software scale, so both signals agree on the band.

Capability

4 medium confidence
4.0

Combines automated red-team scanning with structured evaluation; broad coverage for both safety and reliability. The v3 rewrite renamed Scan to vulnerability_scan and ships it in giskard-scan alongside knowledge-base and RAG evaluation, so the shape of the coverage moved but not its breadth, and the band holds.

  • https://github.com/Giskard-AI/giskard recorded 2026-08-13

    README describes 'Evals, Red Teaming and Test Generation for Agentic Systems' and a vulnerability scanner covering 'red teaming, prompt injection, jailbreaks & harmful content' (vulnerability_scan, successor of v2 Scan) plus knowledge-base and RAG quality evaluation, with v3 built for dynamic multi-turn testing of agents.

Verified 2026-08-13