G
Giskard
Open SourceModel Evaluation & BenchmarkingOpen-source testing framework that scans ML models and LLM apps for vulnerabilities and quality issues.
Last verified
overview
Giskard scans LLM applications for hallucination, harmful generation, injection susceptibility, and bias, producing structured test suites from detected issues. Backed by European research funding, it aligns its checks with EU AI Act expectations, which makes it popular with teams preparing for conformity assessments.
- Automated vulnerability scanning for LLM apps - Test suite generation from findings - RAG evaluation toolkit - EU AI Act aligned quality checks
core features
- Automated vulnerability scanning for LLM apps
- Test suite generation from findings
- RAG evaluation toolkit
- EU AI Act aligned quality checks
target frameworks
EU AI Act
faq
Giskard — frequently asked questions
- What is Giskard?
- Giskard scans LLM applications for hallucination, harmful generation, injection susceptibility, and bias, producing structured test suites from detected issues. Backed by European research funding, it aligns its checks with EU AI Act expectations, which makes it popular with teams preparing for conformity assessments.
- Which compliance frameworks does Giskard support?
- Giskard addresses EU AI Act, OWASP LLM Top 10. Check the vendor site for the latest scope and any region-specific certifications.
- How much does Giskard cost?
- Giskard is open source, so you can self-host it for free. Managed/cloud tiers may be offered separately.
- Who is Giskard for?
- Teams working on model evaluation & benchmarking — particularly those that need to evidence EU AI Act, OWASP LLM Top 10 controls.
- Is Giskard open source?
- Yes — the source code is available on GitHub at https://github.com/Giskard-AI/giskard.