These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
SimpleAudit
SimpleAudit is a simple, extensible, local-first framework for multilingual auditing and red-teaming of AI systems via adversarial probing. Developed by Simula/SimulaMet in collaboration with the Norwegian Directorate of Health, it enables systematic testing of safety and reliability across scenarios including healthcare and retrieval-augmented generation (RAG).
The framework supports open-source models running locally (no external APIs required) and can optionally evaluate API-hosted models, making it adaptable across deployment setups. It aims to make safety auditing accessible with minimal setup while encouraging reproducible evaluations and transparent scenario design. SimpleAudit does not collect or transmit user data by default. The project is open source (MIT), is a verified Digital Public Good, and provides standards/best practices for creating custom test scenarios.
About the tool
You can click on the links to see the associated tools
Developing organisation(s):
Tool type(s):
Objective(s):
Impacted stakeholders:
Purpose(s):
Country/Territory of origin:
Lifecycle stage(s):
Type of approach:
Usage rights:
License:
Target groups:
Target users:
Stakeholder group:
Geographical scope:
People involved:
Risk management stage(s):
Technology platforms:
Programming languages:
Tags:
- accountability
- auditing
- red-teaming
- digital public good
- llm evaluation
Use Cases
Would you like to submit a use case for this tool?
If you have used this tool, we would love to know more about your experience.
Add use case
Partnership on AI
