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.
Origin
SUBMIT A TOOL
If you have a tool that you think should be featured in the Catalogue of Tools & Metrics for Trustworthy AI, we would love to hear from you!
Submitgarak, LLM vulnerability scanner
TechnicalUploaded on Mar 20, 2026garak is an open-source LLM vulnerability scanner developed by NVIDIA that probes large language models for security weaknesses including prompt injection, jailbreaks, hallucination, toxicity, data leakage, and misinformation.
Objective(s)
OpenEnv
TechnicalUploaded on Mar 20, 2026OpenEnv is a framework for evaluating AI agents against real systems rather than simulations. It provides a standardised way to connect agents to real tools and workflows while preserving the structure needed for consistent and reliable evaluation.
Objective(s)
Resaro's Approved Intelligence Platform (AIP)
TechnicalProceduralUploaded on Mar 20, 2026The Approved Intelligence Platform (AIP) provides modular, scenario-based testing workflows to evaluate mission-critical AI systems in defence, public safety, and critical civil use cases. It delivers a comprehensive, end-to-end testing environment based on a proprietary AI trust ontology with measurable AI Solutions Quality Indicators (ASQI) for the testing, evaluation, validation and verification of software solutions with different AI modalities.
Objective(s)
Resaro AI Solutions Quality Index Engineer (ASQI Engineer)
TechnicalUploaded on Jan 19, 2026ASQI Engineer is an open-source framework for testing and assuring AI systems. Built for scale and reliability, it uses containerised test packages, automated assessments, and repeatable workflows to make evaluation transparent and robust. With ASQI Engineer, organisations also run ASQIs that they have created themselves, giving teams full control and confidence in AI quality.
Objective(s)
Resaro AI Solutions Quality Index (ASQI)
TechnicalProceduralUploaded on Mar 20, 2026The Resaro AI Solutions Quality Index (ASQI) provides a transparent, use-case-specific measure of AI quality — for applications such as customer chat services, object recognition, deepfake detection, or x-ray anomaly identification.
Objective(s)
Inspect
TechnicalUploaded on Oct 9, 2025An open-source framework for large language model evaluations. Inspect can be used for a broad range of evaluations that measure coding, agentic tasks, reasoning, knowledge, behavior, and multi-modal understanding.
Objective(s)
Voiceitt
TechnicalEducationalUploaded on Oct 1, 2025An AI-powered speech recognition app that adapts to users' unique speech patterns, facilitating communication for individuals with speech impairments.
Objective(s)
Related lifecycle stage(s)
Operate & monitorReadSpeaker
TechnicalUploaded on Aug 27, 2025ReadSpeaker is a SaaS-based text-to-speech platform providing natural-sounding, multilingual voices for seamless integration in web, document, and application environments.
Objective(s)
Related lifecycle stage(s)
Operate & monitoraRTIFICIAL iNTELLIGENCE for the Deaf
TechnicalUploaded on Aug 27, 2025aiD leverages artificial intelligence to improve communication accessibility for deaf and hard-of-hearing individuals through advanced speech-to-text and sign language technologies.
Objective(s)
Dytective
TechnicalEducationalUploaded on Aug 1, 2025Dytective by Change Dyslexia is an innovative AI-powered tool designed to detect the risk of dyslexia in children quickly and reliably. Developed in collaboration with researchers, Dytective combines language exercises with machine learning to screen for dyslexia in just 15 minutes. Backed by scientific validation and used by schools and families worldwide, it empowers early intervention and promotes equal opportunities in education.
Objective(s)
SeismicAI's Earthquake Early Warning Systems
TechnicalEducationalMexicoUnited StatesIsraelUploaded on May 19, 2025SeismicAI is a provider of innovative Earthquake Early Warning Systems (EEW) ensuring earthquake preparedness. SeismicAI's algorithms utilise local sensors to issue high-precision alerts for earthquake preparedness. The system covers the full early warning cycle - from monitoring and reporting, through alerts, to optionally triggering automated preventive actions.
Objective(s)
Related lifecycle stage(s)
Operate & monitorRisk Atlas Nexus
TechnicalIrelandUploaded on May 2, 2025Risk Atlas Nexus provides tooling to connect fragmented AI governance resources through a community-driven approach to curation of linkages between risks, datasets, benchmarks, and mitigations. It transforms abstract risk definitions into actionable AI governance workflows.
Objective(s)
Eticas Bias
TechnicalUnited StatesUploaded on Mar 24, 2025An open-source Python library designed for developers to calculate fairness metrics and assess bias in machine learning models. This library provides a comprehensive set of tools to ensure transparency, accountability, and ethical AI development.
Objective(s)
COMPL-AI
TechnicalSwitzerlandEuropean UnionUploaded on Jan 24, 2025COMPL-AI is an open-source compliance-centered evaluation framework for Generative AI models
Objective(s)
MLPerf Client
TechnicalUnited StatesUploaded on Jan 8, 2025MLPerf Client is a benchmark for Windows and macOS, focusing on client form factors in ML inference scenarios like AI chatbots, image classification, etc. The benchmark evaluates performance across different hardware and software configurations, providing command line interface.
Objective(s)
AIxploit
TechnicalFranceUploaded on Dec 6, 2024AIxploit is a tool designed to evaluate and enhance the robustness of Large Language Models (LLMs) through adversarial testing. This tool simulates various attack scenarios to identify vulnerabilities and weaknesses in LLMs, ensuring they are more resilient and reliable in real-world applications.
Objective(s)
Mindgard
TechnicalUnited KingdomUploaded on Dec 6, 2024Continuous automated red teaming for AI, minimize security threats to AI models and applications.
Objective(s)
PyRIT
TechnicalUnited StatesUploaded on Nov 8, 2024The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.
Objective(s)
garak
TechnicalUploaded on Nov 5, 2024garak, Generative AI Red-teaming & Assessment Kit, is an LLM vulnerability scanner. Garak checks if an LLM can be made to fail.
Objective(s)
Dioptra
TechnicalUnited StatesUploaded on Sep 9, 2024Dioptra is an open source software test platform for assessing the trustworthy characteristics of artificial intelligence (AI). It helps developers on determining which types of attacks may impact negatively their model's performance.
Objective(s)
Partnership on AI
