AI Verify

Input—per 1M tokens

Output—per 1M tokens

Context—tokens

WeightsClosed

About

AI Verify is an open-source toolkit for evaluating AI systems, with technical tests for fairness, explainability, and robustness in traditional machine-learning models. Users can run tests through a Portal or command line, upload results, complete process checklists, and produce standard or customized reports. AIVT 2.0 accepts tabular and image data, with a model file, preprocessing pipeline, or model API as input. Plugins extend the toolkit, and Veritas adds threshold-trade-off tests for fairness and transparency plus explainability plots. The broader framework assesses responsible implementation against 11 AI-governance principles and maps to NIST AI RMF, its Generative AI Profile, the Hiroshima Process Code of Conduct, and ISO/IEC 42001. Project Moonshot is a separate tool for LLM applications, offering benchmark testing and red teaming. AI Verify is available under the Apache 2.0 license and supports web, Linux, API, and self-hosted use. It does not set ethical standards or guarantee that tested systems are free of risk or bias, or completely safe.

Who it is for

It suits data-science and compliance users who need to assess traditional AI systems through self-assessment or third-party testing. AI owners, developers, researchers, service providers, and companies integrating the toolkit are also listed as potential users.

What is good

Includes more than eight technical tests.
Accepts tabular and image data.
Offers Portal and command-line test workflows.
Plugins and Veritas extend testing options.
Apache 2.0 license.

What to know first

Toolkit tests traditional AI applications, not LLM applications.
Supports tabular and image data types currently.
Does not guarantee systems are risk-free or unbiased.
Does not define AI ethical standards.

Verdict

AI Verify brings technical testing, governance principles, and reporting into an open-source toolkit, with a separate Moonshot tool for LLM applications. It is an evaluation aid, not a guarantee of ethical or risk-free AI.

Compared on AI governance tools

Free plan: Yesaiverifyfoundation.sg
AI system inventory: Noaiverifyfoundation.sg
Risk assessments: Yesaiverifyfoundation.sg
Policy and controls: Yesaiverifyfoundation.sg
Compliance frameworks: AI Verify Testing Framework; NIST AI RMF; NIST AI RMF Generative AI Profile; Hiroshima Process Code of Conduct; ISO/IEC 42001aiverifyfoundation.sg
Deployment options: on-premisesaiverifyfoundation.sg
Listed integrations: Veritasaiverifyfoundation.sg

Facts

Purpose: AI Verify is an open-source, extensible toolkit that validates AI-system performance.aiverify-foundation.github.io · 1 Oct 2026
Testing coverage: The toolkit provides more than eight technical tests for fairness, explainability and robustness.aiverify-foundation.github.io · 1 Oct 2026
Users: It is built for data-science and compliance users, and supports both third-party testing and self-assessment.aiverify-foundation.github.io · 1 Oct 2026
Framework principles: The framework contains 11 AI-ethics principles, including transparency, explainability, safety, security, robustness, fairness, data governance and accountability.aiverifyfoundation.sg · 1 Oct 2026
International alignment: The framework is aligned with internationally recognised principles and frameworks from the EU, OECD and Singapore.aiverifyfoundation.sg · 1 Oct 2026
Portal and CLI: Users can run tests through the Portal or command line, upload results, complete process checklists and generate reports.aiverify-foundation.github.io · 1 Oct 2026
Data support: AIVT 2.0 currently supports tabular and image data types and can use a model file, preprocessing pipeline or model API as input.aiverify-foundation.github.io · 1 Oct 2026
Extensibility: The toolkit supports plugins built by the AI Verify Foundation or third parties.aiverify-foundation.github.io · 1 Oct 2026
Veritas integration: Veritas integration adds fairness and transparency tests for threshold trade-offs plus explainability plots.aiverify-foundation.github.io · 1 Oct 2026
Reporting: AI Verify includes standard report templates that predefine report layouts, technical tests and process checks, while also allowing customized reports.aiverify-foundation.github.io · 1 Oct 2026
License: The toolkit is open-sourced under the Apache 2.0 permissive license.aiverifyfoundation.sg · 1 Oct 2026
Security: The Foundation says electronic storage and transmission of personal data are secured with appropriate security technologies.aiverifyfoundation.sg · 1 Oct 2026
Scope limit: Project Moonshot tests LLM-based applications, while the AI Verify Testing Toolkit tests traditional AI applications for fairness, explainability and robustness.aiverifyfoundation.sg · 1 Oct 2026
Foundation status: AI Verify Foundation is a not-for-profit, wholly owned subsidiary of Singapore’s Infocomm Media Development Authority.aiverifyfoundation.sg · 1 Oct 2026
Framework coverage: The framework assesses responsible implementation against 11 internationally recognised AI-governance principles and covers traditional and generative AI.aiverifyfoundation.sg · 2 Oct 2026
Standards alignment: The framework is mapped to NIST AI RMF, NIST AI RMF Generative AI Profile, Hiroshima Process Code of Conduct and ISO/IEC 42001.aiverifyfoundation.sg · 2 Oct 2026
Traditional AI tests: The Toolkit provides technical tests for fairness, explainability and robustness of traditional machine-learning models.aiverifyfoundation.sg · 2 Oct 2026
Reports: The Toolkit creates customised reports and can combine independent developer and compliance-team work into a full report.aiverifyfoundation.sg · 2 Oct 2026
Open source: The Toolkit is open-sourced under the permissive Apache 2.0 license.aiverifyfoundation.sg · 2 Oct 2026
Who can use it: Anyone can use the AI Verify Testing Framework and Toolkit, including AI owners, developers, researchers, service providers and companies integrating it into their systems.aiverifyfoundation.sg · 2 Oct 2026
Integration: Veritas was integrated into AI Verify to help financial institutions meet common safety-baseline and financial-testing requirements from MAS.aiverifyfoundation.sg · 2 Oct 2026
Generative AI tool: Project Moonshot assesses LLM applications through benchmark testing and red teaming and implements benchmarks recommended in IMDA's Starter Kit.aiverifyfoundation.sg · 2 Oct 2026
Moonshot interfaces: Project Moonshot offers a Web UI, interactive CLI, library APIs and Web APIs for MLOps integration.github.com · 2 Oct 2026
Limitation: AI Verify does not define AI ethical standards and does not guarantee that tested systems are free from risks or biases or completely safe.github.com · 2 Oct 2026
Support: Users are directed to GitHub discussions, the issue tracker, documentation and the Foundation contact page for assistance.github.com · 2 Oct 2026