PyRIT
MicrosoftThe Python Risk Identification Tool from the Microsoft AI Red Team: an open framework that automates red-teaming of generative AI systems, orchestrating adversarial prompts, attack strategies, and scoring to surface harms and vulnerabilities at scale.
PyRIT, maintained by the Microsoft AI Red Team at github.com/microsoft/PyRIT. The package ships prompt converters and datasets, attack executors and scenarios, scorers, and prompt targets for multiple providers. The README is now a pointer at the docs site rather than a description. Verified 2026-08-13 via GitHub.
Openness
5 high confidence- license
- MIT(OSI)
- source
- public(full Python framework)
- self-host
- yes
- service
- none
- core-gated
- ungated
Fully open source: MIT-licensed automation framework, self-hostable, no proprietary tier.
- https://github.com/microsoft/PyRIT recorded 2026-08-13
Repo metadata records license spdxId - MIT. README describes PyRIT as 'an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems' and points at the docs site for install and use; no hosted tier, no enterprise directory and no license key on the page.
Adoption
2 low confidence4,285 GitHub stars on microsoft/PyRIT, which bands at 1K-10K stars, level 2. No download, install or customer figure is published for this product, so stars are the only honest signal and the level is directional; a stars proxy never rises above 3, because a star is not a use. Microsoft's backing is provenance rather than adoption volume.
- https://api.github.com/repos/microsoft/PyRIT recorded 2026-08-12
stargazers_count = 4,285 for microsoft/PyRIT
Capability
4 medium confidenceA leading open red-teaming harness; strong automation and scoring, and multi-provider. The README is now a pointer at the docs site and no longer names the pieces, so the band is read off the shipped modules in the package listing.
- https://github.com/microsoft/PyRIT recorded 2026-08-13
README describes 'an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems'; the component detail it used to carry now lives on the docs site.
- https://api.github.com/repos/microsoft/PyRIT/contents/pyrit recorded 2026-08-13
Top-level package listing carries converter, datasets and prompt_normalizer (adversarial prompt generation), executor and scenario (attack-strategy orchestration), score (scoring), and prompt_target with backend and auth (multi-provider targets) - the three things the band is recorded on, as shipped modules.
Verified 2026-08-12