- Home
- AI Red Teaming Tools
- PyRIT
PyRIT
What it is
PyRIT is a free, MIT-licensed, open-source framework for security professionals and engineers assessing risks in generative AI systems. It supports single-turn and multi-turn red-team strategies, including Crescendo, TAP, and Skeleton Key. Scenario evaluations provide repeatable testing across hundreds of objectives, including content harms, psychosocial risks, and data leakage. CoPyRIT adds a web interface for interacting with AI systems, tracking findings, and collaborating with a team. Documented targets include OpenAI, Azure, Anthropic, Google, HuggingFace, custom HTTP endpoints, WebSockets, and web apps tested with Playwright. PyRIT stores conversations, scores, and attack results in SQLite or Azure SQL and supports exports. Scorers can use true/false, Likert, classification, or custom methods, including LLM-based and Azure AI Content Safety scoring. Scanner, GUI, Framework, pyrit_scan, and pyrit_shell modes are documented. Installation is available through Docker, pip, or uv, with Python 3.13 recommended for local setup. GitHub Issues handle project questions and bugs, while vulnerability reports go to Microsoft’s security response center.
For and against
For
- Free and MIT licensed
- Supports single-turn and multi-turn attacks
- Evaluates hundreds of scenario objectives
- Offers web-based collaborative review
- Stores and exports assessment results
Against
- Local documentation recommends Python 3.13
- Support is limited to listed resources
- Requires user-managed installation
The verdict
PyRIT provides an open framework for structured generative-AI red teaming and safety evaluation. Its range of targets, scoring methods, storage options, and installation paths supports both command-line and collaborative workflows.
Who it suits
It suits security professionals and engineers evaluating generative AI behavior, safety, and data-leakage risks. Teams wanting repeatable scenarios, custom scoring, or collaborative review may use its documented modes.
Plans and prices
PyRIT
Open-source framework · install from PyPI or Docker
Read 8 Oct 2026 · github.com
On the record
- Human-led interface
- CoPyRIT provides a web interface for interacting with AI systems, tracking findings, and collaborating with a team.microsoft.github.io · read 8 Oct 2026
- Installation
- The project documents user installation through Docker or locally with pip or uv, plus contributor Docker and local installation options.microsoft.github.io · read 8 Oct 2026
- License
- The GitHub repository identifies PyRIT as MIT licensed.github.com · read 8 Oct 2026
- Memory
- PyRIT can store conversations, scores, and attack results in SQLite or Azure SQL, and supports exporting results.microsoft.github.io · read 8 Oct 2026
- Purpose
- PyRIT is an open-source framework for security professionals and engineers to identify risks in generative AI systems.github.com · read 8 Oct 2026
- Python compatibility
- The current documentation recommends Python 3.13 for local installation.microsoft.github.io · read 8 Oct 2026
- Red teaming
- It supports single-turn and multi-turn attack strategies, including Crescendo, TAP, and Skeleton Key.microsoft.github.io · read 8 Oct 2026
- Scenario evaluations
- Its scenario framework supports repeatable evaluations across hundreds of objectives, including content harms, psychosocial risks, and data leakage.microsoft.github.io · read 8 Oct 2026
- Scoring
- Response scoring supports true/false, Likert scale, classification, and custom scorers, including LLM-based and Azure AI Content Safety scoring.microsoft.github.io · read 8 Oct 2026
- Security reporting
- The documentation directs vulnerability reports to the Microsoft Security Response Center and says not to report them through public GitHub issues.microsoft.github.io · read 8 Oct 2026
- Support
- The project uses GitHub Issues for bugs, feature requests, and questions, and says support is limited to the resources it lists.github.com · read 8 Oct 2026
- Targets
- Documented targets include OpenAI, Azure, Anthropic, Google, HuggingFace, custom HTTP endpoints and WebSockets, and web apps tested with Playwright.microsoft.github.io · read 8 Oct 2026
- Ways to use
- The documentation describes Scanner, GUI, and Framework modes, including command-line assessment through pyrit_scan and pyrit_shell.microsoft.github.io · read 8 Oct 2026
