microsoft.github.io · LLM Evals
Microsoft's open source (MIT) Python Risk Identification Tool for red teaming generative AI, with composable targets, converters, scorers and multiturn attacks.
PyRIT is one of 20 LLM eval tools on TrueIQ. See all LLM eval tools or how we check facts.
// guides
What a prompt injection attack is, direct and indirect examples, why there is no complete fix, and how to test your LLM app with Promptfoo, garak and PyRIT.
The best LLM red teaming tools in 2026 compared: Promptfoo, garak, PyRIT, DeepTeam and Giskard, with licenses, first commands and OWASP LLM Top 10 coverage.
// related
DeepTeamtrydeepteam.comOpen source (Apache 2.0) LLM red teaming framework from Confident AI, built on DeepEval, covering 50+ vulnerability types with OWASP, NIST and MITRE presets.LLM EvalsOpen source★ 3.1k
garakgarak.aiNVIDIA's open source (Apache 2.0) LLM vulnerability scanner that probes models and endpoints for jailbreaks, prompt injection, data leakage and toxic output.LLM EvalsOpen source★ 9.7k
Inspect AIinspect.aisi.org.ukMIT licensed framework from the UK AI Security Institute for rigorous LLM and agent evaluations, with tool use, sandboxed tasks and 200+ prebuilt evals.LLM EvalsOpen source★ 3.1k
mlprintsgithub.comOpen source AGPL-3.0 framework from Sentient for implementing, attacking and verifying LLM fingerprinting methods in a shared evaluation environment.LLM EvalsOpen source★ 3
Promptfoopromptfoo.devOpen source CLI for testing prompts, models and RAG apps with assertions, side by side comparisons and automated red teaming. Part of OpenAI since 2026 and still MIT licensed.LLM EvalsOpen source★ 26.5k
Giskardgiskard.aiOpen source Python library for evaluating and red teaming AI agents and RAG apps. Version 3 is a modular rewrite for multiturn testing; v2 is no longer maintained.LLM EvalsOpen source★ 5.9k