promptfoo/promptfoo
# Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
$ git clone https://github.com/promptfoo/promptfoo.git
stars
23,460
forks
2,104
language
TypeScript
license
MIT License
What is promptfoo/promptfoo?
Promptfoo is a testing and evaluation framework for large language model applications, including prompts, agents, and RAG systems. It lets you compare performance across different LLM providers (GPT, Claude, Gemini, DeepSeek, etc.), run red team security tests for vulnerabilities, and define test cases through declarative configuration files with CLI and CI/CD integration. Developers use it to systematically validate and improve their LLM-based applications before deployment.
Links
Topics
Activity
439 open issues · last updated Jul 21, 2026