Plain-AyI
← All projects
AI testing & safety

Promptfoo

Tests AI apps and chatbots to check their answers are good and that they can't be easily tricked.

What it does

Promptfoo is a testing tool for apps built on AI language models. You describe the questions and expected behaviour in a simple settings file, and it runs them automatically so you can see how well your prompts, chatbot or AI agent performs.

It can compare different AI models side by side, and it does "red teaming": deliberately trying to trick an AI app into unsafe or wrong behaviour so problems are found before real users find them. It produces reports on any weaknesses it finds.

Its makers say tests run locally so your prompts don't leave your machine. It can run automatically whenever code changes, and its makers note it is now part of OpenAI while remaining open source.

Who it's for

Developers and teams who build AI-powered apps and need to check their quality and safety.

Can I use it without coding?

Developers only. Used from the command line or in code, with configuration files and AI provider keys. New to this? Start here.

Can I run it?

Cost
Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

Try it

  1. Install promptfoo and create its getting-started example.
  2. Add an API key for the AI provider you want to test.
  3. Run an evaluation and view the results side by side.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it