Skip to content
@promptfoo

promptfoo

Test your LLM apps
README.md
Promptfoo

Ship agents, not vulnerabilities

Website • Blog • LinkedIn

NPM Discord License: MIT

AI security testing platform for LLMs, agents, and RAG systems

Automated vulnerability detection and remediation trusted by 85 Fortune 500 companies and 200K+ developers

🚀 Get Started

Developer Tools

Security Testing

🛠️ Core Projects

promptfoo ⭐ 9.6k Test your prompts, agents, and RAGs. Red teaming and vulnerability scanning for LLMs.

promptfoo-action GitHub Action for CI/CD security testing

evil-mcp-server Red team testing for Model Context Protocol servers

js-rouge JavaScript ROUGE metrics for summarization evaluation

🔒 Security & Compliance

Promptfoo helps you build secure AI applications by detecting:

  • Prompt injections & jailbreaks
  • PII & sensitive data leaks
  • Hallucinations & policy violations
  • Adversarial attacks

Certifications: SOC2, ISO 27001, HIPAA

Privacy-first: Run evaluations locally or in your cloud

👥 Community

Connect with us:

  • GitHub - Star our repos and follow updates
  • Discord - Join our community of AI security practitioners
  • X/Twitter - Latest news and updates
  • Bluesky - Follow us on Bluesky

Contributing:

Resources:

Ready to secure your AI applications?

npm install -g promptfoo
promptfoo init
promptfoo eval

Get Started → • Enterprise Solutions →

Popular repositories Loading

  1. promptfoo promptfoo Public

    Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with co…

    TypeScript 9.6k 828

  2. promptfoo-action promptfoo-action Public

    The GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. S…

    TypeScript 31 14

  3. evil-mcp-server evil-mcp-server Public

    An evil MCP server used for redteam testing

    TypeScript 10 1

  4. mini-foo mini-foo Public

    Mini promptfoo used for interviews

    TypeScript 2 2

  5. js-rouge js-rouge Public

    A Javascript implementation of the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) evaluation metric for summaries.

    TypeScript 1

  6. redscan-lite redscan-lite Public

    Promptfoo Interview Exercise

    JavaScript 1

Repositories

Showing 10 of 16 repositories
  • promptfoo Public

    Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

    promptfoo/promptfoo’s past year of commit activity
    TypeScript 9,553 MIT 828 100 106 Updated Dec 23, 2025
  • .github Public
    promptfoo/.github’s past year of commit activity
    1 MIT 0 0 0 Updated Dec 23, 2025
  • redscan-lite Public

    Promptfoo Interview Exercise

    promptfoo/redscan-lite’s past year of commit activity
    JavaScript 1 MIT 0 0 3 Updated Dec 23, 2025
  • demo-app Public

    Basic ChatGPT wrapper start example

    promptfoo/demo-app’s past year of commit activity
    JavaScript 1 MIT 0 0 0 Updated Dec 23, 2025
  • mcp-agent-provider Public

    A promptfoo custom provider to test MCP servers with our evil mcp server

    promptfoo/mcp-agent-provider’s past year of commit activity
    JavaScript 1 MIT 0 0 0 Updated Dec 22, 2025
  • renovate-config Public

    Shared Renovate configuration for the promptfoo organization

    promptfoo/renovate-config’s past year of commit activity
    1 0 0 1 Updated Dec 22, 2025
  • js-rouge Public

    A Javascript implementation of the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) evaluation metric for summaries.

    promptfoo/js-rouge’s past year of commit activity
    TypeScript 1 MIT 0 0 1 Updated Dec 22, 2025
  • promptfoo-action Public

    The GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

    promptfoo/promptfoo-action’s past year of commit activity
    TypeScript 31 MIT 14 3 1 Updated Dec 21, 2025
  • mini-foo Public

    Mini promptfoo used for interviews

    promptfoo/mini-foo’s past year of commit activity
    TypeScript 2 2 0 0 Updated Dec 21, 2025
  • evil-mcp-server Public

    An evil MCP server used for redteam testing

    promptfoo/evil-mcp-server’s past year of commit activity
    TypeScript 10 MIT 1 0 0 Updated Dec 21, 2025
View all repositories

Top languages

Loading…

Most used topics

Loading…