A testing framework for evaluating LLM output quality through systematic test cases and side-by-side model comparisons. It supports automated red teaming and vulnerability scanning for RAG-based applications via CLI and CI/CD.
Tech Stack
TypeScriptAI, ML & Data
Why promptfoo?
• Supports 50+ LLM providers
• Automated red teaming
• CI/CD integration
Limitations
• CLI-first (limited GUI)
• Requires test case writing
• High API token usage
3/6/2026
Last Update
961
Forks
256
Issues
MIT
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to promptfoo instantly boosts your runway.
