promptfoo
An open-source CLI and library for systematic LLM evaluation, prompt testing and AI security, running YAML-defined test cases across 50+ providers with automated scoring, plus red-teaming for prompt injection and data leakage.
- Website
- https://www.promptfoo.dev/
- Who it's for
- CLI-first developers and security-conscious teams that want test-driven evaluation and red-teaming in CI, with data staying local.
- Pricing
- Community edition free forever, including eval features and up to 10k red-team probes/month. Enterprise and on-premise pricing custom.
- Category
- Agent operations
- Last verified
- 2026-10-22 (current)
- Confidence
- high
Key facts
- Acquired by OpenAI, announced 9 March 2026
- Remains open source under its existing MIT licence
- Local-first: evals run on your machine like unit tests
- YAML-configured tests across 50+ providers
- Automated red-teaming for prompt injections, jailbreaks and data leakage
Sources
Every claim above is drawn from these; we do not publish unsourced specifications.
- https://www.promptfoo.dev/blog/promptfoo-joining-openai/
- https://openai.com/index/openai-to-acquire-promptfoo/
- https://techcrunch.com/2026/03/09/openai-acquires-promptfoo-to-secure-its-ai-agents/
- https://www.promptfoo.dev/pricing/
Notes & uncertainties
Still open source and supported per both parties, but it now sits inside a major model vendor's platform - watch what happens to the standalone product.
Something changed or out of date? Tell us — corrections are how this stays worth reading.