# Promptfoo

Open-source LLM evaluation and red-teaming tool, with paid enterprise and on-premise plans.

Promptfoo tests prompts, models, RAG pipelines and AI agents during development. Its red-team mode generates attacks for your target, including direct and indirect prompt injection, jailbreaks, data and PII leaks, business rule violations and insecure tool use in agents. It runs in CI/CD pipelines such as GitHub, GitLab and Jenkins. The free Community plan is the open-source tool. It runs locally or self-hosted and includes 10k red-team probes per month. The Enterprise and On-Premise plans are priced on request and add team sharing, continuous monitoring, a compliance dashboard and SSO.

Price: Community plan free (open source); Enterprise and On-Premise priced on request. Site: https://www.promptfoo.dev/.

Also on the [web page](https://aigovernancetools.fyi/apps/promptfoo).