Promptfoo is an AI security platform for testing prompts, models, RAG pipelines, and agents. It provides red teaming, vulnerability scanning, runtime guardrails, MCP proxying, and integrations for development workflows and CI/CD, serving developers and enterprise security teams.
Promptfoo is a LLM evaluation & benchmarks project. It focuses on finding and preventing security vulnerabilities and quality issues in AI applications before and during deployment. It is built as a B2B product for AI developers, security teams, and enterprise engineering teams. Promptfoo is commercial open source (MIT). It ships for the web, the command line, and API, and it can be self-hosted.
Promptfoo builds and maintains Promptfoo, and it first shipped in 2023. Development happens publicly on GitHub with 24.6k stars and 668 commits in the last 90 days. Key capabilities include Red Teaming, Runtime Guardrails, and Model Security. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do