Promptfoo is an open-source tool for testing prompts, agents, and RAGs, with AI red teaming, pentesting, and vulnerability scanning for LLMs. Built under MIT license, Promptfoo was originally developed for LLM apps serving over 10 million users in production. The platform compares performance across GPT, Claude, Gemini, Llama, and more with simple declarative configs supporting command line and CI/CD integration. The Community version includes up to 10,000 probes monthly at no charge, with infrastructure costs typically USD 50-500 monthly for hosting and LLM API calls. Developers praise Promptfoo for its speed, quality-of-life features like live reloads and caching, security features including red teaming, and budget-friendly open-source model. However, the CLI-focused approach creates friction for non-technical team members, and the platform lacks end-to-end observability, version control for prompts, and test management features needed for complex production agents.
Free trial available
Integrate Promptfoo's open-source LLM testing with Respan to add comprehensive evaluation and red teaming to your AI workflows. Test prompts, agents, and RAGs against security threats and performance benchmarks. With Respan orchestrating Promptfoo alongside your AI services, ensure quality and security before production deployment.
Top companies in Observability, Prompts & Evals you can use instead of Promptfoo.
Companies from adjacent layers in the AI stack that work well with Promptfoo.
Last verified: March 10, 2026