Map / AI Red Teaming / Promptfoo
Promptfoo
promptfoo.dev ↗ · LinkedIn ↗ · Open on the map
AI Red TeamingRuntime & GuardrailsObservability & Governance
Capabilities
AI security platform protecting LLMs from online adversaries; open-source LLM evaluation, red teaming, and security testing framework; widely adopted by enterprise AI teams for prompt evaluation and adversarial testing; supports OpenAI, Anthropic, Google, open-source models; CI/CD integration for security regression testing of LLM applications; will be integrated into OpenAI Frontier (the enterprise AI agents platform) post-acquisition.
Sensors / integration
Open-source CLI and library; integrates into developer and CI/CD pipelines; SaaS evaluation platform for enterprise customers.
Protections
Adversarial test generation against LLM applications; regression detection for prompt-injection and jailbreak resistance; red-team campaign automation; runtime hooks for production guardrails.
Differentiator
Rapid open-source adoption (15K+ GitHub stars); acquired by OpenAI in March 2026 — the first major frontier-lab acquisition of a dedicated AI security startup; signals OpenAI views agentic security as a strategic capability, hardening its enterprise agents platform.
Team & funding
- Founders
- Ian Webster, Michael D'Angelo
- Total raised
- $5M
- Investors
- Andreessen Horowitz
- Acquired by
- OpenAI · March 2026
Other AI Red Teaming companies
A Security · AccuKnox · ActaClad · ActiveFence · Advai · Adversa AI · Aether AI · AgentFox · Aikido · AIM Intelligence · Akto · Alice · See all →
Last updated · Get the “Listed on” badge