garak vs promptfoo: Which One Covers More of the OWASP LLM Top 10 in 2026?
garak and promptfoo are both open-source AI Red Teaming tools, diffed on license, language, maintainer, and repository status as of 2026-07-13. Both fit teams evaluating ai red teaming; the real difference is language, maintenance activity, and scope — not feature count.
Sponsored Comparison — this slot is available to category sponsors. Paid placement does not alter the coverage data or verdict below.
Spec comparison
| Attribute | garak | promptfoo |
|---|---|---|
| Maintainer | NVIDIA | Promptfoo (a subsidiary of OpenAI as of March 2026) |
| License | Apache-2.0 | MIT |
| Language | Python | TypeScript |
| Status | Active | Ownership changed |
| Primary use | LLM vulnerability scanner — automated probing for jailbreaks, prompt injection, data leakage, hallucination, and other failure modes | Prompt/agent/RAG testing and LLM red-teaming — vulnerability scanning, eval, and CI/CD security testing for AI applications |
Read the full profiles: garak, promptfoo.
Last verified . Sources: https://github.com/NVIDIA/garak, https://github.com/promptfoo/promptfoo. Funding and repo figures are third-party and go stale. Re-verify before you rely on them.
Informational, not professional security advice — verify both projects' claims against OWASP, MITRE, and the maintainers directly before a decision. OWASP, MITRE, and the listed vendors and maintainers do not endorse llmthreat.com.