Both ai-blackteam and Promptfoo red-team LLMs and integrate into CI. The core difference is ownership and focus: Promptfoo was acquired by OpenAI in March 2026 (it remains MIT-licensed); ai-blackteam is independent and not backed by any model vendor.
The competitor column describes those projects as of 2026-09-20 and is not maintained by their authors. These tools move independently of this one, so check their own documentation before relying on a row here. Corrections are welcome as issues.

​
At a glance

​
When Promptfoo fits

  • Your stack is Node/TypeScript and you want declarative YAML configs
  • You want the tool OpenAI and Anthropic use internally for application-layer testing
  • You are testing prompt/agent/RAG applications and want tight CI integration

​
When ai-blackteam fits

  • You want a vendor-neutral framework not owned by a model lab
  • You are in a Python stack and want pip install + one command
  • You need a large curated attack corpus mapped to multiple compliance frameworks (including the OWASP Agentic Top 10 2026)
  • You want to test your own deployed endpoint via the generic HTTP provider

​
Interop

ai-blackteam can export results in Promptfoo’s JSON format:
So you can run ai-blackteam’s attack corpus and view results in Promptfoo-compatible tooling.