Garak
apache 2.0 from nvidia, twenty-plus probe modules, and a peer-reviewed paper behind it.
the most rigorous free option and the narrowest in scope — it tests a model beautifully and knows nothing about the application around it.
apache 2.0, maintained under nvidia's github organisation with leon derczynski as co-copyright holder, and backed by a peer-reviewed preprint on arxiv that users are asked to cite. in a category where most vendors publish marketing copy, having a paper to point at is a meaningful difference.
the probe coverage is broad for model-level work: hallucination, data leakage, prompt injection, misinformation, toxicity, jailbreaks including dan-style attacks, encoding-based injection, malware generation, package hallucination and xss-style output, across more than twenty modules. it runs from the command line against a named target model with no account and no sales contact.
the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.
- category
- ai red-teaming tools
- pricing
- free
- website
- github.com
the most rigorous free option and the narrowest in scope — it tests a model beautifully and knows nothing about the application around it.
we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.
more ai red-teaming tools
Promptfoo
we checked thisfreemit-licensed, free for ten thousand probes a month, and the only free tool here that tests agent tool access.
Adversa AI
we checked thisnot publishedthe most itemised attack taxonomy and the only vendor naming five compliance frameworks — behind a demo form.