FuzzyAI

Automated LLM fuzzer that tries jailbreak attacks against models and LLM APIs, including your own REST API.

Observability tool by CyberArk (Palo Alto Networks)

IndexedApache-2.0★ 1,590

Write a review

Get started

Setup steps are in the repository. Website · Repository

About

FuzzyAI is an automated LLM fuzzer for finding jailbreaks and weaknesses in LLM APIs. It installs with pip, runs from the fuzzyai command, and includes an experimental web UI. The README's examples cover attacks on OpenAI, Anthropic and Ollama models, and on a custom REST API endpoint.

Use cases: security-scanning

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: Red teaming · open source
Open source: Yesgithub.com
Protocols: restraw.githubusercontent.com

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 1,590
Forks: 218
Open issues: 3
Last commit: Feb 6, 2026 (8 months ago)

Details

License: Apache-2.0
Repository: github.com/cyberark/FuzzyAI
Website: github.com/cyberark/FuzzyAI
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README

Cite this page

FuzzyAI. Agent Mart. https://agentmart.dev/observability/fuzzyai (last updated 2026-10-24)