Gray Swan
Active behavior assessment and runtime enforcement for AI agents, built on adversarial red teaming research.
Observability tool by Gray Swan AI
IndexedLicense unknown
Get started
Sign up on the vendor's site. Website
About
Gray Swan sells two products for AI systems. SHADE runs LLM-based adversarial agents to assess how models and agents misbehave, and CYGNAL classifies and blocks adversarial inputs and unsafe agent outputs at runtime. The site says its attacks are drawn from arena competitions with more than 15,000 adversarial researchers.
Use cases: security-scanning
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Category
- Red teaming
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.
Details
- License
- License unknown
- Website
- www.grayswan.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- Website
Cite this page
Gray Swan. Agent Mart. https://agentmart.dev/observability/gray-swan (last updated 2026-10-24)