CalypsoAI

Policy enginecalypsoai

Runtime AI security for prompt-injection defence, data-leak detection and red teaming of models and agents.

Provider
default
Category
Operations
Also known as
F5 AI Guardrails
Properties · 1 set by this component
propertytypevaluesrequiredkind defaultthis component
deployment · component propertyenumpublic-cloud | private-cloud | on-premisesno—inherited
effectenumaudit | deny | modify | deploy-if-not-existsno—inherited
enforcementModeenumenforced | disabledno—inherited
managedboolean—nofalseinherited
policyCountinteger—no—inherited
redTeaming · component propertyboolean—nofalseinherited
remediationboolean—nofalseinherited
scopeenumresource | group | account | organizationno—▸ resource
Rules that apply · 0

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

No rule reads this kind yet. That is a gap, not a guarantee.
Use it in a design
nodes:
  - { id: "calypsoai", component: "calypsoai" }
Other Policy engine products · 56
Cloud Configalibaba-cloud-configalibabacloudpolicy-engineData Security Centeralibaba-data-security-centeralibabacloudpolicy-engineAmazon CodeGuru Revieweraws-codeguru-reviewerawspolicy-engineAWS Configaws-configawspolicy-engineAWS Control Toweraws-control-towerawspolicy-engineIAM Access Analyzeraws-iam-access-analyzerawspolicy-engineAWS Lake Formationaws-lake-formationawspolicy-engineAWS License Manageraws-license-managerawspolicy-engineAWS Organizationsaws-organizationsawspolicy-engineAWS Resource Access Manageraws-ramawspolicy-engineAmazon Verified Permissionsaws-verified-permissionsawspolicy-engineMicrosoft Entra Conditional Accessazure-conditional-accessazurepolicy-engineAzure Policyazure-policyazurepolicy-engineMicrosoft Entra Privileged Identity Managementazure-privileged-identity-managementazurepolicy-engineCloudflare Data Loss Preventioncloudflare-dlpcloudflarepolicy-engineCerboscerbospolicy-engineOPA Gatekeepergatekeeperpolicy-engineGuardrails AIguardrails-aipolicy-engineHiddenLayer AI Security Platformhiddenlayerpolicy-engineKubeArmorkubearmorpolicy-engineKubewardenkubewardenpolicy-engineKyvernokyvernopolicy-engineLakera Guardlakera-guardpolicy-engineLLM Guardllm-guardpolicy-engineNeMo Guardrailsnemo-guardrailspolicy-engineOpen Policy Agentopapolicy-enginePermit.iopermit-iopolicy-engineGeneric policy enginepolicy-enginepolicy-enginePrompt Securityprompt-securitypolicy-engineProtect AIprotect-aipolicy-engineRebuffrebuffpolicy-engineRobust Intelligencerobust-intelligencepolicy-engineSonarQube Serversonarqubepolicy-engineDigitalOcean CSPMdigitalocean-cspmdigitaloceanpolicy-engineAccess Context Managergoogle-access-context-managergcppolicy-engineAssured Workloadsgoogle-assured-workloadsgcppolicy-engineBinary Authorizationgoogle-binary-authorizationgcppolicy-engineIdentity and Access Managementgoogle-cloud-iamgcppolicy-engineFirebase App Checkgoogle-firebase-app-checkgcppolicy-engineModel Armorgoogle-model-armorgcppolicy-engine
and 16 more → Policy engine page
Source
# yaml-language-server: $schema=../../schema/component.schema.json
# CalypsoAI: runtime AI security platform with prompt-injection and jailbreak defence, data-leak detection
# and large-scale red teaming. Retired September 2025: F5 completed the acquisition (announced 29 September
# 2025) and relaunched it as F5 AI Guardrails and F5 AI Red Team; calypsoai.com now redirects to F5. Per
# "F5 AI Guardrails", it deploys in public cloud, private cloud or on premises; no default mode is published.
schemaVersion: "1"
type: "component"
id: "calypsoai"
kind: "policy-engine"
provider: "default"
docs: "https://www.f5.com/company/blog/what-are-ai-guardrails"
aliases: ["F5 AI Guardrails"]
defaults:
  scope: "resource"
properties:
  redTeaming:
    type: "boolean"
    default: false
  deployment:
    type: "enum"
    values: ["public-cloud", "private-cloud", "on-premises"]

The same page as markdown, for an agent: /catalogue/components/calypsoai.md