Guardrails AI

Open-source Python framework that validates LLM inputs and outputs with Hub validators and structures output.

Provider: default
Kind: Policy engine
Category: Operations
Official docs: https://www.guardrailsai.com/docs/concepts/validator_on_fail_actions

Properties · 3 set by this component

property	type	values	required	kind default	this component
effect	enum	audit \| deny \| modify \| deploy-if-not-exists	no	—	▸ deny
enforcementMode	enum	enforced \| disabled	no	—	inherited
guardrailsServer · component property	boolean	—	no	false	inherited
hubValidators · component property	integer	—	no	0	inherited
managed	boolean	—	no	false	▸ false
onFail · component property	enum	reask \| fix \| filter \| refrain \| noop \| exception \| fix_reask \| custom	no	exception	inherited
policyCount	integer	—	no	—	inherited
remediation	boolean	—	no	false	inherited
scope	enum	resource \| group \| account \| organization	no	—	▸ 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: "guardrails-ai", component: "guardrails-ai" }

Other Policy engine products · 56

Cloud Configalibaba-cloud-configalibabacloudpolicy-engine Data Security Centeralibaba-data-security-centeralibabacloudpolicy-engine Amazon CodeGuru Revieweraws-codeguru-reviewerawspolicy-engine AWS Configaws-configawspolicy-engine AWS Control Toweraws-control-towerawspolicy-engine IAM Access Analyzeraws-iam-access-analyzerawspolicy-engine AWS Lake Formationaws-lake-formationawspolicy-engine AWS License Manageraws-license-managerawspolicy-engine AWS Organizationsaws-organizationsawspolicy-engine AWS Resource Access Manageraws-ramawspolicy-engine Amazon Verified Permissionsaws-verified-permissionsawspolicy-engine Microsoft Entra Conditional Accessazure-conditional-accessazurepolicy-engine Azure Policyazure-policyazurepolicy-engine Microsoft Entra Privileged Identity Managementazure-privileged-identity-managementazurepolicy-engine Cloudflare Data Loss Preventioncloudflare-dlpcloudflarepolicy-engine CalypsoAIcalypsoaipolicy-engine Cerboscerbospolicy-engine OPA Gatekeepergatekeeperpolicy-engine HiddenLayer AI Security Platformhiddenlayerpolicy-engine KubeArmorkubearmorpolicy-engine Kubewardenkubewardenpolicy-engine Kyvernokyvernopolicy-engine Lakera Guardlakera-guardpolicy-engine LLM Guardllm-guardpolicy-engine NeMo Guardrailsnemo-guardrailspolicy-engine Open Policy Agentopapolicy-engine Permit.iopermit-iopolicy-engine Generic policy enginepolicy-enginepolicy-engine Prompt Securityprompt-securitypolicy-engine Protect AIprotect-aipolicy-engine Rebuffrebuffpolicy-engine Robust Intelligencerobust-intelligencepolicy-engine SonarQube Serversonarqubepolicy-engine DigitalOcean CSPMdigitalocean-cspmdigitaloceanpolicy-engine Access Context Managergoogle-access-context-managergcppolicy-engine Assured Workloadsgoogle-assured-workloadsgcppolicy-engine Binary Authorizationgoogle-binary-authorizationgcppolicy-engine Identity and Access Managementgoogle-cloud-iamgcppolicy-engine Firebase App Checkgoogle-firebase-app-checkgcppolicy-engine Model Armorgoogle-model-armorgcppolicy-engine

and 16 more → Policy engine page

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Guardrails AI: open-source Python framework that wraps LLM calls in input and output Guards built from
3# Guardrails Hub validators, and generates structured output. Per "Validator OnFail Actions", a failed
4# validator can reask, fix, filter, refrain, noop, raise or call a custom handler; the Validator base
5# class sets on_fail to EXCEPTION when none is given, so an unhandled failure blocks the call.
6schemaVersion: "1"
7type: "component"
8id: "guardrails-ai"
9kind: "policy-engine"
10provider: "default"
11docs: "https://www.guardrailsai.com/docs/concepts/validator_on_fail_actions"
12aliases: ["Guardrails"]
13defaults:
14  managed: false
15  scope: "resource"
16  effect: "deny"
17properties:
18  onFail:
19    type: "enum"
20    values: ["reask", "fix", "filter", "refrain", "noop", "exception", "fix_reask", "custom"]
21    default: "exception"
22  guardrailsServer:
23    type: "boolean"
24    default: false
25  hubValidators:
26    type: "integer"
27    default: 0

The same page as markdown, for an agent: /catalogue/components/guardrails-ai.md