Protect AI

Protect AI is an AI/ML security platform (now part of Palo Alto Networks) whose products secure the AI lifecycle from model selection to runtime. Its developer surface centers on LLM Guard, an open-source Python toolkit of prompt and output scanners that ships a self-hostable REST API for real-time input/output sanitization. Commercial products - Guardian (model scanning), Recon (LLM red-teaming), and Layer (runtime protection) - are delivered through a portal under sales-led terms.

4 APIs 0 Features

AIMLSecurityLLMGuardrails

APIs

LLM Guard (Scanners)

Open-source (Apache 2.0) toolkit of input and output scanners that detect, redact, and sanitize LLM prompts and responses for prompt injection, PII, toxicity, secrets, and more....

Guardian (Model Scanning)

Commercial AI model security product that scans first- and third-party models for serialization attacks, malicious code, and supply-chain threats before they reach production. T...

Recon (Red-Teaming)

Commercial automated red-teaming product that rigorously tests LLM and GenAI applications for vulnerabilities, jailbreaks, and policy violations. Delivered as a sales-led platfo...

Layer (Runtime)

Commercial runtime security product that monitors and controls AI applications in production with deep visibility and inline threat prevention. Delivered as a sales-led platform...

Resources

👥

GitHubOrganization

Sources

aid: protectai
url: https://raw.githubusercontent.com/api-evangelist/protectai/refs/heads/main/apis.yml
name: Protect AI
kind: company
description: Protect AI is an AI/ML security platform (now part of Palo Alto Networks)
  whose products secure the AI lifecycle from model selection to runtime. Its developer
  surface centers on LLM Guard, an open-source Python toolkit of prompt and output
  scanners that ships a self-hostable REST API for real-time input/output sanitization.
  Commercial products - Guardian (model scanning), Recon (LLM red-teaming), and Layer
  (runtime protection) - are delivered through a portal under sales-led terms.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- ML
- Security
- LLM
- Guardrails
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: protectai:llm-guard-scanners
  name: LLM Guard (Scanners)
  tags:
  - LLM
  - Guardrails
  - Prompt Injection
  - PII
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://llm-guard.com/api/overview/
  baseURL: http://localhost:8000
  properties:
  - url: https://llm-guard.com/
    type: Documentation
  - url: https://llm-guard.com/api/overview/
    type: APIReference
  - url: openapi/protectai-openapi.yml
    type: OpenAPI
  - url: https://github.com/protectai/llm-guard
    type: GitHub
  description: Open-source (Apache 2.0) toolkit of input and output scanners that detect,
    redact, and sanitize LLM prompts and responses for prompt injection, PII, toxicity,
    secrets, and more. The llm-guard-api service wraps the library in a self-hostable
    FastAPI app exposing /analyze and /scan endpoints for prompts and outputs.
- aid: protectai:guardian-model-scanning
  name: Guardian (Model Scanning)
  tags:
  - Model Scanning
  - Supply Chain
  - MLSecOps
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://protectai.com/guardian
  baseURL: https://protectai.com/guardian
  properties:
  - url: https://protectai.com/guardian
    type: Documentation
  - url: https://github.com/protectai/modelscan
    type: GitHub
  description: Commercial AI model security product that scans first- and third-party
    models for serialization attacks, malicious code, and supply-chain threats before
    they reach production. The open-source ModelScan project (Apache 2.0) provides
    the underlying model-scanning engine; Guardian itself is a sales-led platform
    without a documented public REST API.
- aid: protectai:recon-red-teaming
  name: Recon (Red-Teaming)
  tags:
  - Red Teaming
  - Adversarial Testing
  - LLM
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://protectai.com/recon
  baseURL: https://protectai.com/recon
  properties:
  - url: https://protectai.com/recon
    type: Documentation
  description: Commercial automated red-teaming product that rigorously tests LLM and
    GenAI applications for vulnerabilities, jailbreaks, and policy violations. Delivered
    as a sales-led platform; no public REST API surface is documented.
- aid: protectai:layer-runtime
  name: Layer (Runtime)
  tags:
  - Runtime Security
  - Observability
  - Threat Detection
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://protectai.com/layer
  baseURL: https://protectai.com/layer
  properties:
  - url: https://protectai.com/layer
    type: Documentation
  description: Commercial runtime security product that monitors and controls AI applications
    in production with deep visibility and inline threat prevention. Delivered as a
    sales-led platform; no public REST API surface is documented.
common:
- type: GitHubOrganization
  url: https://github.com/protectai
- type: LinkedIn
  url: https://www.linkedin.com/company/protect-ai
- type: Website
  url: https://protectai.com/
- type: Documentation
  url: https://llm-guard.com/
- type: Plans
  url: plans/protectai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/protectai-rate-limits.yml
- type: FinOps
  url: finops/protectai-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com