LLM Guard

Palo Alto Networks (Protect AI)

Open Source

Open source safety filtering toolkit whose development has slowed following acquisition activity.

MITVersion 0.3.162,978

Strengths

Practitioner note

Best for security-minded teams that want open source scanning around prompts and outputs and are comfortable assembling their own policy pipeline.

LLM Guard: Development slowed significantly post acquisition. Last meaningful commit noted as December 2025 in the guide.

Reviewed 2026-05-26

YesData residency

Self-hosted library; data stays on operator infrastructure.

YesDeployment model

Open-source Python library; maintenance mode, no managed service. (self-hosted)

N/AAudit logging

No built-in audit log in the OSS library.

N/ASOC 2

Self-hosted library; certification applies to the operator.

N/AISO 27001

Self-hosted library; applies to the operator's ISMS.

N/AISO 42001

Self-hosted library; applies to the operator.

N/AEU AI Act

OSS safety-filtering library; not itself an AI system. (role: not-applicable)

YesLicense risk

MIT — permissive; note maintenance-mode operational risk. (low)

Compare this tool against the rest of its category and the cloud platform foundation layer.

Return to the category grid to compare governance posture across every tracked tool.

Review Microsoft Foundry, Amazon Bedrock, and Gemini Enterprise Agent Platform as the foundation layer.

Track releases, deprecations, license changes, and other market movements.