enterpriseai.tools
Open navigation menu

LLM Guard

Palo Alto Networks (Protect AI)

Open Source

Open source LLM safety-filtering toolkit; the repository was archived in July 2026 and is no longer maintained.

Curated by Tiberiu ArvaStale

MITVersion 0.3.163,205
DocsRepository

Strengths

  • Prompt/output scanning
  • PII and toxicity detectors
  • Useful safety primitives

Practitioner note

Archived: fine as a reference for prompt/output scanner design, but do not start new production dependencies on it; pick a maintained guardrail layer instead.

Warning

LLM Guard: Repository archived by the owner on July 9, 2026; the project and its Hugging Face models are no longer under active development.

Where it sits in the stack

Listed under Guardrails & security in the Control plane layer.

  1. Build & orchestrate
  2. Control plane
  3. Use

Pairs with, from Palo Alto Networks (Protect AI)

Governance posture

Reviewed 2026-05-26
YesData residency

Self-hosted library; data stays on operator infrastructure.

Source
YesDeployment model

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

Source
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)

Source

EU AI Act obligations

Risk tier: Not applicable · as of 2026-10-10

Source-backed information mapped from LLM Guard's tracked risk tier — not legal advice. Obligations depend on how your organisation deploys the system; see the full obligation reference and timeline.

This record's EU AI Act risk tier is marked not applicable, so no tier-specific obligations attach. Deployers embedding it in an AI system in scope of the Act should assess that system's own tier.

Change history

Source-backed and auto-detected events for this tool, newest first.

  1. DeprecationHigh impact

    Protect AI archived the LLM Guard repository; the project and its Hugging Face models are no longer under active development.

    LLM Guard README (archive notice) · protectai/llm-guard
  2. Auto-detectedHigh impact
    status: maintenance → archived

    From snapshot diff 2026-09-13 → 2026-10-10.

  3. Auto-detected
    githubStars: 3202 → 3205

    From snapshot diff 2026-08-22 → 2026-09-13.

  4. Auto-detected
    githubStars: 3163 → 3202

    From snapshot diff 2026-07-17 → 2026-08-04.

  5. Auto-detected
    githubStars: 3045 → 3163

    From snapshot diff 2026-06-07 → 2026-07-17.

Explore the category

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

AI Guardrails & Agent Security

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

Platforms

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

Weekly updates

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