Skip to content

LLM Guard

by Protect AI

Open-source scanner toolkit for LLM inputs and outputs; the repository is now archived.

  • Self-hosted
  • Small business
  • Mid-size
  • Enterprise
  • Open source
  • Free tier

From LLM Guard's own website and public documents, updated 4 Nov 2026. Not a hands-on review: I add a verdict only to products I use myself.

What is LLM Guard?

Protect AI built LLM Guard, a security toolkit for LLM interactions. It scans prompts before they reach a model and responses before they reach users, covering sanitisation, harmful language, data leakage and prompt injection.

The README lists 15 input scanners, including Anonymize, PromptInjection, Secrets, Toxicity and TokenLimit, and 21 output scanners, including Deanonymize, MaliciousURLs, NoRefusal and Sensitive. It installs as a Python library with pip and can also run as an API. The licence is MIT and the repository shows about 3.2k stars.

The repository is archived and read-only. Its page says it is no longer under active development or maintained, and the same applies to its Hugging Face models.

Best forDevelopers who can maintain a fork or accept an unmaintained library

LLM Guard features

  • Input scanners

    15 scanners including Anonymize, PromptInjection, Secrets and BanTopics.

  • Output scanners

    21 scanners including Deanonymize, MaliciousURLs, Sensitive and Relevance.

  • Prompt injection

    PromptInjection scanner for incoming prompts.

  • PII handling

    Anonymize and Deanonymize scanners for personal data.

  • Library or API

    Install with pip or deploy as an API.

  • MIT licence

    Free to use and fork.

LLM Guard pricing

Starting price

Free (open source)

  • Pricing modelFlat fee
  • Free tierYes
  • Free trialNo

Current prices on the vendor's site · Checked 4 Nov 2026. Prices change often; the vendor's page wins.

Security and compliance

Certifications
None listed on a public trust page
EU data residency
Not documented

Where it fits (NIST CSF 2.0)

  1. Govern (not covered)
  2. Identify (not covered)
  3. Protect
  4. Detect (not covered)
  5. Respond (not covered)
  6. Recover (not covered)

Independent audits

No public independent audit found.

Good to know before you buy

  • The repository is archived and no longer maintained, so no new fixes or model updates.
  • Scanner models will age against new attack methods; plan a replacement.

LLM Guard alternatives

Open-source Python framework with a validator hub for checking LLM inputs and outputs.

Meta's open safety models that classify LLM prompts and responses, part of the Purple Llama project.

Open-source NVIDIA toolkit for adding programmable input, dialog, retrieval, execution and output rails to LLM apps.

Securiti

Securiti, LLC

Data and AI security platform with privacy automation, DSAR, DSPM and LLM firewalls.

LLM Guard vs Guardrails AILLM Guard vs Llama GuardLLM Guard vs NeMo Guardrails

Frequently asked questions

What is LLM Guard?

Open-source scanner toolkit for LLM inputs and outputs; the repository is now archived.

How much does LLM Guard cost?

LLM Guard starts at Free (open source), according to its pricing page (checked 4 Nov 2026).

Is there a free version of LLM Guard?

Yes. LLM Guard has a free plan or tier; check the pricing page for its limits.

What are the alternatives to LLM Guard?

Products in the same category include Guardrails AI, Llama Guard, NeMo Guardrails, Securiti.

Have you tested LLM Guard?

Not yet. This page lists published facts only. When I test it, my verdict will appear at the top.

Sources (2), checked 4 Nov 2026
  1. github.com/protectai/llm-guard
  2. protectai.github.io/llm-guard

Spotted something out of date? Tell me through the contact page and I will fix it.

By using this site, you agree to the Privacy Policy.