LLM Guard
Open-source scanners for LLM prompts and outputs.
A library of input and output scanners — prompt injection, secrets, PII anonymisation, toxicity, code — to sanitise LLM traffic.
- Vendor
- Protect AI (Palo Alto Networks)
- Category
- AI security & guardrails
- Pricing
- Open source
- Open source
- Yes
- License
- MIT
- Platforms
- Python, API
- Launched
- 2023
- Website
- protectai.com/llm-guard
Features
- Input & output scanners
- PII anonymisation
- Self-hosted API
Best for
- Enterprise
More ai security & guardrails
- NeMo Guardrails — NVIDIA. Open-source toolkit for programmable LLM guardrails.
- Guardrails AI — Guardrails AI. Validators that check and correct LLM inputs and outputs.
- Lakera Guard — Lakera (Check Point). Real-time prompt-injection and data-leak protection API.
- garak — NVIDIA. LLM vulnerability scanner for red-teaming.
- LlamaFirewall — Meta. Open-source guardrail system for AI agents.