LlamaFirewall
Open-source guardrail system for AI agents.
Part of Meta’s Purple Llama project: layered defences for agents including PromptGuard (jailbreak detection), agent alignment checks and CodeShield for insecure generated code.
- Vendor
- Meta
- Category
- AI security & guardrails
- Pricing
- Open source
- Open source
- Yes
- Platforms
- Python
- Launched
- 2025
- Website
- github.com/meta-llama/PurpleLlama
Features
- PromptGuard
- Agent alignment checks
- CodeShield
Best for
- Agents
- Enterprise
Works with
- Llama Guard 4 12B — Meta. Open multimodal safety classifier for prompts and responses.
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.
- LLM Guard — Protect AI (Palo Alto Networks). Open-source scanners for LLM prompts and outputs.
- garak — NVIDIA. LLM vulnerability scanner for red-teaming.