NeMo Guardrails
Open-source toolkit for programmable LLM guardrails.
Adds input, output, dialog and retrieval rails around LLM apps — topic control, jailbreak and injection detection, fact-checking — configured in YAML and the Colang language.
- Vendor
- NVIDIA
- Category
- AI security & guardrails
- Pricing
- Open source
- Open source
- Yes
- License
- Apache 2.0
- Platforms
- Python
- Launched
- 2023
- Website
- github.com/NVIDIA/NeMo-Guardrails
Features
- Colang dialog rails
- Jailbreak detection
- Works with any LLM
Best for
- Enterprise
- Chat & assistants
Works with
- Nemotron 3.5 Content Safety — NVIDIA. Compact 4B multimodal guardrail model for LLM and VLM traffic.
More ai security & 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.
- LlamaFirewall — Meta. Open-source guardrail system for AI agents.