Governance
NeMo Guardrails
Define programmable rules around conversational AI inputs, outputs, and dialogue flows.
7.3K GitHub starsAs of Checked
Where it fits
What you can use it for
Applications that need explicit conversational behavior rules.
Apply policy, document risks and check system behaviour.
Before you adopt
What to check for your team
Rules reduce selected risks; they do not prove that all unsafe behavior is blocked. Test them with your models and tools.
Get help evaluating the fitLicence and scope
Apache-2.0
The pinned license explicitly identifies Apache-2.0. Model weights, dependencies and hosted services can have separate terms.
Read the upstream licenceSupport the work
Go directly to the maintainers
Use the project's contribution guidance to report issues, help with documentation or contribute code. Follow any published funding links if you want to support the maintainers financially.
Find contribution guidanceKeep exploring
