AgentSea.
Copy Markdown
An LLM-as-moderator guardrail: asks a model whether the content violates a
policy and blocks it if so. Runs over any AgentSea.Provider (so it can go
through the gateway).
Options:
:provider—{module, opts}(required):model— model id (or in the provider opts):policy— what to disallow (default: unsafe/harmful content):fail_open— on a provider error, allow (true, default) or block (false)