WardenAuth
Authorization for your users and your AI agents. Define who can do what, and get the reason behind every decision.
Two products, one model
WardenAuth is two products on one permission model: Authorization for your users, and Agent Security for the AI agents that act for them. An agent can never do more than its user.
Both share the same permission model, the same audit trail, and the same API.
Grant a user access to documents:read, or grant an AI agent access to
github__list_issues — it's the same call.
Access Control
Define permissions. Bundle them into roles. Assign roles to users and API keys. Check access at runtime. Every decision is logged to an immutable audit trail.
Agent Security
Every tool an AI agent uses goes through WardenAuth. Define tool tiers. Grant or deny access. Require human approval for sensitive operations. Get push notifications on your phone.