Clovie Docs

Get started

What is Clovie

Clovie helps you see, control and pay for the AI agents your organization runs.

Clovie is a governance platform for AI agents. It gives your security, platform and finance teams one place to answer three questions:

  • Which agents do we run? Every agent is registered, has an owner and has its own key.
  • What are they allowed to do? Policies decide which requests go through, which are blocked and which wait for a person to approve them.
  • What do they cost? Every request is priced and attributed to an agent, a team and a budget.

How it works

Your agents keep using the model providers and SDKs they use today. You change one setting: the base URL. Instead of calling a model provider directly, an agent sends its requests to the Clovie gateway with its own Clovie key.

The gateway checks each request against your policies and budgets, forwards allowed requests to the provider with your provider key, and records what happened. Nothing about the agent's code has to change beyond the URL and the key.

Monitor first, then enforce

Every new policy starts in monitor mode. Clovie records what the policy would have done without blocking anything, so you can check its effect on real traffic before you turn it on.

What you can do with Clovie

Who uses Clovie

  • Security and risk teams write policies, review approvals and export evidence for auditors.
  • Platform and engineering teams register agents, manage keys and choose which models agents may use.
  • Finance teams set budgets, apply negotiated prices and produce chargeback statements.

Where Clovie runs

You can use Clovie as a service we host for you, or run it inside your own cloud account or data center. Both options have the same features. See Choose SaaS or self-hosted.

Next step

Follow the Quickstart to connect your first agent, add a policy in monitor mode and find its audit record.

On this page