Agent Registry
One inventory for every agent. Know what you have before you govern it.
Prefactor's Agent Registry gives you a single source of truth for every AI agent in your organisation — who owns it, what framework it uses, what tools it can access, and whether it's governed. No more shadow agents, no more spreadsheet inventories.
How it works
TODO: Describe the registration flow — manual registration via dashboard, API-based registration from CI/CD, and discovery-based detection of unregistered agents. Include screenshots of the registry dashboard.
What the registry tracks
TODO: Detail the metadata schema — agent identity, owner, team, model provider, framework, tools, permissions, deployment environment, lifecycle status, risk score, last activity. Show a sample agent record.
Integration with your stack
TODO: Describe how the registry integrates with existing tools — CI/CD pipelines (GitHub Actions, GitLab CI), identity providers (Okta, Azure AD), and observability platforms. Mention SDK and API availability.
From registry to governance
The registry is the foundation for every other Prefactor capability. Runtime policies reference the registry to determine which rules apply to which agents. Cost attribution uses registry metadata to allocate spend to teams. Audit trails link every action back to the registered agent that performed it. Without the registry, governance is guesswork.