From the library

The library is the catalogue of ready-made agents your tenant can add. Adding one never deploys it on the spot: it raises a request that reaches your deployment through a reviewed merge and the release gate, so what runs is always what was tested.

Browsing the library

Agents → Library lists agents from three places:

Namespace	What it holds
aal	Atlantic’s own agents
your tenant’s own	The agents your deployments already report
market/<publisher>	Agents other publishers list on the marketplace, approved by Atlantic

Each entry shows its card’s settings: purpose, triggers, tools, connectors, models, effect, autonomy, budget and timeout. An Atlantic card holds settings and a short purpose, never code. Model prices and Atlantic’s margin are shown to your client_admins; everyone else sees a relative cost tier.

By API: GET /api/v1/library and GET /api/v1/library/{namespace}/{name}. By MCP: library. See the Marketplace reference.

Adding an agent

You need the client_admin role, signed in as a person.

1. Open the agent and choose Add to deployment.
2. Choose the deployment and the version, and add a note if you want one (up to 500 characters).
3. LightHouse records an agent request and writes it to your audit log.

The request goes to your administrators and to Atlantic’s engineers. The card reaches your catalogue through a merge, and the agent runs once its version passes the release gate in your deployment. Follow it in GET /api/v1/agent-requests: open, accepted, declined or done.

A machine key or an MCP client can read the library, never add to it (403 person_required): an agent holding a key cannot add agents.

What you can change

Everything on the card is yours to set in your own catalogue: the tools, the model, the budget, the schedule, the autonomy (within your pack’s ceiling) and the approvers. Changing a card is changing code: it goes through review and the release gate like any other change. See In code and Versioning and rollback.