Skip to content

LightHouse documentation

Every agent in sight. Every cost in check. Every call on the record. How LightHouse and the Atlantic Agentic Engine work, how to connect them to your estate, and what they do with your data.
01Start hereLightHouse manages your agents, models, approvals, access and billing, on the Atlantic Agentic Engine, and reports on them in six areas.02ConceptsThe ideas LightHouse and the engine are built from, and how they fit together.03Connect your estateEvery connector, the three ways to connect it, the read-only scopes it asks for, and what it indexes.04CloudsWhere the engine runs: your AWS, Azure or Google Cloud account, your own servers, or Atlantic-hosted.05Build agentsThree ways to build an agent: from the library, with the builder, or in code.06SecurityEvery control: what it is, where it is enforced, and how you can verify it yourself.07Data sovereigntyYour content stays in your account and is read in place. Export to Atlantic is opt-in and off by default.08Cost and token optimisationHow cost is measured, how every saving is calculated, and how to reproduce the figure yourself.09The model routerThe router picks the cheapest model that meets the quality bar for the job, not the cheapest model.10APILightHouse's HTTP API: your tenant's host, authentication, conventions, and the generated reference.11MCPLightHouse's reads as Model Context Protocol tools, for Claude, Cursor, Codex and any MCP client.12CLIThe LightHouse command line: install, sign in, and every command.13SDKsPython and TypeScript clients, generated from the OpenAPI document.14OperationsRunning LightHouse and the engine day to day.15TrustSub-processors, the security controls summary, status and change notices.16ChangelogWhat changed in each release of LightHouse and the engine.

Last updated: