Skip to main content
OpenAgentCore separates orchestration, compute and native execution. Core owns the API and durable state. Sandbox Providers manage compute. A Runtime daemon prepares an Environment and runs the selected Harness, whose native SDK or protocol owns the model and tool loop. Dashed arrows show provisioning and installation. Solid arrows show component interactions, including in-process interfaces. The daemon initiates its authenticated WebSocket connection to Core. The API index describes the application, operator and machine namespaces; protocol boundaries lists each protocol’s code and owning document.

​
Component responsibilities

The repository map locates these components. Concepts and ownership explains Project boundaries, administrator authority and tool isolation.

​
A Session, end to end

An application creates a Session through the Agents API. Core resolves its configuration and execution location. A managed Session obtains compute through the selected Sandbox Provider; a self-hosted Session waits for the user to run its installation command. A Session with environment: none uses a connected execution device without a workspace. The application guide describes these choices. After the daemon connects, Core checks the available Harness and requested capabilities. The Runtime prepares a workspace Environment and its capability snapshot, then prepares or reuses the Session Executor. Each Turn runs through the native Harness. Core persists the output, tool interactions and receipts for application reads and events. Completion or cancellation settles the Turn; a healthy Executor can serve the next Turn in the same Environment. Execution and compute have separate lifetimes: closing an Executor preserves its allocation and workspace until the Provider reclaims them. Preparation, connection and execution readiness have distinct states. The Environment contract owns preparation, and the Core–Runtime protocol owns ordering, receipts and failure handling.