Deep agents use a modular middleware architecture where each core capability is implemented as composable middleware. This design allows you to customize agent behavior by adding, removing, or modifying middleware.
Learn more: For architecture details and customization patterns, see the Middleware documentation.
Middleware for providing filesystem and optional execution tools to an agent.
Middleware for providing subagents to an agent via a task tool.
Middleware for loading agent memory from AGENTS.md files.
Middleware for loading and exposing agent skills to the system prompt.
