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.
Create filesystem middleware with all tools and features.
Create subagent middleware with task tool
Create middleware for loading agent memory from AGENTS.md files.
Create summarization middleware with backend support for conversation history offloading.
Create backend-agnostic middleware for loading and exposing agent skills.
Create middleware for loading agent-specific long-term memory.
Options for creating filesystem middleware.
Options for creating subagent middleware
Options for the memory middleware.
Options for the agent memory middleware.
Options for the summarization middleware.
Options for the skills middleware.
