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.
Provides tools for context management through file operations. This is one of the main challenges in building effective agents—the filesystem middleware helps agents work with large amounts of context without overflowing the context window.
| Tool | Description |
|---|---|
ls |
List files in a directory |
read_file |
Read file contents |
write_file |
Write content to a file |
edit_file |
Edit an existing file |
glob |
Find files matching a pattern |
grep |
Search for text within files |
execute |
Run shell commands (sandbox backends only) |
Provides the task tool for spawning specialized subagents. Subagents are useful for:
Learn more: See Subagents for usage patterns.
Enables long-term memory capabilities using LangGraph Store.
Learn more: See Long-term Memory for usage patterns.
Provides agent-scoped memory that persists across conversations.
Automatically summarizes long conversations to prevent context overflow.
Loads reusable skill modules to extend agent capabilities.
Learn more: See Skills for creating and loading skills.
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.
