MemoryMiddleware

MemoryMiddleware(
  self,
  *,
  backend: BACKEND_TYPES,
  sources: list[str],
  add_cache_control:

Bases

AgentMiddleware[MemoryState, ContextT, ResponseT]

Constructors

Attributes

Methods

View source on GitHub

Parameters

Name	Type	Description
`backend`*	`BACKEND_TYPES`	Backend instance or factory function that takes runtime and returns a backend. Use a factory for StateBackend.
`sources`*	`list[str]`	List of memory file paths to load (e.g., `["~/.deepagents/AGENTS.md", "./.deepagents/AGENTS.md"]`). Display names are automatically derived from the paths. Sources are loaded in order.
`add_cache_control`	`bool`	Default:`False` If `True`, tag the last system-message content block with `cache_control: {"type": "ephemeral"}` when the request model is `ChatAnthropic`. This creates a second prompt-cache breakpoint that pairs with `AnthropicPromptCachingMiddleware`'s breakpoint on the static system prompt, keeping the memory block boundary cached across turns (memory content would otherwise shift after every update and invalidate the prefix cache). No-ops on non-Anthropic models; Bedrock and Vertex wrappers do not qualify.
`system_prompt`	`str \| None`	Default:`MEMORY_SYSTEM_PROMPT`

constructor

__init__

Name	Type
backend	BACKEND_TYPES
sources	list[str]
add_cache_control	bool
system_prompt	str \| None

Middleware for loading agent memory from AGENTS.md files.

Loads memory content from configured sources and injects into the system prompt. Supports multiple sources that are combined together. See constructor for the full argument list.

System-prompt fragment template. Must contain a {agent_memory} slot for runtime memory substitution. Pass None to skip appending entirely (memory is still loaded into state["memory_contents"]).