Memory - Agno

Memory is a class that manages conversation history, session summaries, and long-term user memories for AI agents. It provides comprehensive memory management capabilities including adding new memories, searching memories, and deleting memories.

Parameters

Parameter	Type	Description	Default
`model`	`Optional[Model]`	Model used for memories and summaries	`None`
`memory_manager`	`Optional[MemoryManager]`	Manager for memory operations	`None`
`summarizer`	`Optional[SessionSummarizer]`	Summarizer for generating session summaries	`None`
`db`	`Optional[MemoryDb]`	Database for storing memories	`None`
`debug_mode`	`bool`	Whether to enable debug logging	`False`

Key Methods

User Memory Management

Method	Description	Parameters	Returns
`get_user_memories`	Retrieves all memories for a user	`user_id: str`	`List[UserMemory]`
`get_user_memory`	Gets a specific memory	`user_id: str, memory_id: str`	`UserMemory`
`add_user_memory`	Adds a new memory and gets the memory id	`memory: UserMemory, user_id: Optional[str] = None`	`str`
`replace_user_memory`	Updates an existing memory and gets the memory id	`memory_id: str, memory: UserMemory, user_id: Optional[str] = None`	`str`
`delete_user_memory`	Deletes a memory	`user_id: str, memory_id: str`	`None`
`create_user_memories`	Creates memories from one or more messages	`message: Optional[str] = None, messages: Optional[List[Message]] = None, user_id: Optional[str] = None`	`str`
`acreate_user_memories`	Creates memories from one or more messages (Async)	`message: Optional[str] = None, messages: Optional[List[Message]] = None, user_id: Optional[str] = None`	`str`
`search_user_memories`	Searches user memories using specified retrieval method	`query: Optional[str] = None, limit: Optional[int] = None, retrieval_method: Optional[Literal["last_n", "first_n", "semantic"]] = None, user_id: Optional[str] = None`	`List[UserMemory]`

Session Summary Management

Method	Description	Parameters
`get_session_summaries`	Retrieves all session summaries for a user	`user_id: str`
`get_session_summary`	Gets a specific session summary	`user_id: str, session_id: str`
`create_session_summary`	Creates a summary for a session from the stored session runs	`session_id: str, user_id: Optional[str] = None`
`acreate_session_summary`	Creates a summary for a session from the stored session runs (Async)	`session_id: str, user_id: Optional[str] = None`
`delete_session_summary`	Deletes a session summary	`user_id: str, session_id: str`

UserMemory

Parameter	Type	Description	Default
`memory`	`str`	The actual memory content	Required
`topics`	`Optional[List[str]]`	Topics or categories of the memory	`None`
`input`	`Optional[str]`	Original input that generated the memory	`None`
`last_updated`	`Optional[datetime]`	When the memory was last updated	`None`
`memory_id`	`Optional[str]`	Unique identifier for the memory	`None`

SessionSummary

Parameter	Type	Description	Default
`summary`	`str`	Concise summary of the session	Required
`topics`	`Optional[List[str]]`	Topics discussed in the session	`None`
`last_updated`	`Optional[datetime]`	When the summary was last updated	`None`

Memory Manager

Parameter	Type	Description	Default
`model`	`Optional[Model]`	Model used for managing memories	`None`
`system_message`	`Optional[str]`	Custom system prompt for the memory manager	`None`
`additional_instructions`	`Optional[str]`	Additional instructions added to the end of the system message	`None`

Session Summarizer

Parameter	Type	Description	Default
`model`	`Optional[Model]`	Model used for summarizing sessions	`None`
`system_message`	`Optional[str]`	Custom system prompt for the summarizer	`None`
`additional_instructions`	`Optional[str]`	Additional instructions added to the end of the system message	`None`