agents.ltm.memory_schemas

Memory schemas for LTM agent using LangMem patterns.

These schemas define the structure of memories that will be extracted and managed by the LTM agent.

Classes

ConversationalMemory	General conversational memory.
FactualMemory	Factual information memory.
Memory	Basic memory schema following LangMem patterns.
PersonalContext	Personal context and relationship memory.
UserPreference	User preference memory.

Module Contents

class agents.ltm.memory_schemas.ConversationalMemory(/, **data)

Bases: pydantic.BaseModel

General conversational memory.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

class agents.ltm.memory_schemas.FactualMemory(/, **data)

Bases: pydantic.BaseModel

Factual information memory.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

class agents.ltm.memory_schemas.Memory(/, **data)

Bases: pydantic.BaseModel

Basic memory schema following LangMem patterns.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

class agents.ltm.memory_schemas.PersonalContext(/, **data)

Bases: pydantic.BaseModel

Personal context and relationship memory.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

class agents.ltm.memory_schemas.UserPreference(/, **data)

Bases: pydantic.BaseModel

User preference memory.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)