Agent

A self-contained AI agent bundling persona, memory, and conversation history.

Usage

Source

Agent()

An Agent wraps a ChatBot, a PersonaDefinition, a MemoryStore, and a ConversationCapture into a single entity that can participate in multi-agent workflows.

The agent configures its ChatBot automatically from the persona (system prompt, temperature, tools, guardrails) and applies retention policies after each response when a RetentionPolicy is attached.

Parameters

name: str

Unique identifier for this agent (e.g., "triage_bot").

persona: PersonaDefinition

The persona definition that drives the agent’s behavior.

memory: MemoryStore = (lambda: MemoryStore(long_term_path=":memory:"))()


The agent’s memory store. Defaults to an in-memory store.

chatbot: ChatBot = None

A pre-configured ChatBot. If None, one is built from the persona automatically.

capture: ConversationCapture = ConversationCapture()


Conversation capture for recording events. Created automatically if not provided.

instructions: str = ""

Additional instructions appended to the persona’s system prompt.

metadata: dict[str, Any] = dict()


Arbitrary metadata for the agent (e.g., team, version, owner).

Examples

Create an agent from a built-in persona:

import talk_box as tb

agent = tb.Agent.from_persona("code_reviewer")
agent.name          # "code_reviewer"
agent.persona.display_name  # "Code Reviewer"

Create a custom agent with memory and retention:

import talk_box as tb

policy = tb.RetentionPolicy(
    remember_tags=["identity", "preference"],
    forget_tags=["scratch"],
)
agent = tb.Agent(
    name="support_agent",
    persona=tb.create_persona(
        "support",
        persona_role="customer support specialist",
        retention=policy,
    ),
    memory=tb.MemoryStore(long_term_path="support.db"),
)

Respond to a user message:

conversation = agent.respond("How do I reset my password?")