Strands Agents Typescript SDK
    Preparing search index...

    Type Alias AgentConfig

    Configuration object for creating a new Agent.

    type AgentConfig = {
        model?: Model<BaseModelConfig> | string;
        messages?: Message[] | MessageData[];
        tools?: ToolList;
        systemPrompt?: SystemPrompt | SystemPromptData;
        state?: Record<string, JSONValue>;
        printer?: boolean;
        conversationManager?: HookProvider;
        hooks?: HookProvider[];
    }
    Index

    Properties

    model?: Model<BaseModelConfig> | string

    The model instance that the agent will use to make decisions. Accepts either a Model instance or a string representing a Bedrock model ID. When a string is provided, it will be used to create a BedrockModel instance.

    // Using a string model ID (creates BedrockModel)
    const agent = new Agent({
    model: 'anthropic.claude-3-5-sonnet-20240620-v1:0'
    })

    // Using an explicit BedrockModel instance with configuration
    const agent = new Agent({
    model: new BedrockModel({
    modelId: 'anthropic.claude-3-5-sonnet-20240620-v1:0',
    temperature: 0.7,
    maxTokens: 2048
    })
    })
    messages?: Message[] | MessageData[]

    An initial set of messages to seed the agent's conversation history.

    tools?: ToolList

    An initial set of tools to register with the agent. Accepts nested arrays of tools at any depth, which will be flattened automatically.

    A system prompt which guides model behavior.

    state?: Record<string, JSONValue>

    Optional initial state values for the agent.

    printer?: boolean

    Enable automatic printing of agent output to console. When true, prints text generation, reasoning, and tool usage as they occur. Defaults to true.

    conversationManager?: HookProvider

    Conversation manager for handling message history and context overflow. Defaults to SlidingWindowConversationManager with windowSize of 40.

    hooks?: HookProvider[]

    Hook providers to register with the agent. Hooks enable observing and extending agent behavior.