# Agent class

The `Agent` class is the foundation for creating AI agents in Mastra. It provides methods for generating responses, streaming interactions, and handling voice capabilities.

## Usage examples

### Basic string instructions

Passing instructions as a string or array of strings is the simplest way to set up an agent. This is useful for straightforward use cases where you need to provide a prompt without additional configuration.

```typescript
import { Agent } from '@mastra/core/agent'

// String instructions
export const agent = new Agent({
  id: 'test-agent',
  name: 'Test Agent',
  instructions: 'You are a helpful assistant that provides concise answers.',
  model: 'openai/gpt-5.4',
})

// System message object
export const agent2 = new Agent({
  id: 'test-agent-2',
  name: 'Test Agent 2',
  instructions: {
    role: 'system',
    content: 'You are an expert programmer',
  },
  model: 'openai/gpt-5.4',
})

// Array of system messages
export const agent3 = new Agent({
  id: 'test-agent-3',
  name: 'Test Agent 3',
  instructions: [
    { role: 'system', content: 'You are a helpful assistant' },
    { role: 'system', content: 'You have expertise in TypeScript' },
  ],
  model: 'openai/gpt-5.4',
})
```

### Provider-specific configurations

Each model provider also enables a few different options, including prompt caching and configuring reasoning. You can set `providerOptions` on the instruction level to set different caching strategy per system instruction/prompt.

```typescript
import { Agent } from '@mastra/core/agent'

export const agent = new Agent({
  id: 'core-message-agent',
  name: 'Core Message Agent',
  instructions: {
    role: 'system',
    content: 'You are a helpful assistant specialized in technical documentation.',
    providerOptions: {
      openai: {
        reasoningEffort: 'low',
      },
    },
  },
  model: 'openai/gpt-5.4',
})
```

### Mixed instruction formats

```typescript
import { Agent } from '@mastra/core/agent'

// This could be customizable based on the user
const preferredTone = {
  role: 'system',
  content: 'Always maintain a professional and empathetic tone.',
}

export const agent = new Agent({
  id: 'multi-message-agent',
  name: 'Multi Message Agent',
  instructions: [
    { role: 'system', content: 'You are a customer service representative.' },
    preferredTone,
    {
      role: 'system',
      content: 'Escalate complex issues to human agents when needed.',
      providerOptions: {
        anthropic: { cacheControl: { type: 'ephemeral' } },
      },
    },
  ],
  model: 'anthropic/claude-sonnet-4-6',
})
```

## Thread signals

Use Agent signals to send real-time context into a memory thread. Signals are useful when a user adds input while an agent is already streaming, or when another process needs to add structured context to the thread.

A `user-message` signal represents user input. When the target thread is running, Mastra delivers the signal into the active agent loop. When the thread is idle, Mastra starts a stream with the signal as the first input by default.

```typescript
const subscription = await agent.subscribeToThread({
  resourceId: 'user-123',
  threadId: 'thread-abc',
})

void (async () => {
  for await (const chunk of subscription.stream) {
    console.log(chunk)
  }
})()

agent.sendSignal(
  { type: 'user-message', contents: 'Use the latest customer note too.' },
  {
    resourceId: 'user-123',
    threadId: 'thread-abc',
    ifIdle: {
      streamOptions: {
        maxSteps: 3,
      },
    },
  },
)
```

Use `attributes` to identify different users in a shared thread. The signal type and attributes are rendered as XML so the model can distinguish who said what:

```typescript
agent.sendSignal(
  {
    type: 'user',
    contents: 'Can we simplify the API surface?',
    attributes: { name: 'Devin', from: 'slack' },
  },
  { resourceId: 'user-123', threadId: 'thread-abc' },
)
```

The model receives this as:

```xml
<user name="Devin" from="slack">Can we simplify the API surface?</user>
```

The UI sees just the message contents but can also read `attributes` and `metadata` off the signal message for custom rendering (e.g. showing user names, avatars, or platform badges).

### `sendSignal(signal, options)`

Sends a signal to an active run or memory thread.

**signal** (`{ type: 'user-message' | 'system-reminder' | string; contents: string | Array<TextPart | FilePart>; attributes?: Record<string, JSONValue>; metadata?: Record<string, unknown>; providerOptions?: ProviderMetadata }`): \`user-message\` signals without attributes are treated as plain user input. All other signals — including \`user-message\` with \`attributes\`, \`system-reminder\`, and custom types — are wrapped in an XML element named after the signal type with \`attributes\` rendered as XML attributes (e.g. \`\<user name="Devin" from="slack">message\</user>\`). The model sees the XML; the UI sees the raw contents and can read \`attributes\` for custom rendering. \`providerOptions\` is attached to the resulting prompt turn and persisted on the stored signal message.

**options.runId** (`string`): Run ID to target directly. Use this when you already know the active run ID.

**options.resourceId** (`string`): Resource ID for the memory thread. Required with \`threadId\` for thread-targeted signals.

**options.threadId** (`string`): Thread ID to target. Required with \`resourceId\` for thread-targeted signals.

**options.ifActive.behavior** (`'deliver' | 'persist' | 'discard'`): Controls what happens when the target thread is active. Defaults to \`deliver\`.

**options.ifIdle.behavior** (`'wake' | 'persist' | 'discard'`): Controls what happens when the target thread is idle. Defaults to \`wake\`.

**options.ifIdle.streamOptions** (`AgentExecutionOptions`): Options for the stream that starts when \`ifIdle.behavior\` is \`wake\`. Mastra uses the top-level \`resourceId\` and \`threadId\` for memory context.

Returns `{ accepted: true, runId: string, signal: CreatedAgentSignal, persisted?: Promise<void> }`. `persisted` is only present for `persist` behavior and resolves when Mastra finishes writing the signal to memory.

### `subscribeToThread(options)`

Subscribes to raw stream chunks for a memory thread. Use this before calling `sendSignal()` when you need to render stream output, observe signal echoes, or abort the active run.

**options.resourceId** (`string`): Resource ID for the memory thread.

**options.threadId** (`string`): Thread ID to subscribe to.

Returns an `AgentThreadSubscription` object with these members:

**stream** (`AsyncIterable<AgentChunkType>`): Raw agent stream chunks for the subscribed thread.

**activeRunId** (`() => string | null`): Returns the active run ID for the thread, or \`null\` when no run is active.

**abort** (`() => boolean`): Aborts the active run for the thread. Returns \`true\` when a run was aborted.

**unsubscribe** (`() => void`): Stops the subscription without aborting the active run.

## Constructor parameters

**id** (`string`): Unique identifier for the agent. Defaults to \`name\` if not provided.

**name** (`string`): Display name for the agent. Used as the identifier if \`id\` is not provided.

**description** (`string`): Optional description of the agent's purpose and capabilities.

**metadata** (`Record<string, unknown> | ({ requestContext: RequestContext }) => Record<string, unknown> | Promise<Record<string, unknown>>`): Optional metadata for classifying or filtering the agent in clients. Can be a static record or a function that resolves the metadata from the request context.

**instructions** (`SystemMessage | ({ requestContext: RequestContext }) => SystemMessage | Promise<SystemMessage>`): Instructions that guide the agent's behavior. Can be a string, array of strings, system message object, array of system messages, or a function that returns any of these types dynamically. SystemMessage types: string | string\[] | CoreSystemMessage | CoreSystemMessage\[] | SystemModelMessage | SystemModelMessage\[]

**model** (`MastraLanguageModel | ({ requestContext: RequestContext }) => MastraLanguageModel | Promise<MastraLanguageModel>`): The language model used by the agent. Can be provided statically or resolved at runtime.

**agents** (`Record<string, Agent> | ({ requestContext: RequestContext }) => Record<string, Agent> | Promise<Record<string, Agent>>`): Subagents that the agent can access. Can be provided statically or resolved dynamically.

**tools** (`ToolsInput | ({ requestContext: RequestContext }) => ToolsInput | Promise<ToolsInput>`): Tools that the agent can access. Can be provided statically or resolved dynamically.

**transform** (`ToolPayloadTransformPolicy`): Shared policy for transforming tool payloads before display streams or user-visible transcript messages receive them. Use per-tool \`transform\` on \`createTool()\` for tool-local rules.

**workflows** (`Record<string, Workflow> | ({ requestContext: RequestContext }) => Record<string, Workflow> | Promise<Record<string, Workflow>>`): Workflows that the agent can execute. Can be static or dynamically resolved.

**defaultOptions** (`AgentExecutionOptions | ({ requestContext: RequestContext }) => AgentExecutionOptions | Promise<AgentExecutionOptions>`): Default options used when calling \`stream()\` and \`generate()\`.

**defaultGenerateOptionsLegacy** (`AgentGenerateOptions | ({ requestContext: RequestContext }) => AgentGenerateOptions | Promise<AgentGenerateOptions>`): Default options used when calling \`generateLegacy()\`.

**defaultStreamOptionsLegacy** (`AgentStreamOptions | ({ requestContext: RequestContext }) => AgentStreamOptions | Promise<AgentStreamOptions>`): Default options used when calling \`streamLegacy()\`.

**mastra** (`Mastra`): Reference to the Mastra runtime instance (injected automatically).

**scorers** (`MastraScorers | ({ requestContext: RequestContext }) => MastraScorers | Promise<MastraScorers>`): Scoring configuration for runtime evaluation and telemetry. Can be static or dynamically provided.

**memory** (`MastraMemory | ({ requestContext: RequestContext }) => MastraMemory | Promise<MastraMemory>`): Memory module used for storing and retrieving stateful context.

**voice** (`CompositeVoice`): Voice settings for speech input and output.

**inputProcessors** (`(Processor | ProcessorWorkflow)[] | ({ requestContext: RequestContext }) => (Processor | ProcessorWorkflow)[] | Promise<(Processor | ProcessorWorkflow)[]>`): Input processors that can modify or validate messages before they are processed by the agent. Can be individual Processor objects or workflows created with \`createWorkflow()\` using ProcessorStepSchema.

**outputProcessors** (`(Processor | ProcessorWorkflow)[] | ({ requestContext: RequestContext }) => (Processor | ProcessorWorkflow)[] | Promise<(Processor | ProcessorWorkflow)[]>`): Output processors that can modify or validate messages from the agent before they are sent to the client. Can be individual Processor objects or workflows.

**maxProcessorRetries** (`number`): Maximum number of times a processor can request retrying the LLM step.

**requestContextSchema** (`StandardJSONSchemaV1`): Standard JSON Schema for validating request context values. When provided, the context is validated at the start of generate() or stream(), throwing a MastraError if validation fails.

## Returns

**agent** (`Agent<TAgentId, TTools>`): A new Agent instance with the specified configuration.