> For the complete documentation index, see [llms.txt](https://ai.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai.ortusbooks.com/main-components/agents/streaming.md).

# Streaming

Agents support streaming responses, delivering content in real-time chunks as the AI generates them.

## Basic Streaming

```javascript
agent = aiAgent(
    name       : "StreamAgent",
    description: "Streaming assistant"
)

// Accumulate response as it streams
response = ""

agent.stream(
    onChunk: ( chunk ) => {
        content   = chunk.choices?.first()?.delta?.content ?: ""
        response &= content
        print( content )   // Print each chunk immediately
    },
    input: "Write a short story about BoxLang"
)

// response now contains the full text
println( "" )  // New line after stream
```

## Streaming with Parameters

```javascript
agent = aiAgent(
    name  : "Writer",
    params: { temperature: 0.9, max_tokens: 2000 }
)

agent.stream(
    onChunk: ( chunk ) => {
        content = chunk.choices?.first()?.delta?.content ?: ""
        writeOutput( content )
    },
    input  : "Write a blog post about AI in 2026",
    params : { temperature: 0.8 },    // Override params per call
    options: { returnFormat: "single" }
)
```

## Streaming in a Pipeline

Agents implement `IAiRunnable`, so they work in streaming pipelines:

```javascript
pipeline = aiMessage()
    .user( "Write about: ${topic}" )
    .to( agent )

pipeline.stream(
    onChunk: chunk => print( chunk ),
    input  : { topic: "Quantum Computing" }
)
```

## Streaming with Memory

Streaming calls store messages in memory the same as regular calls:

```javascript
agent = aiAgent(
    name  : "ChatBot",
    memory: aiMemory( "window" )
)

// First exchange
agent.run( "My name is Luis" )

// Stream the next response
agent.stream(
    onChunk: chunk => print( chunk.choices?.first()?.delta?.content ?: "" ),
    input  : "What's my name?"
)
// → Streams "Your name is Luis"
```

## Streaming with Per-Call Identity (v3.0+)

```javascript
agent.stream(
    onChunk: chunk => print( chunk.choices?.first()?.delta?.content ?: "" ),
    input  : "Help me with billing",
    options: {
        userId        : "alice",
        conversationId: "conv-001"
    }
)
```

## Resume Streaming (v3.0+)

After a suspension, resume and stream the continuation:

```javascript
// Agent was suspended by HumanInTheLoopMiddleware
result = agent.run( "Deploy to production" )

if ( result.isSuspended() ) {
    threadId = result.getThreadId()

    // Later, resume as a stream:
    agent.resumeStream(
        decision: "approved",
        threadId: threadId,
        onChunk : chunk => print( chunk.choices?.first()?.delta?.content ?: "" )
    )
}
```

## Related Pages

* [Getting Started](/main-components/agents/getting-started.md) — Agent construction and return formats
* [Memory Management](/main-components/agents/memory.md) — Per-call identity routing in streaming
* [Middleware](/main-components/agents/middleware.md) — Intercepting stream lifecycle events
* [Pipeline Streaming](/main-components/pipelines/streaming.md) — Streaming in full pipelines


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ai.ortusbooks.com/main-components/agents/streaming.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.