Skip to main content

​
Overview

Streaming lets your application receive execution updates while work is still running. Instead of waiting for the final result, you can render LLM tokens, tool activity, Flow lifecycle events, and conversation messages as they happen. CrewAI has two streaming surfaces: For new runtime integrations, UIs, terminal apps, service bridges, and conversational surfaces, use frame streaming. It provides one stable event envelope across the runtime.

​
StreamFrame

A StreamFrame is the common object emitted by streamable runtimes:
The important fields for most consumers are:

​
Channels

Frames are grouped into high-level channels: The stream itself remains one ordered timeline. Channel projections let consumers focus on only part of that timeline.

​
Stream Sessions

Frame streaming returns a stream session:
The session is both an iterator and the holder for the final result:
Consume the stream before reading stream.result. Reading the result too early raises an error because the runtime may still be producing frames.

​
Channel Projections

Use channel projections when you only need one kind of frame:
Available projections:

​
Entrypoints

Use the entrypoint that matches the runtime you are streaming: Direct llm.call(...) still returns the final assembled LLM result. Use llm.stream_events(...) when you want to iterate over LLM chunks as they arrive.