Build multi-modal AI applications using our new open-source Vision AI SDK.

Tutorials

Build a Marketplace Voice Shopping Agent with Kimi K2.5 and Vision Agents

Build a voice shopping concierge for a multi-seller marketplace using Kimi K2.5, Deepgram STT, and Vision Agents. Runnable Python, function calling, Stream WebRTC.

Read more
10 min read

Integrate Local and Open-Source Core AI Models Into Stream Chat

Discover how to integrate and use local, free, and open-source Core AI models with Stream Chat.

Read more
10 min read

Building a Live Shopping App with One-Shot AI

The design process behind one-shot generating VinylStream, a live shopping app for buying and selling vinyl - and why a good design document, not the fanciest model, is what makes AI app generation actually work.

Read more
12 min read

Build On-Device Reply Suggestions with Apple's Foundation Models & Stream Chat

Build on-device suggested replies in a SwiftUI chat app with Apple's Foundation Models and Stream Chat. Generation runs entirely on the device: no token cost, no network round-trip.

Read more
16 min read

Build a Voice Agent That Calls to Confirm Fraud Alerts

Build a Python voice agent with Vision Agents that places an outbound call to a cardholder, reads back a suspicious transaction, and either clears it or freezes the card - using Deepgram, an LLM, Cartesia, and Twilio.

Read more
16 min read

How Stream Chat Authentication Works: User Tokens, Refresh, and Secret Handling

Stream Chat authentication works by having your backend sign short-lived JWTs with your API secret. This guide covers the four credentials in play, how to wire token refresh with a tokenProvider, and why your API secret must never leave the server.

Read more
11 min read

Build a Stream Chat App With Xcode 26.3's Coding Agent

Xcode 26.3 ships with a built-in coding agent backed by Claude. Pair it with Stream's Agent Skills and you can build a working SwiftUI chat app from a single goal-level prompt - channel list, message thread, and composer - then iterate without leaving the IDE. This is a build log of exactly that, including the WebSocket race condition the agent diagnosed by reading the SDK source.

Read more
10 min read

How to Build a Background Removal Tool with Segment Anything & Vision Agents

A step-by-step guide to building a real-time background removal tool with SAM 2, YOLO, and Vision Agents. Runs on a CPU, no GPU required.

Read more
22 min read