ai-core/chat-experience
OfficialShip streaming AI chat experiences instantly.
Software Engineering#multimodal#server-sent-events#usechat#adapter-configuration#tanstack-ai#chat-streaming#thinking-parts
AuthorTanStack
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Stops teams from piecing together incompatible TanStack AI chat endpoints, streaming clients, and rendering rules by documenting the complete SSE/HTTP architecture for server and framework hooks.
Core Features & Use Cases
- Streaming chat lifecycle: Demonstrates how to expose chat() streams via toServerSentEventsResponse or toHttpResponse while wiring framework-specific fetchers like fetchServerSentEvents and fetchHttpStream.
- Multimodal and thinking content rendering: Shows how to render UIMessage parts (text, thinking, tool-call, image) along with adapter modelOptions to surface reasoning and multimedia inside useChat.
- Use Case: Power a help-center assistant that streams Claude or Gemini thinking, renders images from the model, and respects middleware analytics while avoiding outdated Vercel patterns.
Quick Start
Spin up a TanStack Start chat route feeding chat() into toServerSentEventsResponse and connect useChat with fetchServerSentEvents to stream UIMessage parts, including thinking and multimodal content, to the client.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: ai-core/chat-experience Download link: https://github.com/TanStack/ai/archive/main.zip#ai-core-chat-experience Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.