tanstack-ai

Generates streaming, tool-calling AI responses across multiple providers with React hooks.

Updated Mar 10, 2026

Search Tags:#ai #sdk #tool calling #streaming #gemini #openai #anthropic

Ready to run

npx skills add https://github.com/dotlab-hq/medisync --skill tanstack-ai-dotlab-hq

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tanstack-ai
Source: https://github.com/dotlab-hq/medisync/tree/main/.agents/skills/tanstack-ai
Command: npx skills add https://github.com/dotlab-hq/medisync --skill tanstack-ai-dotlab-hq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill simplifies integrating AI models into applications by providing a unified, type-safe interface across various AI providers and frameworks.

Core Features & Use Cases

Unified AI Interface: Interact with models from OpenAI, Anthropic, Gemini, and Ollama through a single SDK.
Streaming & Tool Calling: Supports real-time text streaming, structured output generation, and complex tool-use workflows.
Use Case: Build a customer support chatbot that can understand user queries, call external APIs to fetch information (like order status), and provide a coherent, streaming response to the user.

Quick Start

Use the tanstack-ai skill to generate a response to the prompt "Explain React hooks in 3 sentences."

Frequently Asked Questions about tanstack-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

What is a provider-agnostic AI SDK for streaming and tool calling?▼

A provider-agnostic AI SDK provides a unified, type-safe interface to interact with models from OpenAI, Anthropic, Gemini, and Ollama. It supports real-time text streaming, structured output generation, and complex agentic tool-use workflows across these platforms.

How do I integrate OpenAI and Anthropic models into a single application?▼

You integrate OpenAI and Anthropic models by using a unified AI SDK with adapters for different providers. This allows you to interact with multiple models through a single type-safe interface, enabling multimodal content generation and tool calling without provider-specific code.

Can I build a customer support chatbot with streaming responses and API tool calling?▼

You can build a customer support chatbot using a provider-agnostic AI SDK that supports real-time text streaming and complex tool-use workflows. The chatbot can understand user queries, call external APIs to fetch information like order status, and provide coherent streaming responses.

Does the AI SDK support React and Solid hooks for UI development?▼

The AI SDK supports React and Solid hooks for UI development, allowing you to integrate streaming and tool calling directly into your frontend components. It also integrates with server functions to ensure secure API key management.

How do I manage API keys securely when using multiple AI providers?▼

You manage API keys securely by integrating the provider-agnostic AI SDK with server functions. This setup handles API key management for OpenAI, Anthropic, Gemini, and Ollama adapters without exposing sensitive credentials to the client-side UI.

What's the best way to run complex agentic loops across different AI models?▼

The best way to run complex agentic loops is using a type-safe AI SDK that supports structured output and tool calling across multiple providers. It provides a unified interface to orchestrate sequential tool-use workflows and generate multimodal content.