AI SDK

Go API. React-native streaming. One path from model call to user interface.

Build text, structured output, tools, and agent loops with one API—without a protocol adapter.

Get started

Go from an empty directory to a real model response in three small steps.

Create the project

Install the core module and only the provider your application uses.

$ mkdir ai-sdk-quickstart
$ cd ai-sdk-quickstart
$ go mod init example.com/ai-sdk-quickstart
$ go get github.com/grafana/ai-sdk
$ go get github.com/grafana/ai-sdk/providers/anthropic

Generate a response

Create a model, pass a typed user message, and handle the ordinary Go result.

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    aisdk "github.com/grafana/ai-sdk"
    "github.com/grafana/ai-sdk/provider"
    "github.com/grafana/ai-sdk/providers/anthropic"
)

func main() {
    apiKey := os.Getenv("ANTHROPIC_API_KEY")
    if apiKey == "" {
        log.Fatal("ANTHROPIC_API_KEY is required")
    }

    model := anthropic.New(apiKey, "claude-sonnet-5")
    result, err := aisdk.GenerateText(context.Background(), model,
        aisdk.WithModelMessages(provider.UserText("Explain goroutines in one sentence.")),
    )
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(result.Text)
}

3
Run it

Set the provider credential and run the program.
Terminal
```
$ ANTHROPIC_API_KEY=sk-... go run .
```
Provider modules stay separate, so applications only carry the integrations they need. Read the installation guide.

Start with what you need to build

Move directly from an application outcome to the maintained guide and runnable code.

Backend

Generate text from GoComplete responses and typed streams

Full stack

Build a React chatGo backend with AI SDK UI hooks

Agents

Add tools and agent loopsTyped functions, approval, and multi-step work

See example apps

AI SDK

Create the project

Generate a response

Run it