Go LLM SDK for streaming, tool-calling AI backends (plus frontend React lib)

Grafana released an open-source Go SDK for AI SDK that provides a unified API for calling language models, streaming responses, executing tools, and serving AI-powered endpoints from Go, with wire compatibility with Vercel's AI SDK React frontend hooks. The SDK supports multiple providers including Anthropic, Amazon Bedrock, OpenAI, and Grafana's hosted endpoint, and includes production controls for timeouts, fallback, logging, and Prometheus metrics.

Call language models, stream responses, execute tools, and serve AI-powered endpoints from Go. Use the SDK on its own or pair it with an AI SDK React frontend. The SDK gives Go applications one API for model calls, streaming, tools, structured output, and multi-step agents across supported providers. It follows the design of Vercel's AI SDK https://ai-sdk.dev and stays wire-compatible with its TypeScript frontend hooks. A Go endpoint can stream Server-Sent Events SSE directly to hooks such as useChat . Go backend React frontend ────────── ────────────── aisdk.StreamText ... ── SSE ──▶ useChat { transport } aisdk.WriteUIMessageStream w, … // same protocol See How a request runs /grafana/ai-sdk/blob/main/docs/concepts/architecture.md for the generation, tool, and streaming flow. Reuse an existing AI SDK React frontend or replace a TypeScript backend with Go without adding a protocol adapter. — stream a response or wait for the complete result, with retries and multi-step tool execution StreamText / GenerateText React compatibility — serve useChat , useCompletion , and useObject Composable tools — call plain Go functions from a model and require approval for consequential actions Structured output — generate schema-validated objects, arrays, and choices Multiple providers — call Anthropic, Amazon Bedrock, OpenAI, OpenAI-compatible APIs, and Grafana's hosted endpoint from internal services Production controls — configure timeouts, fallback, logging, Prometheus metrics, and Agent Observability /grafana/ai-sdk/blob/main/docs/middleware/agent-observability.md Create a Go project and install the core module and one provider: 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 See Choose a provider /grafana/ai-sdk/blob/main/docs/providers/overview.md for Amazon Bedrock, OpenAI, OpenAI-compatible APIs, and the internally provisioned Grafana hosted endpoint. Save this complete program as main.go . It makes one model call and prints the response: 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 } Run it with an Anthropic API key: ANTHROPIC API KEY=sk-... go run . For project initialization and credential guidance, follow Installation /grafana/ai-sdk/blob/main/docs/getting-started/installation.md . To stream this response to a React client, continue with Build a full-stack chat /grafana/ai-sdk/blob/main/docs/getting-started/full-stack-chat.md . | Goal | Start here | |---|---| | Make model calls from Go | | Full-stack chat /grafana/ai-sdk/blob/main/docs/getting-started/full-stack-chat.md Structured output /grafana/ai-sdk/blob/main/docs/guides/structured-output.md Tools /grafana/ai-sdk/blob/main/docs/guides/tools.md Agent loops /grafana/ai-sdk/blob/main/docs/guides/agent-loops.md Provider overview /grafana/ai-sdk/blob/main/docs/providers/overview.md Middleware overview /grafana/ai-sdk/blob/main/docs/middleware/overview.md Production checklist /grafana/ai-sdk/blob/main/docs/best-practices/production.md Full index: Documentation · Runnable code: · Exact APIs: Examples /grafana/ai-sdk/blob/main/examples pkg.go.dev https://pkg.go.dev/github.com/grafana/ai-sdk Contributions are welcome. CONTRIBUTING.md /grafana/ai-sdk/blob/main/CONTRIBUTING.md covers the development setup, the two conventions that make this repository unusual — upstream parity with the Vercel AI SDK, and spec-driven development with OpenSpec — and the pull request checklist. All participants follow our Code of Conduct /grafana/ai-sdk/blob/main/CODE OF CONDUCT.md . Apache License 2.0 /grafana/ai-sdk/blob/main/LICENSE . This SDK follows the design of Vercel's AI SDK https://github.com/vercel/ai , also Apache-2.0 licensed; attribution is recorded in NOTICE /grafana/ai-sdk/blob/main/NOTICE .