grafana/ai-sdk

Última atividade de origem registrada: 20 de outubro de 2026 às 13:07

Catálogo do SkillsMP atualizado: 2 de novembro de 2026 às 18:02

skills coletadas: 9

Estrelas no GitHub: 262
Forks no GitHub: 16

Instalar com um assistente de IA

Copie este prompt para o assistente de IA que você usa.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/grafana/ai-sdk.

README do repositório

Arquivo de origem do README: README.md

Ler o README original

Expandir README completo

<div align="center"> <img src="docs/assets/ai-sdk-banner.gif" alt="Grafana AI SDK for Go — streaming, tool-calling AI backends that speak fluent @ai-sdk/react" width="960" /> 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. [Quick start](#quick-start) · [Documentation](docs/README.md) · [Examples](examples/) · [API reference](https://pkg.go.dev/github.com/grafana/ai-sdk) </div> --- ## Why 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`. ```text Go backend React frontend ────────── ────────────── aisdk.StreamText(...) ── SSE ──▶ useChat({ transport }) aisdk.WriteUIMessageStream(w, …) // same protocol ``` See [How a request runs](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. ## Features - **`StreamText` / `GenerateText`** — stream a response or wait for the complete result, with retries and multi-step tool execution - **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, and OpenAI-compatible APIs - **Production controls** — configure timeouts, fallback, logging, Prometheus metrics, and [Agent Observability](docs/middleware/agent-observability.md) ## Install Create a Go project and install the core module and one provider: ```bash 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](docs/providers/overview.md) for Amazon Bedrock, OpenAI, and OpenAI-compatible APIs. ## Quick start Save this complete program as `main.go`. It makes one model call and prints the response: ```go 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: ```bash ANTHROPIC_API_KEY=sk-... go run . ``` For project initialization and credential guidance, follow [Installation](docs/getting-started/installation.md). To stream this response to a React client, continue with [Build a full-stack chat](docs/getting-started/full-stack-chat.md). ## Where to go next | Goal | Start here | |---|---| | Make model calls from Go | [Generate text from Go](docs/getting-started/backend-only.md) | | Build a React chat | [Full-stack chat](docs/getting-started/full-stack-chat.md) | | Return typed data | [Structured output](docs/guides/structured-output.md) | | Let a model call Go code | [Tools](docs/guides/tools.md) | | Build a reusable agent | [Agent loops](docs/guides/agent-loops.md) | | Choose a model provider | [Provider overview](docs/providers/overview.md) | | Add logging or observability | [Middleware overview](docs/middleware/overview.md) | | Prepare for production | [Production checklist](docs/best-practices/production.md) | Full index: **[Documentation](docs/README.md)** · Runnable code: **[Examples](examples/)** · Exact APIs: **[pkg.go.dev](https://pkg.go.dev/github.com/grafana/ai-sdk)** ## Contributing Contributions are welcome. [CONTRIBUTING.md](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](CODE_OF_CONDUCT.md). ## License The reusable SDK is licensed under [Apache-2.0](LICENSE). The separate [`ai-gateway/`](ai-gateway/) module is licensed under [AGPL-3.0-only](ai-gateway/LICENSE). See the SDK [NOTICE](NOTICE) and Gateway [NOTICE](ai-gateway/NOTICE) for attribution.

Carregando o README do repositório…

Skills neste repositório

Desenvolvedores de software

1 categorias ocupacionais · 11% classificado