developing-genkit-go

Files (20)

• SKILL.md
• a2ui.md · references/
• agents-artifacts.md · references/
• agents-background.md · references/
• agents-branching.md · references/
• agents-custom.md · references/
• agents-deployment.md · references/
• agents-human-in-the-loop.md · references/
• agents-multi-agent.md · references/
• agents-sessions.md · references/
• agents-state.md · references/
• agents.md · references/
• flows-and-http.md · references/
• generation.md · references/
• getting-started.md · references/
• middleware.md · references/
• observability.md · references/
• prompts.md · references/
• providers.md · references/
• tools.md · references/

SKILL.md (first lines)

# Genkit Go

Genkit Go is an AI SDK for Go that provides generation, structured output,
streaming, tool calling, prompts, and flows with a unified interface across
model providers.

## Hello World

```go
package main

import (
	"context"
	"fmt"
	"log"
	"net/http"

	"github.com/firebase/genkit/go/ai"
	"github.com/firebase/genkit/go/genkit"
	"github.com/firebase/genkit/go/plugins/googlegenai"
	"github.com/firebase/genkit/go/plugins/server"
)

func main() {
	ctx := context.Background()
	g := genkit.Init(ctx, genkit.WithPlugins(&googlegenai.GoogleAI{}))

	genkit.DefineFlow(g, "jokeFlow", func(ctx context.Context, topic string) (string, error) {
		return genkit.GenerateText(ctx, g,
			ai.WithModelName("googleai/gemini-flash-latest"),
			ai.WithPrompt("Tell me a joke about %s", topic),
		)
	})

	mux := http.NewServeMux()
	for _, f := range genkit.ListFlows(g) {
		mux.HandleFunc("POST /"+f.Name(), genkit.Handler(f))
	}
	log.Fatal(server.Start(ctx, "127.0.0.1:8080", mux))
}
```

## Core Features

Load the appropriate reference based on what you need:

| Feature | Reference | When to load |
| --- | --- | --- |
| Initialization | [references/getting-started.md](references/getting-started.md) | Setting up `genkit.Init`, plugins, the `*Genkit` instance pattern |
| Generation | [references/generation.md](references/generation.md) | `Generate`, `GenerateText`, `GenerateData`, streaming, output formats, `Embed` |
| Prompts | [references/prompts.md](references/prompts.md) | `DefinePrompt`, `DefineDataPrompt`, `.prompt` files, schemas |
| Tools | [references/tools.md](references/tools.md) | `DefineTool`, `DefineResumableTool` interrupts (`Interrupted` claim, `Restart`/`Respond`, `WithResume`), `ai/tool` helpers (`tool.Interrupt`, `tool.Fail`, `tool.AttachParts`) |
| Middleware | [references/middleware.md](references/middleware.md) | `ai.Middleware`, `ai.WithUse`, `Hooks` (Generate/Model/Tool), built-ins (`Retry`, `Fallback`, `ToolApproval`, `Filesystem`, `Skills`, `SoftToolErrors`, `ContextCompression`, `Budget`) |
| Observability | [references/observability.md](references/observability.md) | OpenTelemetry export (`otelgenai`), `tracing.SetInstrumentation`, `aix.Observer`, reflection API outside dev |
| Flows & HTTP | [references/flows-and-http.md](references/flows-and-http.md) | `DefineFlow`, `DefineStreamingFlow`, `genkit.Handler`, HTTP serving |
| Model Providers | [references/providers.md](references/providers.md) | Google AI, Vertex AI, Anthropic, OpenAI-compatible, Ollama setup |

## Agents (Experimental)

Genkit Go has an **experimental** agent API for persistent, multi-turn
conversations (sessions, snapshots, interrupts, branching, background
execution).
It is gated: initialize with `genkit.Init(ctx, genkit.WithExperimental())` or
the
constructors panic. Server constructors come from `genkit/exp` (aliased
`genkitx`); types and options from `ai/exp` (aliased `aix`); session stores from
`ai/exp/localstore`.

- **Agent or flow?** If the task is conversational, multi-turn, or described as
  "an agent", "assistant", or "chatbot", build it with `genkitx.DefineAgent`
  rather than hand-rolling a `Generate` + tools loop in a flow. Reach for a
  plain flow only for single-shot, stateless generation.

For details see:

-   [Agents](references/agents.md): defining/serving an agent, running turns,
    and client- vs server-managed state (start here).
-   [Sessions & persistence](references/agents-sessions.md): session stores
    (`localstore.NewInMemorySessionStore`/`NewFileSessionStore`, PostgreSQL),
    snapshots, and the `sessionstoretest` conformance suite.
-   [Human-in-the-loop / interrupts](references/agents-human-in-the-loop.md):
    pausing for approval/input and resuming.
-   [Branching](references/agents-branching.md): forking a conversation from a
    snapshot.
-   [Background agents](references/agents-background.md): detaching long-running
    turns and polling.
-   [Working with state](references/agents-state.md): typed custom session
    state, streamed as JSON patches.
-   [Artifacts](references/agents-artifacts.md): producing and reading named
    deliverables.
-   [Multi-agent orchestration](references/agents-multi-agent.md): delegating to
    sub-agents, background delegation, `continue_task`, and remote agents
    (`DefineRemoteAgent`).
-   [Advanced custom agents](references/agents-custom.md): `DefineCustomAgent`
    for full turn control.
-   [Deploying agents](references/agents-deployment.md): serving agents over
    HTTP with `genkit.Handler`.

## Generative UI (A2UI)

Genkit Go has an **A2UI** (Agent-to-UI) plugin
(`github.com/firebase/genkit/go/plugins/a2ui/exp`, imported as `a2uix`) that
lets an agent stream interactive UI **surfaces** (cards, lists, forms, buttons),
not just prose. The whole integration is the `&a2uix.Surfaces{}` model
middleware added via `ai.WithUse`
on a generate call or agent inline prompt. **Go is server-only: it has no A2UI
client/renderer.** Render surfaces with a JS or Dart/Flutter client that talks
to
your Go agent over HTTP (the server and clients are wire-compatible).

-   [A2UI](references/a2ui.md): server middleware, options, custom catalogs, and
    security. For the client (rendering surfaces), refer to the A2UI reference
    in the Genkit JS or Dart skill.

## Genkit CLI (recommended)

`genkit start` unintrusively wraps any Go program that uses the Genkit library,
running it unchanged while capturing traces from every Genkit action so you can
prove tools were actually called and inspect model I/O from the terminal, even

From google/skills, Apache-2.0.

More from google/skills