Skip to main content
Agent SDK for Go is a Go library for building production AI agents. It handles the full execution loop — LLM calls, tool use, approvals, memory, multi-agent delegation — so you write configuration and business logic, not plumbing. Who it’s for: Go backend engineers who want to ship agents in the same language, type system, and deployment pipeline as the rest of their stack — without glue code, dynamic typing, or a Python runtime.

​
Your First Agent

llmClient, _ := openai.NewClient(
    llm.WithAPIKey(os.Getenv("OPENAI_API_KEY")),
    llm.WithModel("gpt-4o"),
)

a, _ := agent.NewAgent(
    agent.WithName("my-agent"),
    agent.WithSystemPrompt("You are a helpful assistant."),
    agent.WithLLMClient(llmClient),
)
defer a.Close()

result, _ := a.Run(ctx, "What is the capital of France?", nil)
fmt.Println(result.Content) // Paris.
That’s it — configure once, call repeatedly. Tools, memory, streaming, and durable execution are additive options — not new APIs to learn.

​
Install

go get github.com/agenticenv/agent-sdk-go@latest
Go 1.26+. OpenAI API key required for the example above; Anthropic and Gemini are also built in. Temporal is optional.

​
Why Agent SDK for Go

  • Idiomatic Go — functional options, typed interfaces, no reflection magic. Swap any component (LLM client, memory backend, approval policy) by passing a different option.
  • Same code, two runtimes — run in-process for development with no infrastructure, then add WithTemporalConfig for crash-proof durable execution in production. Nothing else changes.
  • Concurrent by default — one Agent instance handles parallel Run, RunAsync, and Stream calls; Temporal issues each a unique workflow automatically.
  • Protocol-native integrations — MCP tool servers, A2A agent-to-agent delegation, and AG-UI streaming events are first-class, not adapters bolted on after the fact.
  • Middleware hooks — intercept LLM calls, tool use, retrieval, and memory at any lifecycle point for logging, PII scrubbing, and guardrails without touching agent logic.

​
Runtimes

Run agents locally for development, or with Temporal for production-grade durability and fault tolerance.
In-process (default)Temporal
SetupNo infraRunning Temporal server
DurabilityNoneSurvives crashes and restarts
ScaleSingle processHorizontal worker pools
WhenDev, scripts, low-volume APIsProduction, long-running tasks
Add WithTemporalConfig to switch. See Runtimes.

​
Start here

Quickstart

Your first agent, step by step — under 5 minutes

Architecture

How the agent loop maps to capabilities and runtimes

Runnable examples

Annotated examples for every feature

Temporal runtime

Durable runs, worker separation, crash recovery