> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agenticenv.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Runtimes Overview

> Choose between in-process and Temporal runtimes based on your durability and infrastructure requirements

Agent SDK for Go supports two execution backends. **In-process is the default** — pass no Temporal options. **Temporal is opt-in** — add `WithTemporalConfig` or `WithTemporalClient` when you need durable, production-grade execution.

Your agent code (`NewAgent`, tools, prompts, streaming) stays the same. Only the configuration changes.

## Comparison

|                           | In-process                            | Temporal                                      |
| ------------------------- | ------------------------------------- | --------------------------------------------- |
| **Enable**                | Default — omit Temporal options       | `WithTemporalConfig` or `WithTemporalClient`  |
| **Infrastructure**        | None beyond your LLM provider         | Running Temporal server or Temporal Cloud     |
| **Where the loop runs**   | Inside your Go process                | Durable workflow + activities                 |
| **Crash recovery**        | No — run is lost if the process exits | Yes — workflow history replays from last step |
| **Horizontal scale**      | Single process only                   | Add workers on task queues                    |
| **Split client / worker** | Not applicable                        | `DisableLocalWorker` + `NewAgentWorker`       |
| **Feature parity**        | Full                                  | Full                                          |
| **Conversation backend**  | In-memory (single process)            | Redis for split-process deployments           |

## When to use in-process

* Developing, testing, or prototyping
* Short-lived runs where crash recovery is not needed
* Zero-infrastructure deployments (serverless, scripts, single binary)

See [In-Process](/runtimes/in-process) for details and limitations.

## When to use Temporal

* Agent runs must survive process crashes, deploys, and restarts
* You need horizontal scaling by adding workers
* You want to split the agent client and worker across separate processes
* Long-running agent sessions require durable orchestration

See [Temporal](/runtimes/temporal) for cluster setup and SDK connection.

## How runtime selection works

The SDK selects a backend from your `NewAgent` options. You never instantiate a runtime directly.

```go theme={null}
// In-process (default)
a, err := agent.NewAgent(
    agent.WithLLMClient(llmClient),
    agent.WithSystemPrompt("You are a helpful assistant."),
)

// Temporal
a, err := agent.NewAgent(
    agent.WithTemporalConfig(&agent.TemporalConfig{
        Host: "localhost", Port: 7233,
        Namespace: "default", TaskQueue: "my-app",
    }),
    agent.WithLLMClient(llmClient),
    agent.WithSystemPrompt("You are a helpful assistant."),
)
```

<Warning>
  Provide **either** `WithTemporalConfig` or `WithTemporalClient`, not both. They configure different levels of the Temporal client lifecycle — mixing them is a compile-time option error.
</Warning>

## Switching runtimes

<Tip>
  Start in-process during development and add Temporal for production with a single config change. The agent code — tools, prompts, streaming, approvals — does not change.
</Tip>

1. Develop with no Temporal options
2. Add `WithTemporalConfig` (or `WithTemporalClient`) for production
3. If you use conversation with a split-process deployment (agent + separate worker), switch from in-memory to Redis. See [Conversation](/features/conversation)

## Related pages

<CardGroup cols={2}>
  <Card title="In-Process" icon="laptop" href="/runtimes/in-process">
    Default runtime — zero infrastructure
  </Card>

  <Card title="Temporal" icon="server" href="/runtimes/temporal">
    Durable workflows, workers, and production deployment
  </Card>

  <Card title="Configuration" icon="sliders" href="/getting-started/configuration">
    WithTemporalConfig, DisableLocalWorker, and all runtime options
  </Card>

  <Card title="Architecture" icon="sitemap" href="/overview/architecture">
    How the agent loop maps to each backend
  </Card>
</CardGroup>