Runtimes Overview

​

Comparison

​

When to use in-process

• Short-lived runs where crash recovery is not needed
• Zero-infrastructure deployments (serverless, scripts, single binary)

​

When to use Temporal

• Agent runs must survive process crashes, deploys, and restarts
• You need horizontal scaling by adding workers on a task queue
• You want to split the agent client and worker across separate processes (NewAgentWorker)
• Long-running agent sessions require durable orchestration on Temporal

​

When to use Restate

• Agent runs must survive process crashes, deploys, and restarts
• You prefer Restate’s ingress + embedded endpoint model
• You want durable streaming and approvals with the same public Run / Stream / reconnect APIs
• Long-running agent sessions require durable orchestration on Restate

​

How runtime selection works

// In-process (default)
a, err := agent.NewAgent(
    agent.WithLLMClient(llmClient),
    agent.WithSystemPrompt("You are a helpful assistant."),
)

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

// Restate
a, err := agent.NewAgent(
    restate.WithRestateConfig(&restate.RestateConfig{
        Ingress:  restate.IngressConfig{URL: "http://localhost:8080"},
        Endpoint: restate.EndpointConfig{ListenAddress: ":9080", AdminURL: "http://localhost:9070"},
    }),
    agent.WithLLMClient(llmClient),
    agent.WithSystemPrompt("You are a helpful assistant."),
)

​

Switching runtimes

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

​

Related pages