AI / Agents with Restate

Learn how to build durable AI agents and integrate popular AI SDKs with Restate.

Restate makes AI agents and workflows innately resilient. Restate provides the reliability infrastructure you need to run AI workloads in production - from simple LLM chains to complex multi-agent systems.

restatedev/ai-examples

Browse through all AI examples here

Why Restate?

Restate makes building AI workflows and agent easy:

• ✅ Recovery from failures - Never lose agent progress again
• ✅ Built-in session management - Store context in Restate’s K/V store
• ✅ Complete observability - Trace every decision and action
• ✅ Composable patterns - From simple agents to complex multi-agent systems
• ✅ Production safety - Approvals, timeouts, rollbacks, and more

Whether you’re building chatbots, autonomous agents, or AI-powered workflows, Restate handles the complexity of distributed execution so you can focus on your AI logic.

LLM & Agent SDK Integrations

Get started quickly by integrating Restate with your favorite LLM and Agent SDKs. Restate works with most AI SDKs that allow you to wrap model calls and tools, enabling durable execution for your AI workloads.

Vercel AI SDK

OpenAI Agents SDK

LiteLLM

Google ADK

Integrating with other AI SDKs

Composable AI Patterns

If you prefer to own your control flow and only want to use an LLM SDK for model calls, Restate turns your custom logic into durable, fault-tolerant workflows.

Prompt chaining

Build fault-tolerant processing pipelines with automatic retries and recovery.

Tools and Workflows

Implement recoverable routing and tool execution with Restate.

Multi-Agent Systems

Coordinate multiple AI agents to collaborate on complex tasks and workflows.

Sessions & chat

Build stateful chat sessions with persistent context and concurrency control.

Human-in-the-loop

Integrate human feedback and approval steps into AI workflows and agent decision-making.

Parallelization

Execute multiple tools and agents concurrently with deterministic recovery.

Competitive racing

Start multiple workflows/agents, return the first result, cancel the rest.

Notify when ready

Resilient async notifications for late responses of long-running agents.

Roll back on failures

Undo completed work when an agent fails to execute the entire workflow.

Other Resources

Blog posts:

• Announcements:
  • Vercel AI SDK Integration
  • OpenAI Agents SDK
  • Google ADK
• Durable AI Loops: Fault Tolerance across Frameworks and without Handcuffs
• AI Agents should be serverless and durable
• A Durable Coding Agent — with Modal and Restate

Webinars:

• Video: Durable AI Agents with Restate - Community Meeting July 2025