AI / Agents with Restate

Build durable AI agents and workflows that recover from failures, maintain state, and scale to production.

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

AI Agent Quickstart

Build and run your first durable AI agent in minutes.

Why Restate?

Restate makes building AI workflows and agents 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.

SDK integrations

Any LLM SDK — write the agent loop yourself with OpenAI, Anthropic, Vercel AI SDK, Google Gen AI, LiteLLM, or any other SDK. Wrap LLM calls in ctx.run() for durability.

Vercel AI SDK

LiteLLM

Any other SDK

Agent frameworks — higher-level APIs for a faster start.

Vercel AI SDK

OpenAI Agents SDK

Google ADK

Pydantic AI

LangChain

Integrating with other SDKs

Want another integration? Reach out on Discord or Slack.

Getting Started

The following pages give you a tour of how to build durable AI agents and workflows with Restate:

1. Durable Agents

Implement agents that survive crashes and recover automatically. Every LLM call and tool execution is durably persisted.

2. Durable Sessions

Add persistent sessions keyed by ID with built-in concurrency control. Conversation state survives crashes and restarts.

3. Approvals with Pause & Resume

Add resilient human approvals that pause the agent and resume when the response arrives, even across restarts.

4. Multi-Agent Orchestration

Route tasks between specialized agents with durable routing decisions. Coordinate via handoffs, tools, or remote calls.

5. Observability & Control

Inspect agent execution step by step, export traces, and cancel or kill stuck agents.

Implementation Guides

The following pages provide detailed implementation guides for common AI patterns:

Parallel Tool Calls

Workflows

Workflows as Tools

Remote Agents

Racing Agents

Interrupt & Regenerate

Retries & Error Handling

Rollback on Failures

Chat UI Integration

Streaming Responses

Notify when ready