ai-examples

<!-- markdown-link-check-disable --> [](https://docs.restate.dev) [](https://discord.restate.dev) [](https://slack.restate.dev) [](https://x.com/intent/follow?screen_name=restatedev) <!-- markdown-link-check-enable --> # Durable Agents and AI workflows with Restate This repo contains a set of runnable examples of AI workflows and agents, using **Durable Execution and Orchestration** via [Restate](https://restate.dev/) ([Github](https://github.com/restatedev/restate)) The goal is to show how you can easily add production-grade _resilience_, _state persistence_, _retries_, _suspend/resume_, _human-in-the-loop_, and _observability_ to agentic workflows. So you can ship agents that stay alive and consistent without sprinkling retry-code everywhere and without building heavyweight infra yourself. The Restate approach works **independent of specific SDKs** but **integrates easily with popular Agent SDKs**, like the [Vercel AI SDK](https://ai-sdk.dev/), the [OpenAI Agent SDK](https://openai.github.io/openai-agents-python/), [Google ADK](https://google.github.io/adk-docs/), [Pydantic AI](https://ai.pydantic.dev/), and [LangChain](https://www.langchain.com/). Alternatively, you can also roll your own agent loop by combining Restate with any LLM SDK. ## Why Restate? | Use Case | What it solves | |------------------------------------|------------------------------------------------------------------------------------------------------| | **Durable Execution** | Crash-safe model and tool calls, idempotent retries, agents that resume at the last successful step. | | **Detailed Observability** | Auto-captured trace of every step, retry, and message for easy debugging and auditing. | | **Human-in-the-loop & long waits** | Suspend while waiting for user approval or slow jobs; pay for compute, not wall-clock time. | | **Stateful sessions / memory** | Keep multi-turn conversations and other state isolated and consistent. | | **Multi-agent orchestration** | Reliable RPC, queuing, and scheduling between agents running in separate processes. | <img src="/doc/img/patterns/parallel_tools.png" alt="Restate UI - trace of agent with parallel tools" width="900px"/> <br/> <caption><em>Restate UI showing an agent execution with parallel tool calls</em></caption> ## Quickstart Templates Restate integrates with popular Agent SDKs and with all LLM SDKs (only abstracting away the LLM API). | Integration | Quickstart | Template | |------------------------------------|------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------| | **Vercel AI SDK** | [📖](https://docs.restate.dev/ai-quickstart) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/template/README.md) | | **OpenAI Agents SDK** | [📖](https://docs.restate.dev/ai-quickstart) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/template/README.md) | | **Google ADK** | [📖](https://docs.restate.dev/ai-quickstart) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/template/README.md) | | **Pydantic AI** | [📖](https://docs.restate.dev/ai-quickstart) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/template/README.md) | | **LangChain** | [📖](https://docs.restate.dev/ai-quickstart) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/template/README.md) | | **Restate - Python - any LLM SDK** | [📖](https://docs.restate.dev/ai-quickstart) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/template/README.md) | | **Restate - TS - any LLM SDK** | [📖](https://docs.restate.dev/ai-quickstart) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/template/README.md) | ## Getting Started - Basic Examples | Pattern | Docs | Restate + LLM SDK | Vercel AI | OpenAI | ADK | Pydantic AI | LangChain | |---------|------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------|--------|-----|-------------|-----------| | **Durable agents**: Build AI agents that survive crashes and recover automatically | [📖](https://docs.restate.dev/ai/patterns/durable-agents) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/template/agent.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/template/src/agent.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/template/src/app.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/template/agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/template/agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/template/agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/template/agent.py) | | **Durable Sessions**: Persistent, isolated agent sessions | [📖](https://docs.restate.dev/ai/patterns/sessions) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/chat_agent.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/chat-agent.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/chat-agent.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/chat_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/chat_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/chat_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/chat_agent.py) | | **Human approvals with pause/resume**: Human approval steps that suspend execution | [📖](https://docs.restate.dev/ai/patterns/human-in-the-loop) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/human_approval_agent.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/human-approval-agent.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/human-approval-agent.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/human_approval_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/human_approval_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/human_approval_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/human_approval_agent.py) | | **Multi-agent orchestration**: Route requests to specialized agents | [📖](https://docs.restate.dev/ai/patterns/multi-agent) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/multi_agent.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/multi-agent.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/multi-agent.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/multi_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/multi_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/multi_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/multi_agent.py) | ## Implementation Guides ### Orchestration Guides | Pattern | Docs | Restate + LLM SDK | Vercel AI | OpenAI | ADK | Pydantic AI | LangChain | |----------------------------------------------------------------------------------------------------------|------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------|--------|-----|-------------|-----------| | **Parallel tool calls**: Run multiple tools in parallel with recovery and coordination | [📖](https://docs.restate.dev/ai/patterns/parallelization) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/workflow_parallel.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/workflow-parallel.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/workflow-parallel.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/workflow_parallel.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/workflow_parallel.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/workflow_parallel.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/workflow_parallel.py) | | **Sequential LLM calls**: Chain agents in multi-step pipelines | [📖](https://docs.restate.dev/ai/patterns/workflow-sequential) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/workflow_sequential.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/workflow-sequential.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/workflow-sequential.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/workflow_sequential.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/workflow_sequential.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/workflow_sequential.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/workflow_sequential.py) | | **Parallel agents**: Executing multiple agents in parallel | [📖](https://docs.restate.dev/ai/patterns/workflow-parallel) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/workflow_parallel.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/workflow-parallel.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/workflow-parallel.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/workflow_sequential.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/workflow_parallel.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/workflow_parallel.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/workflow_parallel.py) | | **Orchestrator-worker**: Break tasks into specialized subtasks | [📖](https://docs.restate.dev/ai/patterns/workflow-orchestrator) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/workflow_orchestrator.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/workflow-orchestrator.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/workflow-orchestrator.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/workflow_orchestrator.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/workflow_orchestrator.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/workflow_orchestrator.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/workflow_orchestrator.py) | | **Evaluator-optimizer**: Generate, evaluate, improve loop | [📖](https://docs.restate.dev/ai/patterns/workflow-evaluator) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/workflow_evaluator_optimizer.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/workflow-evaluator-optimizer.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/workflow-evaluator-optimizer.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/workflow_evaluator_optimizer.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/workflow_evaluator_optimizer.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/workflow_evaluator_optimizer.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/workflow_evaluator_optimizer.py) | | **Workflows as tools**: Complex tool logic as separate durable services | [📖](https://docs.restate.dev/ai/patterns/tools) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/parallel_tools_agent.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/parallel-tools-agent.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/parallel-tools-agent.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/parallel_tools_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/parallel_tools_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/parallel_tools_agent.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/parallel_tools_agent.py) | | **Remote agents**: Deploy/scale agents separately with resilient RPC and queuing | [📖](https://docs.restate.dev/ai/patterns/remote-agents) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/remote_agents.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/remote-agents.ts) | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/remote-agents.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/remote_agents.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/remote_agents.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/remote_agents.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/remote_agents.py) | | **Competitive racing agents**: Run parallel agents, use the fastest response, cancel others | [📖](https://docs.restate.dev/ai/patterns/competitive-racing) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/tour-of-agents/app/racing_agents.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/tour-of-agents/src/racing-agents.ts) | - | - | - | - | - | | **Interrupt & regenerate**: Interrupt a running agent with new context; cancel in-flight task and restart | - | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](python-restate-only/examples/interrupt-regenerate/agent.py) [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](typescript-restate-only/examples/interrupt-regenerate/src/agent.ts) | - | - | - | - | - | ### Reliability Guides | Pattern | Docs | Restate + LLM SDK | Vercel AI | OpenAI | ADK | Pydantic AI | LangChain | |---------|------|-------------------|-----------|--------|-----|-------------|-----------| | **Error handling**: Retries and error handling for agents | [📖](https://docs.restate.dev/ai/patterns/error-handling) | - | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/errorhandling) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/tour-of-agents/app/error_handling.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](google-adk/tour-of-agents/app/error_handling.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](pydantic-ai/tour-of-agents/app/error_handling.py) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](langchain-python/tour-of-agents/app/error_handling.py) | | **Rollback**: Saga pattern for compensating failed operations | [📖](https://docs.restate.dev/ai/patterns/rollback) | - | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/tour-of-agents/src/rollback-agent.ts) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/examples/rollback) | - | - | - | ### Frontend Integration | Pattern | Docs | Restate + LLM SDK | Vercel AI | OpenAI | ADK | Pydantic AI | LangChain | |---------|------|-------------------|-----------|--------|-----|-------------|-----------| | **Chat UI integration**: Integrate agents with chat UIs | [📖](https://docs.restate.dev/ai/patterns/chat-ui-integration) | - | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/nextjs-example-app/README.md) | - | - | - | - | | **Streaming responses**: Stream agent responses to clients | [📖](https://docs.restate.dev/ai/patterns/streaming-responses) | - | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/nextjs-example-app/README.md) | - | - | - | - | | **Notify when ready**: Callback when agent completes | [📖](https://docs.restate.dev/ai/patterns/notify-when-ready) | - | - | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](openai-agents/examples/notify_when_ready/agent.py) | - | - | - | ## Integrations ### Protocols | Example | Code | |--------------------------------------------------------------------------------------------------------------------------------------------------------------|------| | **MCP**: Using Restate for exposing tools and resilient orchestration of tool calls | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](mcp/README.md) | | **A2A**: Implement Google's Agent-to-Agent protocol with Restate as resilient, scalable task orchestrator | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](a2a/README.md) | ### AI Observability | Integration | Restate + LLM SDK | OpenAI Agents | Google ADK | Pydantic AI | |----------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------| | **Langfuse** | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="20" height="20">](python-restate-only/examples/langfuse/README.md) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="20" height="20">](openai-agents/examples/langfuse/README.md) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="20" height="20">](google-adk/examples/langfuse/README.md) | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="20" height="20">](pydantic-ai/examples/langfuse/README.md) | | **Arize Phoenix** | - | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="20" height="20">](openai-agents/examples/arize_phoenix/README.md) | - | - | | **Pydantic LogFire** | - | - | - | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="20" height="20">](pydantic-ai/examples/logfire/README.md) | | **Braintrust** | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="20" height="20">](typescript-restate-only/examples/braintrust/README.md) | - | - | - | ### Others | Example | Code | |--------------------------------------------------------------------------------------------------------------------------------------------------------------|------| | **NextJS Template**: Minimal example of Restate + AI SDK + NextJS | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/nextjs-template/README.md) | | **NextJS Example App**: Example app of Restate + AI SDK + NextJS with tools, chat, pubsub,... | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](vercel-ai/nextjs-example-app/README.md) | ## Advanced Examples Larger, end-to-end applications (in separate repos) showing how Restate holds up in real-world agentic systems. | Example | Code | |--------------------------------------------------------------------------------------------------------------------------------------------------------------|------| | **Coding agent**: orchestrates multi-turn conversations and coordinates subagents over sandboxed task execution | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](https://github.com/igalshilman/agent47) | | **Deep Research Agent**: Autonomous multi-day research agent (news digests, human-approved plans, parallel investigations) with Restate + LangChain + Tavily | [<img src="https://skillicons.dev/icons?i=python&theme=light" width="24" height="24">](https://github.com/gvdongen/resilient-research-agent) | | **Supervisor Agent**: Supervisor pattern with policy gates, audit trails, and escalation ladders for security remediation workflows | [<img src="https://skillicons.dev/icons?i=ts&theme=light" width="24" height="24">](https://github.com/gvdongen/resilient-supervisor-agent) | ## Supported Languages Restate currently supports 6 languages: [](https://docs.restate.dev/develop/ts/overview) [](https://docs.restate.dev/develop/python/overview) [](https://docs.restate.dev/develop/java/overview) [](https://docs.restate.dev/develop/java/overview) [](https://docs.restate.dev/develop/go/overview) [](https://docs.rs/restate-sdk/latest/restate_sdk/) The examples can be translated to any of the supported languages. Join our [Discord](https://discord.restate.dev)/[Slack](https://slack.restate.dev) to get help with translating an examples to your language of choice. ## Using AI coding tools If you use Claude Code, Codex, or Cursor to build on Restate, we highly recommend installing the [Restate plugin](https://github.com/restatedev/skills). It bundles skills, prompts, and context that help AI coding assistants generate correct, idiomatic Restate code across all supported SDKs. Most templates in this repo install the plugin automatically — see the [skills repo](https://github.com/restatedev/skills) for setup instructions. ## Learn more - [AI Documentation](https://docs.restate.dev/ai) - [Examples on workflows, microservice orchestration, async tasks, event processing](https://github.com/restatedev/examples) - [Restate Cloud](https://restate.dev/cloud/) - [Discord](https://discord.restate.dev) / [Slack](https://slack.restate.dev)