LangGraph + Dapr

Make your LangGraph agents production-ready. These tutorials show you how to add fault tolerance using Dapr.

Start here

Quickstarts

• Quickstart

Secure it

• Access policies

Learn hands-on

🎓Durable Execution & Dapr University · Learn this hands-onMake LangGraph agents durable with Dapr Workflow: Schedule PlannerCrash a LangGraph agent mid-run and watch Dapr Workflow resume it where it stopped. No API key needed.Intermediate30 minPythonStart the track →🎓Durable Execution & Dapr University · Learn this hands-onMake LangGraph agents durable with Dapr Workflow: Supply Chain AuditorRun an agent that audits a dependency bump for supply-chain attacks, crash it, and resume without repeating the LLM call.Intermediate30 minPythonStart the track →

Why Dapr for LangGraph?

Challenge	Dapr Solution
Graph crashes lose all progress	Durable workflows checkpoint every node
Agents tightly coupled, hard to scale	Pub/sub decouples communication
Chat memory lost on restart	State store persists agent memory across restarts
Custom retry logic everywhere	Built-in retries with exponential backoff

Take it to production

• Run your agent on your cluster with Deploy to Kubernetes.
• Watch runs, token use and failures in Operate agents.
• Cap what an agent can spend with token budgets.