← All projects
Running AI at scale

Dapr

Behind-the-scenes software that keeps multi-step apps and AI agents running reliably, even when servers crash.

What it does

Dapr is a runtime (software that runs alongside your app) for building large applications spread across many machines. It gives developers ready-made building blocks for common hard problems: saving progress, sending messages between services, keeping secrets safe and securing communication.

Its standout feature is "durable execution": long, multi-step workflows that pick up where they left off after a crash or restart instead of starting over. The same tools support AI agents, with memory between conversations, coordination of several agents, human approval steps and a consistent way to call AI models.

It works with many programming languages and runs on cloud services, Kubernetes, ordinary servers, laptops and small edge devices. It is a graduated project of the Cloud Native Computing Foundation.

Who it's for

Software teams building dependable business systems or production AI agents.

Can I use it without coding?

Developers only. Infrastructure software for developers and operations teams. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Server, Cloud
Computer
Made for servers or data centres
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it