Dapr Agents: A New Era in Building AI Agents
Background
Back in 2019, Microsoft open-sourced Dapr, a new runtime for making building distributed microservice-based applications easier. At the time, nobody was talking about AI agents yet, but as it turns out, Dapr had some of the fundamental building blocks for supporting AI agents built-in from the outset. That’s because one of Dapr’s core features is a concept of virtual actors, which can receive and process messages, independently from all the other actors in the system.
Introducing Dapr Agents
Today, the Dapr team is launching Dapr Agents, its take on helping developers build AI agents by providing them with a lot of the building blocks to do so.
Key Features
"DAPR Agents are a very good use case for Dapr," Dapr co-creator and maintainer Yaron Schneider explained. "From a technical perspective, you could use actors as a very lightweight way to run these agents and really be able to run them at scale with state — and be resource-efficient. This is all great, but then, there is still a lot of business logic you need to write. The statefulness and the orchestration of it are just one part. And many people, they might choose a workflow engine or an actor framework, but there’s still a lot of work they need to do to actually write the agent logic on the other side. There is lots of agent frameworks out there, but they don’t have the same level of orchestration and statefulness that Dapr has."
How it Works
To efficiently coordinate those agents, you do need an orchestration engine and statefulness, the team argues — which is exactly what Dapr delivers. That’s in part because Dapr’s actors are meant to be extremely efficient and able to spin up within milliseconds when a message comes in (and shut down, with their state preserved, when their job is done).
Current Support
Right now, Dapr Agents can talk to most of the popular model providers out of the box. These include AWS Bedrock, OpenAI, Anthropic, Mistral, and Hugging Face. Support for local LLMs will arrive very soon.
Extensibility
On top of interacting with these models, since Dapr Agents extend the existing Dapr framework, developers also get the ability to define a list of tools that the agent can then use to fulfill a given task.
Language Support
Currently, Dapr Agents supports Python, with .NET support launching soon. Java, JavaScript, and Go will follow soon.
Conclusion
Dapr Agents is a significant step forward in building AI agents, providing a robust and efficient way to develop and deploy AI-powered applications. With its ability to support multiple languages and model providers, Dapr Agents is poised to revolutionize the way we build AI agents.
Frequently Asked Questions
Q: What is Dapr Agents?
A: Dapr Agents is a new agent framework built on top of the Dapr runtime, designed to help developers build AI agents.
Q: What are the key features of Dapr Agents?
A: Key features include support for virtual actors, statefulness, and orchestration, making it easy to build and deploy AI agents.
Q: What languages does Dapr Agents support?
A: Currently, Dapr Agents supports Python, with .NET support launching soon. Java, JavaScript, and Go will follow.
Q: What model providers does Dapr Agents support?
A: Dapr Agents supports AWS Bedrock, OpenAI, Anthropic, Mistral, and Hugging Face, with local LLMs arriving soon.
