\n<\/p>\n
Back in 2019, Microsoft open-sourced Dapr<\/a>, 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\u2019s because one of Dapr\u2019s core features is a concept of virtual actors<\/a>, which can receive and process messages, independently from all the other actors in the system.<\/p>\n 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. <\/p>\n \u201cAgents are a very good use case for Dapr,\u201d Dapr co-creator and maintainer Yaron Schneider explained. \u201cFrom 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 \u2014 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\u2019s 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\u2019t have the same level of orchestration and statefulness that Dapr has.\u201d<\/p>\n