Hi all, I'm the creator and maintainer of Dapr. Today we announced an agentic AI framework that allows developers to run thousands of agents on a single core that can scale to/from zero with minimal latency, with a durable execution engine that supports automatic retries. Us maintainers would very much appreciate your feedback
Interested to see how the "messaging" protocols will work at this scale with use of pub/sub for agent communication (https://dapr.github.io/dapr-agents/home/principles/#5-messag...).